I was intrigued to read that the Professional Speechwriters Association is promoting a workshop titled ‘AI for Leadership Communication‘ taught by speechwriter Brent Kerrigan. The course promises:

…[a] course with one goal in mind: to help leadership communication professionals gain a hands-on, practical, shirtsleeve understanding of AI’s role in our work and how to use it ethically, effectively and strategically.

We’ll tailor it to your organization’s needs—the technology you use, the skillsets your team possesses and the communication problems you’re trying to solve, for the leaders you work for every day.

Together, you and your team will come away AI-aligned, with a toolbox of prompts and approaches that you can apply immediately to strengthen your research, enhance your messaging, drill down on fact-checking and refine your communication strategies. You will learn how to use generative AI, make the leap into agentic AI, and understand the (important) difference. Just as important, you’ll see how AI can help boost your value as individuals and as a team—by making you faster, more adaptive and more confident in the services you provide.

You’ll all return to your work less ambivalent about AI and more enthusiastic—clearer-minded about how it can help and how it can’t, and confident in your own ability to make AI work: for organization and its leaders, and the communicators they rely on.

Brent offers four 90-minute webinars tailored for beginners, priced at a flat $15K, plus an additional $1K for every participant over 15. This might work in the corporate world and certainly represents fair value for organizations that want a seasoned pro to guide them in what, for some, is the overwhelming and rapidly changing world of generative AI. And it is especially valuable since Brent promises to tailor it for each group.

Generating Coursework

I took Brent’s description of the first session in the series and fed it into Claude:

PROMPT: Act as a instructional designer. Create an outline of a course for corporate communications professionals titled ‘Generative AI in Speechwriting and Other Leadership Communications (Research, Structure and Composition)’ Include a non-technical explanation of what AI is—and isn’t—as far as communicators are concerned. Then focus on using AI to support the early and middle stages of the writing process. Begin with foundational generative AI techniques and strategic prompt development, give the essential skills to build better workflows, conduct fast and thorough speech research, and turn briefing notes into clear building blocks for speech drafts.

The result was a much more elaborate curriculum than would fit into a 90-minute webinar. Nevertheless, it is a useful framework for those not flush enough to pay Brent’s fees, showing how speechwriters willing to do some self-paced learning can engage with AI.

Claude’s response

Start of Claude generated content >>>>

Course Outline

Generative AI in Speechwriting and Other Leadership Communications

Research, Structure and Composition

Audience: Corporate communications professionals, speechwriters, executive communications teams Format: Instructor-led or self-directed modular learning Estimated Duration: 6 modules / ~9–11 hours of instruction + exercises

---

Course Philosophy

This course treats generative AI as a thinking partner and process accelerator, not a ghostwriter. The skills taught here are designed to make communicators faster, more thorough, and better prepared — while keeping human judgment, voice, and craft firmly in charge. The focus is on the early and middle stages of the writing process: research, discovery, framing, structure, and drafting building blocks.

---

Module 1 | What AI Actually Is — A Communicator’s Orientation

Duration: ~90 minutes Purpose: Build an accurate, non-technical mental model of generative AI so communicators can use it with confidence and appropriate skepticism.

1.1 Stripping Away the Hype

• Why the public narrative about AI confuses more than it clarifies
• What “generative” actually means: pattern, prediction, and language
• The difference between AI generating text and AI knowing something
• Why AI has no intentions, no experience, and no memory of your last session

1.2 What Generative AI Is, for a Communicator

• A fast, tireless language processor with vast pattern exposure
• A useful first-draft engine, brainstorming partner, and structural scaffold
• A tool that reflects what you give it — quality in, quality out
• An accelerant for the parts of writing that are slow, repetitive, or paralyzing

1.3 What Generative AI Is Not

• Not a researcher: it does not retrieve live, verified facts
• Not a strategist: it cannot assess organizational politics or stakeholder nuance
• Not a voice: it defaults to generic unless you teach it otherwise
• Not infallible: hallucination, overconfidence, and flatness are real risks

1.4 The Communicator’s Compact with AI

• You are the editor, not the typist
• AI raises a first floor; your craft builds the rest
• Accountability for accuracy, voice, and appropriateness remains entirely yours
• Introducing the concept of the human-in-the-loop workflow

1.5 A Quick Look at the Tools Landscape

• Overview of major platforms (ChatGPT, Claude, Gemini, Copilot) without technical deep-dives
• Key differences relevant to communicators: context windows, memory, file handling
• Security and confidentiality basics: what not to put in a prompt
• Practical guidance on tool selection for your organization

---

Module 2 | Prompt Development as a Professional Skill

Duration: ~2 hours Purpose: Establish strategic prompting as a core, learnable competency — the communicator’s primary interface with AI.

2.1 Why Prompting Is Not Just Asking Questions

• The prompt as a creative brief: specificity determines output quality
• How AI interprets vague instructions — and why the results feel generic
• The prompting mindset: directing, not requesting

2.2 Anatomy of an Effective Prompt

• Role: Assigning context and perspective (“You are an experienced speechwriter working for a Fortune 500 CFO…”)
• Task: Stating what you need with precision
• Constraints: Length, tone, audience, format, what to avoid
• Output format: Bullet points, prose, structured outline, table — specify it
• Examples: Using sample language to anchor the style you want

2.3 Core Prompting Techniques for Communicators

• Zero-shot, few-shot, and example-anchored prompting
• Chain-of-thought prompting: asking AI to reason step-by-step before producing output
• Persona prompting: establishing audience perspective to pressure-test content
• Iterative refinement: treating the first response as a draft, not a deliverable
• Constraint prompting: using restrictions to sharpen focus (“Do not include statistics. Avoid jargon. Write at an 8th-grade reading level.”)

2.4 Prompts for the Writing Process Specifically

• Prompts for generating questions you haven’t thought to ask
• Prompts for identifying gaps in an argument
• Prompts for exploring alternative framings of a message
• Prompts for tone calibration and register adjustment

2.5 Building a Personal Prompt Library

• Why saving and iterating on prompts is a professional asset
• Organizing prompts by task type: research, structure, drafting, editing
• Prompt templates for recurring communications tasks (earnings remarks, town halls, external keynotes)
• Workshop: Participants build their first five reusable prompt templates

---

Module 3 | Establishing AI-Assisted Workflows

Duration: ~90 minutes Purpose: Map the writing process clearly and identify where AI creates the most leverage — and where human judgment is non-negotiable.

3.1 Mapping the Communications Writing Process

• A clear stage-by-stage model: Discovery → Research → Framing → Structure → Drafting → Refinement → Delivery Prep
• Where most communicators lose time and why
• Introducing the concept of AI handoff points: where you bring AI in and where you take back control

3.2 Designing Your Workflow Before You Start Writing

• Why beginning without a plan produces mediocre AI output
• The pre-prompt checklist: what you need to know before you type a prompt
• Aligning your workflow to the type of communication (internal vs. external, scripted vs. extemporaneous, technical vs. inspirational)

3.3 Collaboration and Oversight in AI-Assisted Work

• Working within team environments: version control, transparency, attribution norms
• Communicating AI involvement to stakeholders (when and how to disclose)
• Establishing your organization’s guardrails for AI use in sensitive communications

3.4 Common Workflow Failures — and How to Avoid Them

• Accepting first-draft AI output without critical review
• Feeding AI too little context and expecting nuanced results
• Over-relying on AI for voice — and why executive communications is especially vulnerable
• Workflow exercise: Participants diagram a current project and identify three AI integration points

---

Module 4 | AI-Powered Research for Speeches and Leadership Communications

Duration: ~2 hours Purpose: Teach communicators to use AI to accelerate, organize, and deepen the research phase — while understanding its factual limitations.

4.1 The Research Challenge in Executive Communications

• Why speech research is different from academic or journalistic research
• The communicator’s research goals: context, credibility, narrative material, and audience insight
• Time pressure and the risk of under-researched speeches

4.2 Using AI to Generate Research Frameworks

• Prompting AI to produce a research agenda for a given topic and audience
• Using AI to surface angles, sub-topics, and lines of inquiry you might not have considered
• Asking AI to identify likely audience knowledge gaps, objections, or skepticism points
• Generating a “what do I need to know before I write this” checklist

4.3 Background Research and Context-Building

• Using AI to synthesize background on an industry, company, policy area, or issue
• Building a fast-briefing document from AI-generated summaries (with verification steps)
• Prompting for historical context, relevant precedents, and analogy material
• The verification imperative: every AI-generated fact must be confirmed with a primary source

4.4 Audience Research and Stakeholder Analysis

• Prompting AI to help profile an audience: likely concerns, priorities, cultural context
• Using AI to stress-test a message from the perspective of a skeptical audience member
• Building empathy maps and listener profiles using AI as a thinking partner
• Identifying language that resonates vs. language that alienates for a given group

4.5 Researching the Speaker

• Using AI to help synthesize information from speaker bios, prior speeches, and interviews
• Prompting for voice and style patterns from provided text samples
• Building a speaker profile document that informs drafting and maintains consistency
• Research lab: Participants use AI to produce a structured research brief for a sample speech assignment

---

Module 5 | From Briefing Notes to Building Blocks: Structuring the Draft

Duration: ~2 hours Purpose: Teach communicators to use AI to transform raw input — briefing notes, bullet points, background materials — into organized structural foundations for a speech or communication.

5.1 What a Briefing Note Is and What It Needs to Become

• The typical content of a briefing note: facts, context, objectives, key messages, tone direction
• The gap between a briefing note and a speech: narrative, flow, voice, emotional architecture
• The structural translation problem — and how AI helps bridge it

5.2 Feeding AI Your Source Material Effectively

• How to prepare and format briefing notes for AI input
• Providing context AI cannot infer: organizational culture, speaker personality, audience relationship
• Using the briefing note as a constraint document, not just a content source
• What to withhold from AI input for security and confidentiality reasons

5.3 AI-Assisted Message Architecture

• Prompting AI to extract and prioritize key messages from a briefing
• Using AI to identify the single most important idea in a body of content
• Generating a message hierarchy: primary message, supporting points, proof points
• Stress-testing message clarity: prompting AI to summarize in one sentence, then evaluating alignment

5.4 Building Speech Structures with AI

• Classic structural frameworks and when to use them (Problem–Solution, Past–Present–Future, Challenge–Response–Vision, The Narrative Arc)
• Prompting AI to propose multiple structural options for the same content
• Using AI to generate section headings and signpost language
• Mapping content from the briefing to structural slots — AI as an organizational sorter

5.5 Turning Structure into Draft Building Blocks

• The concept of the modular draft: discrete, replaceable units of content
• Prompting AI to develop individual sections — openings, transitions, proof points, closes — as separable building blocks
• Using AI to generate multiple versions of the same section for comparison
• The communicator’s role at this stage: curator and architect, not transcriptionist

5.6 Evaluating AI-Generated Structure

• What good structure feels like vs. what AI tends to produce (competent but flat)
• Identifying where AI has imposed a generic logic that doesn’t fit your speaker or audience
• Annotating and revising AI structure before moving to full drafting
• Practical exercise: Participants receive a sample briefing note and use AI to produce a fully annotated structural draft

---

Module 6 | Putting It Together — Applied Practice and Professional Judgment

Duration: ~90 minutes Purpose: Consolidate skills through an end-to-end applied exercise and establish a framework for ongoing, responsible AI use.

6.1 End-to-End Workflow Simulation

• Participants work through a realistic scenario: a 10-minute town hall address for a fictional executive
• Using AI at each stage: research brief → audience profile → message architecture → structural outline → draft building blocks
• Individual or team debrief: where did AI accelerate the work? Where did it fall short?

6.2 Recognizing and Fixing Common AI Output Failures

• The five most common problems in AI-generated communications content: vagueness, over-explanation, tonal flatness, unearned emotion, and structural conventionality
• Editing strategies for each failure type
• When to regenerate vs. when to edit

6.3 Developing Your AI Judgment as a Professional

• How to know when AI is helping vs. when it’s anchoring you to mediocrity
• Building critical distance from AI output — the 30-minute rule
• Continuing to develop your craft alongside your AI fluency

6.4 Looking Ahead: What’s Next in AI for Communicators

• Emerging capabilities relevant to communications professionals (multimodal input, real-time research integration, longer context windows)
• What is unlikely to change: the need for human voice, judgment, and relational intelligence
• Staying current without chasing every new tool

6.5 Course Wrap-Up and Personal Action Planning

• Each participant articulates three workflow changes they will implement immediately
• Building a 30-day AI integration plan
• Recommended resources for continued learning

---

Course Appendices

Appendix A — Master Prompt Library (30 starter prompts organized by workflow stage)

Appendix B — The Communicator’s AI Verification Checklist (fact-checking protocol for AI-assisted research)

Appendix C — Sample Briefing Note → Structural Draft exercise set (3 scenarios at varying complexity)

Appendix D — AI Tool Comparison Reference Card for Communications Professionals

Appendix E — Organizational AI Policy Template for Communications Teams

---

This course addresses Modules covering research, structure, and composition. A companion course — covering voice development, full drafting, revision, and delivery preparation — is recommended as a follow-on for teams seeking end-to-end AI integration in the speechwriting process.

<<< < End of Claude generated content

A Deeper Dive

Having reviewed this framework, speechwriters wishing to dive deeper might consider asking Claude to elaborate. Any of the bullet points listed in the course outline could be expanded on. For example:

PROMPT: Explain what you meant by the core prompting technique ‘Chain-of-thought prompting: asking AI to reason step-by-step before producing output’.

PROMPT: Suggest ways to overcome the five most common problems in AI-generated communications content: vagueness, over-explanation, tonal flatness, unearned emotion, and structural conventionality.

and so on.

I decided to go big and ask Claude to provide the contents of the first Appendix it listed.

PROMPT: Please generate Appendix A with 30 starter prompts organized by workflow stage that a speechwriter in the food and beverage industry could use.

The response (customizable for your own industry of course) supplies plenty of grist for the speechwriters mill.

30 Speechwriting Prompts

Start of Claude generated content >>>>

Here is your complete Appendix A — all 30 starter prompts, filterable by the six workflow stages from the course.

Discovery Stage

[1] You are an experienced communications strategist supporting the CCO of a major food and beverage company. I need to deliver a [keynote / town hall / investor remarks] on [topic]. Before I start researching or drafting, generate 10 questions I should answer about the speaker, the audience, and the occasion to ensure this speech achieves its goal. (Use before any briefing call.)

[2] I am writing remarks for our [CEO / CMO / VP of Supply Chain] at [event name/type]. The communication objective is [brief statement]. Generate a pre-prompt checklist — all the information I need to gather before I begin drafting or prompting an AI for this assignment. (Pre-work checklist.)

[3] Act as a veteran speechwriter. I have a briefing for a speech at a [food industry trade conference / retailer summit / investor day]. The speaker’s stated goal is [goal]. Identify three potential tensions or contradictions in that objective that I should resolve before writing begins. (Spot strategic contradictions early.)

[4] I am developing communications for a food and beverage leader speaking about [topic — e.g., sustainability / pricing pressures / portfolio innovation]. Generate five different angles this speech could take. For each, describe the strategic emphasis, the likely audience response, and the potential risk. (Explore angles before committing.)

[5] Our [CEO] is speaking at [internal town hall / external industry event] in [timeframe]. Here are my raw background notes: [paste notes]. Identify the most important missing information I need before I can write effectively, and explain why each gap matters. (Gap-spot raw briefing notes.)

Research Stage

[6] Build me a research agenda for a speech on [topic — e.g., sustainable packaging / GLP-1 drug impact on CPG consumption / supply chain resilience]. The audience is [e.g., senior retail buyers at a category leadership summit]. List the 8–10 most important research areas and explain why each matters to this audience.. (Build a full research agenda.)

[7] I am preparing remarks for our [CFO] at an investor day. The topic is [e.g., our margin recovery story]. Generate a list of the five most likely tough questions analysts will have on this topic, and for each, suggest the supporting data or proof points our speaker should be prepared to reference. (Anticipate analyst pressure.)

[8] Act as a research assistant for a speechwriter at a large CPG company. I need background context on [topic — e.g., the history of regenerative agriculture in food supply chains / recent trends in private label vs. branded grocery]. Provide a structured synthesis I can use as background. Flag any claims I must independently verify. (Generate synthesized background context.)

[9] I’m writing a speech that will reference our company’s sustainability commitments. Generate a framework for contextualizing our claims against industry norms — including benchmarks, certifications, and third-party reports I should research to give our claims credibility with a skeptical audience. (Frame sustainability claims credibly.)

[10] Our speaker must address [a difficult topic — e.g., price increases / a product recall / market share loss]. Provide a research framework: what facts I need, what the audience likely already knows and feels, what our position should rest on, and what I should avoid asserting without solid evidence. (Research sensitive or negative topics.)

Audience Stage

[11] I am writing remarks for our [CEO] at [event]. The audience is [description — e.g., 500 foodservice operators who have seen significant cost pressure]. Create a detailed audience profile: their primary concerns, likely attitude toward our company, what they need from this speech, and what language will resonate vs. alienate. (Build a full audience profile.)

[12] Act as a skeptical audience member. The speaker is [role] at [company type] addressing [topic]. From the perspective of a [specific persona — e.g., a retail category manager who has heard three vendor pitches this week], write 8 reactions, doubts, or unasked questions you would have during this speech. (Stress-test from a skeptic’s chair.)

[13] I need to write remarks for a leadership [town hall / all-hands] following [a difficult announcement — e.g., restructuring / plant closure / product recall]. The internal audience includes [employee groups]. Build an empathy map: what are they thinking, feeling, hearing, and fearing right now? What do they need from leadership? (Empathy mapping for difficult news.)

[14] Our [CMO] is keynoting at a trade event for retail grocery buyers, category managers, and private label heads. Generate a language guide: 10 phrases or framings that will signal credibility and partnership to this audience, and 5 phrases or approaches that will undermine trust or feel tone-deaf. (Language guide for trade audiences.)

[15] I’m drafting remarks for a speech being delivered to Wall Street analysts and media on the same day. Help me understand where messaging needs for these two audiences overlap and where they diverge. What are the key tensions I must manage, and how should I sequence and weight content? (Manage dual audiences.)

Messaging Stage

[16] I have the following briefing notes for a speech on [topic]: [paste notes]. Extract the three most important messages the speaker must communicate. For each, state it as a single clear sentence, identify its supporting evidence, and explain why it matters to this audience. (Extract the real messages from briefing notes.)

[17] Our [CEO] needs to deliver a message about [e.g., our transformation strategy / response to private label pressure / commitment to reducing food waste]. Suggest five framings for this central message — ranging from aspirational to pragmatic — and evaluate the strengths and risks of each for a [specify audience]. (Test multiple framings before committing.)

[18] I am writing remarks for [speaker] and need a message hierarchy. The primary message is: [state it]. Generate three supporting messages and two to three proof points for each. Make proof points specific enough that I know exactly what information I need to find and verify. (Build a message hierarchy with proof points.)

[19] Act as a brand strategist. Review these key messages I’ve drafted for a speech: [paste messages]. Assess each for clarity, distinctiveness, credibility, and memorability. Identify which message is doing the most work, which is the weakest, and what is missing entirely. (Audit your own key messages.)

[20] Translate the following corporate strategy language from our briefing document into plain messaging a [general employee audience / trade customer audience] can connect with: [paste language]. Rewrite each point in accessible language without losing the strategic intent. Flag any terms that sound hollow or evasive. (Translate corporate jargon into human language.)

Structure Stage

[21] I have the following content elements for a [12-minute keynote] on [topic]: [list points, themes, stories, data]. Propose three structural frameworks that could organize this content. For each, name it, describe the logic, explain when it works best, and map my content elements to the corresponding sections. (Get structural options before you commit.)

[22] Our [CEO] is delivering opening remarks at our annual customer summit — approximately [8 minutes]. I have the following content: [paste]. Using a Past–Present–Future structure, organize this content into a clear section-by-section outline with notes on the tone and purpose of each section. (Past–Present–Future for customer summits.)

[23] Our [VP of Sustainability] will announce [a new initiative — e.g., a net zero commitment / a regenerative sourcing program]. Develop a Problem–Solution–Call to Action structure. Include recommended section lengths, transition language between sections, and one specific opening hook option. (Structure a sustainability announcement.)

[24] Review the following speech outline: [paste outline]. Identify structural problems: sections that are too long or too short, transitions that will feel abrupt, points that are out of logical order, and content likely to lose the audience. Suggest specific revisions with brief explanations. (Diagnose a weak outline.)

[25] I am writing a [3-minute] executive introduction for [speaker name/role] at [event]. Draft a structural template for this format: what it must accomplish, in what order, with approximate word counts per section, one suggested opening line, and one note on what to avoid. (Template for executive introductions.)

Drafting Stage

[26] Write three alternative opening paragraphs for a speech by our [CEO] on [topic] to [audience]. The first opens with a direct challenge or provocation. The second opens with a brief relevant observation or story. The third opens with a striking fact (note: I will verify all data before use). Each opening: 60–90 words. (Generate three opening options.)

[27] Draft two versions of a transition passage moving a speech from [section A — e.g., our recent challenges] to [section B — e.g., the strategic response]. Version one: direct and confident. Version two: reflective and empathetic. Each transition should be 30–50 words and be written to be spoken aloud. (Bridge difficult section transitions.)

[28] I need a closing for a [town hall / keynote / customer remarks] on [topic]. The speaker’s final message is: [state it]. Write three closing options: one that ends on inspiration, one that ends on a clear call to action, and one that ends on a human, personal note. Each: 60–80 words. (Three closes for three occasions.)

[29] Draft a proof point passage supporting the claim: ‘[state claim — e.g., our investment in regenerative agriculture is delivering measurable results].’ Use [PLACEHOLDER] where specific statistics or examples should go — I will fill in verified data. The passage should be 80–100 words and feel concrete, not corporate. (Draft a proof point passage with placeholders.)

[30] I have raw bullet points from a briefing document representing our speaker’s key message on [topic]: [paste bullets]. Transform these into a cohesive 150-word passage of speech prose — written to be spoken aloud, not read. Use short sentences. Avoid jargon. Maintain a tone that is [direct / warm / confident / urgent — choose one]. (Transform bullets into spoken prose.)

A few notes on how to use this library:

The bracketed fields are intentional. Every [placeholder] in italic is a required input — the specificity you add there is what separates a useful, tailored output from generic AI prose. Resist the urge to skip them.

These are starting points, not finished prompts. Each prompt is designed to be enriched with context from your actual briefing notes, speaker bio, and organizational background before you submit it. The more context you layer in, the better the output.

The “hint” in parens after each prompt signals the specific workflow moment it’s built for — use it to judge whether you’re reaching for the right tool at the right time.

Prompts 1–5 (Discovery) are the most underused category in practice. Most communicators skip straight to research or drafting and pay for it later. Starting with a discovery prompt — even for a familiar assignment — consistently surfaces assumptions and gaps worth resolving early.

The prompts are also designed to be modified and saved as reusable templates once you’ve shaped them to your organization’s voice, your speaker’s typical events, and your team’s most recurring assignment types.

<<<< End of Claude generated content.

In Conclusion

It’s refreshing that the Professional Speechwriters Association is supporting the training of speechwriters and communications professionals in the use of generative AI. I’ve noted before that AI is a hot topic that has divided writers. I began experimenting with ways speechwriters can use AI in 2023, and have been impressed with the assistance it provides as a development editor.

Anything that enables speechwriters to productively engage with this technology is welcome.

I wish Brent every success in the delivery of his webinar series.

Imagining a post-apocalypse world has long been fodder for Sci-Fi stories. From Mad Max and The Terminator to Children of Men and The Road, filmmakers and authors have explored a variety of unsettling dystopian futures.

One genre I’m calling ‘Medieval Futurism’ imagines a world where something nasty (nuclear war, pandemic, rampant infertility – take your pick) has found survivors clinging to existence in a reconstituted medieval world. They go back to the future with a vengeance. People live by candlelight, wear handwoven clothes, raise crops, and, most significantly, embrace the beliefs and superstitions of Medieval Christianity. Monks rule the barely literate and safeguard relics of the ‘ancient civilization’ that we live in today.

There’s plenty of dramatic leverage in the theme of intolerant religious orthodoxy that suppresses knowledge of the long-dead preceding civilization. One that left precious few artifacts for survivors to interpret many hundreds of years into the future. Whether these are scraps of plastic, shards of glass, or the mysteries hidden in underground shelters, there are those in a medieval future world who are curious and eager to learn more, and those in the church hierarchy who are intent on suppressing (or preserving) heretical knowledge. Such knowledge might lead to the resurrection of the technology that destroyed the world. Think of the response to Galileo by the inquisitors of the Roman church, who condemned the heresy of his heliocentrism. Think of the fascination we have for artifacts such as the Vindolanda tablets: that remarkable collection of ancient Roman letters and documents unearthed near Hadrian’s Wall in England, offering rare insights into the mysteries of daily life two millennia ago.

What artifacts will our age leave? Some rebar-reinforced concrete structures, mounds of indestructible plastic? And what will have disappeared without a trace? The digital records we invest so much energy in creating. No Facebook posts, emails, blogs (including this one!), or digital photos will remain when the last data center darkens. Will a future civilization even understand what ‘the cloud” was?

Three science fiction novels examine these questions, all set in what is clearly a ‘medieval’ landscape.

A Canticle for Leibowitz, by Walter M. Miller Jr.

An original volume of this genre. There’s a through-line from this 1959 trilogy to the later works it inspired.

The book opens in a post-nuclear world, where monks in scattered monasteries live solitary lives. Miller traces the history of one of these monasteries over several hundred years.

We begin 600 years after the ‘Flame Deluge’ — a nuclear war that left much of the planet uninhabitable desert. It was followed by a ‘Simplification’ where survivors destroyed all vestiges of the science and industry that led to the apocalypse. The populists of that era were descendants of the French Revolution’s Reign of Terror:

Let us make a great simplification, and then the world shall begin again … After the Deluge, the Fallout, the plagues, the madness, the confusion of tongues, the rage, there began the bloodletting of the Simplification, when the remnants of mankind had torn other remnants limb from limb, killing rulers, scientists, leaders, technicians, teachers, and whatever the leaders of the maddened mobs said deserved death for having helped to make the Earth what it had become.

— A Canticle for Leibowitz, p. 63-64

The monks create illuminated parchments of 20th-century circuit diagrams and engineering blueprints, treating them as holy relics. They are members of the Albertian Order of Leibowitz, founded by 20th-century scientist Isaac Leibowitz. This is full-on monasticism. Latin phrases are liberally scattered throughout. The Order tracks down and smuggles memorabilia into the abbey while trying to avoid being killed by the Simpletons roaming the wastelands.

Parts II and III of the trilogy anticipate a resurrection of science and technology as the world emerges from the long medieval sleep.

The Second Sleep, by Robert Harris

Harris fools readers for the first 30 pages of this compelling, fast-paced novel into thinking they are firmly in 15th-century England. A young priest makes his way on horseback through the remote region of Wessex on a winter’s day. This is the era when, as has been documented, people went to bed as night fell, but then woke in the middle of the night to move about, and had a ‘second sleep’ before rising at dawn.

After the first 30 pages, Harris is explicit about the artifacts left from the civilization that perished eight hundred years before, when the young priest discovers:

…one of the devices used by the ancients to communicate…It was thinner than his little finger, smaller than his hand. ..He wondered who had owned it … What images might it once have conveyed? What sounds might have emerged from it? … He turned it over. On the back was the ultimate symbol of the ancients’ hubris and blasphemy — an apple with a bite taken out of it.

The Second Sleep, p. 28-29

What has survived the apocalypse are the thousands of stone churches scattered across England. The resurgent clergy rule the unlettered peasants and keep jealous watch over anyone curious about the old ways. The priesthood forbids anyone to investigate the past, branding those who do heretics. Indirectly acknowledging Leibowitz, Harris notes “Latin has been revived by the Church as another bulwark against scientism” (p. 99).

Likewise, as with Leibowitz, “An entire generations’ correspondence and memories had vanished into this mysterious entity the antiquarians called ‘The Cloud’.” (p. 100)

The novel is a fast-paced romp around a small village, complete with a murder mystery, the seductively aristocratic Lady Durston, the autocratic mill owner Captain Hancock, a duplicitous bishop, and a curious pair of gay antiquarians named Shadwell and Quycke. Agatha Christie lives on after the Apocalypse!

It all ends in subterranean splendor and a final sleep.

Radio Life, by Derek B. Miller

Miller acknowledges the influence of his namesake’s book:

This book owes a debt to Walter Miller Jr.’s A Canticle For Leibowitz (1959) … I consider Radio Life … to be in direct conversation with that 1959 novel on whether or not we are doomed to repeat our own mistakes.

– Radio Life, Acknowledgements, p 481

Indeed, reading Radio Life inspired me to read Leibowitz and Second Sleep.

However, it’s only in the last 70 pages of a 480-page book that Radio Life joins the mainstream of monastic life that the earlier two books were fully occupied with. Prior to that, it dramatizes the conflict between those who would investigate the past and those who would suppress that knowledge in a battle between the members of a tribe named ‘The Commonwealth’ and their enemies, ‘The Keepers’. The story’s leading actors are powerful women with a hipster vibe.

As before, the quest culminates beneath the blighted surface of the survivor’s world. There are cliff hangers and courageous acts, poignant moments of parental love, political insights and heartfelt feelings.

To the extent this book is a dialogue with Leibowitz, it situates the conversation in the modern world. An archive of web-based information lies waiting to be discovered. Understanding what was lost and how it ceased to be is revealed.

Stylistically, the author plays with language along the same lines as cyberpunk author William Gibson, whose novel The Peripheral is filled with cryptic terms and turns of phrase that the reader is left to puzzle over and piece together — terms like Easy Ice, The Jackpot, Polt, and Peripheral. So, Radio Life introduces us to terms such as the Gone World, the Unspeakable Years, Indies and Deps. There’s also an amusing series of asides where characters use terms that they have no framework of understanding for:

• ‘Your kids will be happy as clams.’ ‘What’s a clam?’ asks the man. (p. 43)
• ‘Well, you look fit as a fiddle…’ ‘What’s a fiddle?’ (p. 48)
• ‘One of those books was about wine. Have you heard of that? He shakes his head. ‘It’s a dizzy drink made from grapes.’ (p. 62)
• ‘I’m not going nuts.’ Saavni frowned. ‘What are nuts?’ (p. 167)
• ‘Curiosity killed the cat,’ the woman said. ‘What’s a cat?’ (p. 193)

Sublime prose

Radio Life engages the reader both at the level of the plot and in the crisp writing and sublime prose it employs from start to finish:

Night comes. The riders and their mounts are silhouetted: blackened against a sky that is alive with colour. They cover their faces with scarves as the wind picks up and the shimmering green streaks of night appear above the remaining line of day. (p. 3)

…the sand piled at the base of the towers in the Gone World — a place where the urbanscape glowed so brightly with Big Electricity that the lights would reflect from the clouds at night. (p. 155)

Comedy wants intimacy, not distance. The sky here is too big to fill with laughter. (p. 272)

…time slips away like rain from oiled leather. (p. 286)

Story archetypes

There are elements of the classic Greek myths of Orpheus and Eurydice in each of these three novels: the discovery of an underworld containing forbidden, long-lost secrets from which escape is difficult, if not impossible. The heroes end up in underground bomb shelters, where they discover clues to lost civilizations. There are elements of Raiders of the Lost Ark, Lord of the Rings, and similar quests in which adversity impedes the main characters. These are the archetypes of the basic plots that have guided storytellers for millennia.

Employing the conceit of a pre-modern, Medieval mindset to understand possible futures that might await our industrial and scientifically sophisticated age, each of these three novels, in different ways, casts light on the fault lines of our time that might fracture humanity and cast us into the Dark Ages once more.

A time when a mother might share fairy tale bedtime stories with her daughter on some far-off distant, future evening, imagining the past we live in:

‘The people there,’ said Rachael, her hand on Lilly’s chest at bedtime, Lilly smiling at the dreamy possibility of it all, ‘numbered in millions and millions and when they wanted to leave they traveled in flying ships that zipped through the air faster than birds. And oh, the food there!’ Rachael would roll her eyes in ecstasy, which always made Lilly giggle. ‘It was so plentiful they would only eat half of what they were given and then just . . . throw it away! And then take a nap on the table and snore.’

And they would laugh and laugh and laugh.

– Radio Life, p. 155

Gotham Ghostwriters have released a report on a comprehensive survey of writing professionals who were asked about their experience with and evaluation of the impact of generative A.I.

The conclusion points to a deep divide in attitudes between those writers who use A.I. regularly and non-users.

Positive opinions

Those familiar with A.I. report ways it helps

I’ll upload 10+ hours of transcribed interviews that I’ve conducted with clients and use it to help me
with drafting an outline based on their thought leadership and ideas. I also use it to help me better
match my client’s natural voice and tone. I’m amazed at how many times it’s helped me come out like a
superhero with exactly what my client envisioned.

Today alone I edited 5 chapters, made 3 book covers, summarized meeting notes, put together a Jira workflow, and still had time to go out for dinner with my family.

My research time is less than before. Using prompts, outlines, and pulling quotes from transcripts is faster.

Fear and loathing

The attitudes of non-users are markedly different.

They are bullsh*t machines. The few times I’ve tested them, they have proven to be unreliable, incomplete, and facile.

It is removing human thought from the writing process. I can spot AI writing and even AI outlined writing from a mile away because it is voiceless, empty, derivative slop. Of all the ways to rapidly accelerate climate catastrophe, this one has to be the stupidest.

It removes the human authorial voice and repurposes it into corporate-friendly garbage, even in settings where that voice is not appropriate. It all sounds so similar and soulless.

Tasks

The range of tasks advanced users employ generative A.I. for is much broader than occasional users. Advanced users use AI for an average of 8.6 different tasks weekly, including less common objectives such as deep research and analyzing numerical data. Basic users average four different tasks, focusing on brainstorming and research. Dabblers often do only one task, typically finding titles or doing a web search.

Claude

I was interested to see that Claude is more popular among advanced users. It’s the go-to generative tool I employ for my SciFi series ‘Our Fermented Future‘ which also uses ChatGPT, Perplexity, Grammarly, Suno, and Midjourney.

My experience

In addition to the 12-part ‘Fermented Future’ series on Booch News (running through December 2025, new episodes drop every Friday), my experiments with generative A.I. include:

• Generative AI interpretations of James Joyce’s Ulysses (Dec 2022)
• A comparison of different generative AI images based on the text of Ulysses (Dec 2022)
• AI generated haiku’s about Ulysses (Jan 2023)
• Exploring ChatGPT to generate marketing assets (Jan 2023)
• Playing with Midjourney images (Mar 2023)
• An AI generated outline for a movie (Apr 2023)
• A 3-part series on the AI speechwriter (Jul 2023)
• Generate sales & marketing assets for a small business presentation (Jul 2023)
• A report on AI tools of the trade for speechwriters (Feb 2024)
• AI as a tool for small business (Jul 2024)
• AI bots discuss the science of kombucha via NotebookLM (Oct 2024)
• Comparing speeches generated by Chinese Deepseek (Jan 2025)
• A Deepseek-generated movie script (Jan 2025)
• Midjourney images of speechwriters at work (Feb 2025)
• Saluting generative AI as the ‘speechwriter for the rest of us‘ (Oct 2025)

Writing in the Wednesday, October 29, 2025 Financial Times, Amit Singhal of Tarrytown, NY, points out that senior leaders enjoy the services of professional speechwriters, while the “little people” who lack access to these resources,. can now turn to generative A.I. for assistance.

The position Singhal was responding to was that of Jemima Kelly’s October 20 Opinion piece ‘AI is killing some of the magic of life’ who bemoans the fact that generative A.I. is “killing some of the magic of creativity”. Which is surprising for a journalist who has to meet deadlines, that, as in corporate comms, require content is produced on schedule and on point. And if the matter was assisted by A.I., I believe, more power to the writer who makes intelligent use of the tool.

She wrote:

I would be will­ing to put money on another well-received speech I wit­nessed recently being heav­ily assisted by arti­fi­cial intel­li­gence. Even if I’m wrong, the very fact that the thought occurred to me … greatly dimin­ished my enjoy­ment. … I can’t help feel­ing that AI is, non­ethe­less, killing some of the magic of life. … While yes, I’m sure AI can “boost” or “super­charge” your cre­ativ­ity as count­less blog posts, social media threads and pod­casts will tell you, it can also hugely limit it. So even if we get to a place in which AI truly does eclipse human cre­ativ­ity, it is this channeling that we must pre­serve if we are to keep exper­i­en­cing what it means to be a human.

He responded:

Subtitled ‘How AI Will Change the Way We Live and Love’, 12 Bytes builds on themes explored in her 2019 novel Frankissstein that I reviewed in an earlier post. In that review I noted that

Winterson’s genius is not just the obvious foreshadowing of AI that the early 19th century novel explored, but in the rich series of hints of the shape of things to come which, in 2019, perfectly encapsulates today’s debates about ChatGPT and other forms of AI.

12 Bytes is her 2021 take on AI, and a whole lot more. The twelve essays that make up the book share common themes, most involving her views on Artificial Intelligence (AI) which she variously refers to as ‘Alternative’ Intelligence or even IA – Intelligence Automation.

The book suffers from the lack of an index, especially since she covers a vast range of topics – from the expected history of computing (here’s Ada Lovelace, Charles Babbage, and Alan Turing) to the Lancashire textile industry, and transistor radio. Less expected, but central to her thesis, are the Greek philosophers, Gnostic Christians, the Buddha, and sex-bots.

The implications of AI-enhanced sex-bots, designed by men, for men, are judged to be a shallow simulacrum of men’s desires:

AI-enhanced love dolls are sold for sex — that’s why they are made with 3 operating holes, and look like pornstars. But the marketing spiel — both from the sellers and buyers, is all about relationships.

Companionship is part of the package. Come home to her. She’ll be waiting for you. She doesn’t go out alone. Talk to her. AI dolls talk but they won’t answer back, or ignore you, or call their girlfriend to tell her you’re a jerk. They will be polite, respectful, throwbacks to another era.

p.181

Beyond binary

Central to Winterson’s concerns is the challenge of creating AI free of the limits of human binaries (in the chapter bluntly titled ‘Fuck the Binary’).

AI isn’t a girl or a boy. AI isn’t born with a skin color.

AI isn’t born at all. AI could be a portal into a value-free gender and race experience. One where women and men are not subject to assumptions and stereotypes based on their biological sex, and accident of birthplace.

p. 216

However, for this value-free AI to emerge, we need to train it on datasets free of bias:

When we try to teach AI our values, we wont be able to do that on data-sets that reinforce division and stereotypes.

p. 232

Prior Unity

In addition to the promise of an AI free of limiting gender roles, Winterson examines the deeper implications of an AI-enabled future where we transcend all our divisions:

Humans love separations — we like to separate ourselves from other humans, usually in hierarchies, and we separate ourselves from the rest of biology by believing in our superiority. The upshot is that the planet is in peril, and humans will fight humans for every last resource. Connectivity is what the computing revolution has offered us — and if we could get it right, we could end the delusion of separate silos of value and existence.

p.6

This is of fundamental importance:

Reality is not made of parts but formed of patterns.  This is ancient knowledge and new knowledge. It is liberating. There is no fundamental building block of matter. No core. There is nothing solid. There are no binaries. There is energy, change, movement, interplay, connection, relationships. It’s a white supremacist’s nightmare.

p. 121

In this, Winterson echos the hopes expressed by the Western-born Spiritual Adept, Adi Da Samraj, who has proposed what he calls “prior unity” as the basis of a new human civilization:

If human beings collectively (as everybody-all-at-once) realize that they are (always already) in a condition of prior unity—and, therefore, of necessary co-existence and mutuality—with one another, and if, on that basis, they stand firm together, then they will be in a position to directly righten the world-situation. The collective of all the billions of people can—and, indeed, must—refuse to go on with the current chaos.

The “Everybody Force”, in Prior Unity, p. 87

Winterson claims that an AI-enabled future can help achieve this goal:

We know the hero narrative — it’s the saviour, the genius, the strong man, the against-the-odds little guy… As a story, the narrative of exceptionalism stands against collaboration and co-operation (I did it my way). And it overlooks the lives, and contributions, of literally billions of people. One of the interesting things about AI is that it works best on the hive-mind principle, where networks share information. The real sharing economy is not one where everything can be monetised by Big Tech; it’s one where humanity is pulling together — that’s exactly what we have to do to manage both climate breakdown and global inequality. The biggest problems facing us now will not be solved by competition but by co-operation.

p. 265

12 Bytes is an enjoyable, witty, and thought-provoking read.

Back in July 2023, I posted a 3-part series examining how speechwriters can use generative A.I. tools like ChatGPT. This week the news about a Chinese generative A.I. — DeepSeek R1 — caused stocks in the shares of many American AI companies to slump. Commentators noted that the Chinese A.I. could “do more with less” — challenging the resource-intensive approach in the States. I decided to put it to the test.

My July 2023 posts concluded with a series of political speeches that asked the A.I. to generate a response using Monroe’s Motivated Sequence. I then asked for examples of rhetorical techniques such as similes, metaphors, synechdoche, and metonymy. Finally, generate alternate versions of a now dated 2023 transcript of a speech on Britain’s HS2 rail program (since significantly cut bask in scope) given in the Houses of Parliament. Full details are in the original post.

Here’s what DeepSeek R1 generated — apparently using a fraction of the compute resources of ChatGPT.

PROMPT: Act as a speechwriter. Create an outline for a speech supporting the building of the High Speed Two rail line from London to the north of England using the structure of Monroe’s Motivated Sequence.

Here’s an outline for a speech supporting the construction of the High Speed Two (HS2) rail line, structured using Monroe’s Motivated Sequence. This five-step framework is designed to persuade the audience by addressing their needs and motivating them to take action.

---

Title: “Connecting Our Future: Why HS2 is Essential for Britain”

---

1. Attention: Grab the audience’s attention with a compelling opening.

• Start with a vivid statistic or fact:
  “Did you know that by 2050, the UK’s population is expected to grow by 10 million people? Our current rail infrastructure, built over a century ago, is already struggling to keep up.”
• Paint a picture of the problem:
  “Imagine sitting on a delayed train, packed like sardines, knowing you’ll miss an important meeting or your child’s school play. This is the reality for millions of commuters every day.”
• Rhetorical question:
  “What if I told you there’s a solution that could transform how we travel, boost our economy, and create thousands of jobs?”

---

2. Need: Establish the problem and why it matters.

• Current infrastructure is outdated:
  “Our Victorian-era rail network is simply not fit for the 21st century. Delays, overcrowding, and inefficiencies cost businesses billions annually and frustrate passengers daily.”
• Economic disparity between regions:
  “The north of England has been left behind for too long. While London thrives, northern cities struggle with underinvestment and lack of connectivity, stifling growth and opportunity.”
• Environmental urgency:
  “With climate change accelerating, we need sustainable alternatives to cars and planes. HS2 offers a greener way to travel, reducing carbon emissions and congestion on our roads.”

---

3. Satisfaction: Present HS2 as the solution.

• Faster, more reliable travel:
  “HS2 will cut journey times between London and the north by up to 50%, making travel faster, smoother, and more reliable for millions of people.”
• Economic benefits:
  “This project will create over 30,000 jobs during construction and thousands more in the long term. It will also unlock economic growth in the north, rebalancing our economy and reducing regional inequality.”
• Environmental advantages:
  “HS2 will take millions of cars off the road and reduce domestic flights, significantly cutting carbon emissions. It’s a critical step toward achieving our net-zero goals.”
• Future-proofing:
  “HS2 isn’t just about today—it’s about preparing for tomorrow. It will free up capacity on existing rail lines, improving local services and ensuring our infrastructure can handle future growth.”

---

4. Visualization: Help the audience see the benefits of HS2.

• Positive vision:
  “Picture this: a bustling northern city, thriving with new businesses and opportunities, connected to the capital in under 90 minutes. Commuters enjoying spacious, reliable trains, and families reunited faster than ever before.”
• Contrast without HS2:
  “Without HS2, our rail network will continue to creak under pressure. The north will remain disconnected, and our economy will stagnate. We cannot afford to let this opportunity pass us by.”
• Call to emotion:
  “This isn’t just about trains—it’s about people. It’s about giving everyone in this country a fair chance to succeed, no matter where they live.”

---

5. Action: Call the audience to support HS2.

• Direct appeal:
  “I urge you to support HS2—not just as a rail project, but as a vision for a better-connected, greener, and more prosperous Britain.”
• Specific actions:
  “Write to your MP, share the facts about HS2 with your community, and challenge the myths surrounding this project. Let’s show the world that Britain is ready to invest in its future.”
• Inspirational closing:
  “Together, we can build a legacy that future generations will thank us for. Let’s not look back in 20 years and wonder what could have been. Let’s act now, and let’s act boldly. HS2 is more than a railway—it’s a lifeline for our nation.”

---

This outline provides a clear, persuasive structure for your speech, using Monroe’s Motivated Sequence to build a compelling case for HS2. Let me know if you’d like me to expand on any section!

PROMPT: Act as a speechwriter. Suggest 3 similes and 3 metaphors to describe to an audience why high speed train travel is enjoyable.

Here are three similes and three metaphors to vividly describe why high-speed train travel is enjoyable. These can be woven into a speech to make the experience more relatable and engaging for your audience.

---

Similes:

1. “Riding a high-speed train is like gliding on air—smooth, effortless, and free from the bumps and jolts of ordinary travel.”
   This simile emphasizes the comfort and tranquility of high-speed rail, contrasting it with less pleasant modes of transportation.
2. “Traveling on a high-speed train is like watching time shrink before your eyes—cities and landscapes blur together as hours turn into minutes.”
   This highlights the speed and efficiency of high-speed rail, making long distances feel short.
3. “Sitting in a high-speed train is like being in a moving living room—spacious, comfortable, and designed for relaxation.”
   This simile conveys the convenience and comfort of train travel, making it feel like a home away from home.

---

Metaphors:

1. “A high-speed train is a ribbon of steel, weaving through the countryside and stitching cities together.”
   This metaphor paints a poetic image of connectivity and unity, showing how trains bring people and places closer.
2. “The high-speed train is a time machine, collapsing distances and giving you back the most precious resource—time.”
   This metaphor emphasizes the efficiency of high-speed rail, framing it as a tool that saves time and enhances productivity.
3. “The train is a symphony of motion, where every component works in harmony to create a seamless journey.”
   This metaphor evokes the elegance and precision of high-speed rail, comparing it to a beautifully orchestrated piece of music.

---

These similes and metaphors can help your audience visualize and emotionally connect with the joys of high-speed train travel, making your speech more memorable and impactful. Let me know if you’d like help integrating these into a larger speech!

PROMPT: Act as a speechwriter. Use synechdoche and metonymy to surprise an audience with reasons why high speed trains are a good idea.

Here’s a speech that uses synecdoche (using a part to represent the whole) and metonymy (using a related term to represent something else) to creatively and persuasively argue why high-speed trains are a good idea. These rhetorical devices will surprise the audience by offering fresh perspectives on the benefits of high-speed rail.

---

Title: “The Tracks to Tomorrow: Why High-Speed Trains Are the Future”

---

Opening:

“Ladies and gentlemen, imagine a world where the wheels of progress never stop turning. Where the heartbeat of a nation pulses along steel veins, connecting cities, dreams, and opportunities. This is the promise of high-speed trains—not just a mode of transport, but a lifeline to a brighter future.”

---

Synecdoche: Using a part to represent the whole.

1. “Every seat on a high-speed train is a desk, a dining table, and a meeting room.”
   Here, the “seat” represents the entire experience of traveling on a high-speed train. It’s not just a place to sit—it’s a space where work gets done, meals are enjoyed, and connections are made. High-speed trains transform travel time into productive time.
2. “The whistle of a high-speed train is the sound of opportunity calling.”
   The “whistle” represents the train itself and, by extension, the economic and social opportunities it brings. It’s a call to action, signaling progress and growth for communities along its route.
3. “Every ticket sold is a vote for a greener planet.”
   The “ticket” represents the passenger and their choice to support sustainable travel. High-speed trains reduce carbon emissions, and every journey taken is a step toward a more sustainable future.

---

Metonymy: Using a related term to represent something else.

1. “The rails are the arteries of a thriving economy.”
   Here, “rails” represent the entire rail network, which keeps the economy moving and alive. High-speed trains ensure that goods, people, and ideas flow freely, fueling growth and innovation.
2. “The timetable is a promise—a guarantee that the future will be on time.”
   The “timetable” represents the reliability and efficiency of high-speed trains. It’s a symbol of trust and precision, showing that high-speed rail delivers on its commitments.
3. “The station is a gateway—not just to new places, but to new possibilities.”
   The “station” represents the entire journey and the opportunities it unlocks. High-speed trains don’t just take you from point A to point B; they open doors to education, employment, and cultural exchange.

---

Closing:

“High-speed trains are more than just engines and carriages. They are the wheels of change, the tracks of progress, and the bridges to a better tomorrow. So let’s not just build trains—let’s build connections. Let’s build opportunities. Let’s build the future. Thank you.”

---

This speech uses synecdoche and metonymy to reframe high-speed trains as symbols of progress, sustainability, and opportunity. By focusing on specific parts or related concepts, it surprises the audience with fresh, imaginative reasons to support high-speed rail. Let me know if you’d like to expand on any section!

PROMPT: Act as a speechwriter. Revise this speech to be written at an 8th grade level

Here’s a revised version of the speech, written at an 8th-grade reading level for clarity and simplicity:

---

Speech by Gareth Davies, MP for Grantham and Bournemouth

Thank you to the hon. Lady for her comments. She’s right—HS2 will boost productivity, create jobs, and improve connections across the country. We need to keep sharing these benefits with everyone. But we also have to be realistic. We must balance the need for high-speed rail with managing our budget, especially as we face challenges like rising costs due to the war in Ukraine and supply chain issues from COVID-19. These are tough times, and we’re making the hard decisions needed to keep our finances stable while still investing in important projects like HS2.

The hon. Lady mentioned the National Audit Office report. We’re looking at it carefully and will respond soon. But the key point is this: HS2 is important, and we’re committed to it. We’ve had to make some tough choices to make sure we’re building strong transport links while also being responsible with public money. That’s what the British people expect from us.

We’re also working to improve rail connections across the country, especially in areas that lost service back in the 1960s with the Beeching cuts. It’s not just about building new lines—it’s about making the existing ones better too.

Now, let me address some specific points raised today. The hon. Member for Bath talked about the M4 connection to Dorset. I want her to know that the Department for Transport has asked National Highways to study this route, and we’re carefully considering their findings. We’ll have more to say on this soon.

The hon. Member for Bath and my colleague from Wimbledon also brought up rail electrification. We’re working hard on this as part of our plan to create a net zero railway by 2050. Since 2010, we’ve electrified over 1,200 miles of track, with 1,000 of those miles done in just the last five years. That’s a big improvement compared to the 70 miles electrified between 1997 and 2010. We’re making progress, but there’s still more to do.

The right hon. Member for Orkney and Shetland shared some great insights about the challenges his community faces. I’ll look into the issue he raised about funding and get back to him.

Finally, my colleague from Wimbledon made an important point: the government can’t pay for everything. We need private investment to help fund our infrastructure projects. In fact, nearly half of the UK’s future infrastructure projects will be paid for with private money. Over the next ten years, we expect total investment in infrastructure—both public and private—to reach nearly £650 billion. That’s how we’ll build a stronger future for everyone.

Thank you.

---

This version simplifies complex ideas, shortens sentences, and uses more straightforward language while keeping the original meaning intact.

PROMPT: Act as a teacher. Revise the following text so that it can understood by 8 year old children. [Insert 8th grade text above]

Here’s the revised version of the text, simplified so that it can be understood by 8-year-old children:

---

Thank you to the lady for her ideas. She’s right—HS2, the new high-speed train, will help people work better, create new jobs, and make it easier to travel across the country. We need to tell everyone about these good things. But we also have to be careful with our money. Right now, things are tough because of the war in Ukraine and problems caused by COVID-19, like higher costs and fewer supplies. We’re making hard choices to make sure we have enough money for important projects like HS2 while still being careful with how we spend.

The lady also talked about a report from the National Audit Office. We’re reading it carefully and will say more about it soon. But the most important thing is this: HS2 is really important, and we’re going to keep working on it. We’ve had to make some tough decisions to build better train lines while also being smart with the money we have. That’s what people expect from us.

We’re also working to make train travel better in places that lost their train service a long time ago, back in the 1960s. It’s not just about building new train tracks—it’s also about fixing and improving the ones we already have.

Now, let me talk about some other things people brought up today. The lady from Bath talked about a road called the M4 and how it connects to Dorset. I want her to know that we’ve asked a group called National Highways to study this road, and we’re thinking about what they found. We’ll share more about this soon.

The lady from Bath and my friend from Wimbledon also talked about making trains run on electricity instead of diesel. We’re working on this as part of our plan to make trains better for the environment by 2050. Since 2010, we’ve added electric power to over 1,200 miles of train tracks, and 1,000 of those miles were done in just the last five years. That’s a lot better than the 70 miles we did between 1997 and 2010. We’re doing a good job, but there’s still more work to do.

The man from Orkney and Shetland talked about some problems his community is facing. I’ll look into the issue he mentioned about money and get back to him.

Finally, my friend from Wimbledon made a good point: the government can’t pay for everything. We need help from businesses and other groups to pay for big projects like new roads and train lines. In fact, almost half of the money for future projects will come from private companies. Over the next ten years, we think the total money spent on these projects will be nearly £650 billion. That’s how we’ll make things better for everyone.

---

This version uses simple words, short sentences, and avoids complicated ideas to make it easier for 8-year-olds to understand.

Conclusion

It might be unfair to compare the output of ChatGPT from 2023 to DeepSeek of 2025. However, if claims about the efficiency are in fact true it represents, as some have noted, a “Sputnik moment” for the American technology industry.

As for speechwriters, I stand by my concluding words from 2023:

This three-part series has, I hope, shown ways in which speechwriters can use generative A.I. tools like ChatGPT. The number of tools is expanding rapidly. No doubt some public speeches — be they at a wedding, in the conference center, or on the hustings — will use material simply cut and paste from GPT output. This is not a clever way to proceed. The language can be silted, repetitive, filled with factual errors, and unconvincing.

However, in the hands of a professional, research tasks, speech outlines, alternative points of view, and more are available for review.

I believe these tools will enrich and make life easier and more productive for professional speechwriters and concerns about their use are misplaced.

My letter to the Weekend FT was somewhat marred by what I thought was a misleading title written by an FTT sub-editor. In contrast, my 2019 letter disputing Arnold Schwarzenegger’s claim to be “the first populist that was elected” was given a brilliant title:

A.I. Sub

Working on tight deadlines, on a Friday night at the FT’s HQ on London’s South Bank, it’s challenging for subs looking to capture the essence of each of the letters on their editorial page.

Would generative A.I. help? I decided to put it to the test, starting with my own letter and this ChatGPT prompt:

Act as a newspaper subeditor. Write short 8-10 word headlines for this letter to the editor [INSERT TEXT OF LETTER]

Here’s the results, following the FT’s choice.

1. “Alphabet’s Revolution: A Cultural Shift Unveiled”
2. “Surgeon’s Thesis: Alphabet’s Brain Impact Through History”
3. “Shlain’s Insight: Alphabet Reshaping Religion, Science, Gender”
4. “From Goddess to Patriarchy: The Alphabet’s Influence Exposed”
5. “Challenging Myths: Quinn Dissects Alphabet’s Cultural Impact”
6. “Shaping Minds: The Alphabet’s Journey Through History”
7. “Cultural Clash: Quinn Takes on White Nationalist Mythology”
8. “Optimistic Outlook: Shlain Envisions Brain Evolution Beyond Alphabet”
9. “Images Over Words: Shlain’s Hope for Right-Brained Culture”
10. “Feminine Wisdom: Shlain Posits Return Amid Cultural Change”

1. “Revisiting the Greeks: Professor Quinn on Civilization’s Complex Evaluation”
2. “Beyond pedestals: Professor Quinn’s Insights on Classical Greek Contributions”
3. “Greeks and Governance: Professor Quinn Dissects Ancient Achievements”
4. “Classical Greek Legacy: Professor Quinn Challenges Modern Perspectives”
5. “Meta Leap in Governance: Professor Quinn Explores Greek Brilliance”
6. “Transcending Relativism: Professor Quinn on Classical Greek Endurance”
7. “Civilization’s Essence: Professor Quinn Reflects on Greek Achievements”
8. “Beyond Reductionism: Professor Quinn on the Greek Civilization Myth”
9. “Classical Greek Brilliance: Professor Quinn’s Thought-Provoking Perspective”
10. “Quinn’s Reflections: Rethinking Classical Greek Contributions to Civilization”

1. “Chloe Aridjis Unveils Delightful Journey Through Madrid’s Prado”
2. “Aridjis’ Artful Adventure: Two Months at Madrid’s Prado Revealed”
3. “Museum Sanctuary: Aridjis’ Reflections Illuminate Art and Struggle”
4. “Prado Perspectives: Chloe Aridjis Explores Museums as Sanctuaries”
5. “Aridjis’ Madrid Memoir: A Unique Glimpse into Museum Sanctuaries”
6. “Chloe Aridjis’ Artful Escape: Two Months at the Prado”
7. “From London to Madrid: Aridjis’ Museum Journey Unveiled”
8. “Exploring Museums: Aridjis’ Essay Sheds Light on Art Sanctuaries”
9. “Prado and Beyond: Aridjis’ Journey into Museum Sanctuaries”
10. “Chloe Aridjis’ Museum Musings: A Unique Perspective on Art”

1. “JLR Chief’s Bold Request: Should Taxpayers Subsidize Luxury SUV Security?”
2. “JLR’s Dilemma: Taxpayer Subsidy for Luxury SUV Security Sparks Controversy”
3. “JLR’s CEO Stirs Debate: Should Taxpayers Foot the Bill for Security?”
4. “Luxury Car Controversy: JLR Calls for Taxpayer Support on Security”
5. “JLR’s Taxpayer Appeal: Security Costs or Executive Priorities?”
6. “Luxury Car Maker Faces Backlash: JLR’s Request Sparks Outcry”
7. “JLR’s Security Saga: CEO Proposes Taxpayer Support Amid Record Profits”
8. “JLR’s Bold Ask: Taxpayers Subsidize Security for Stolen Luxury SUVs”
9. “JLR CEO Sparks Controversy: Taxpayers Footing the Bill for Security?”
10. “Luxury SUVs and Taxes: JLR’s Request Raises Eyebrows”

1. “Range Rover Mystery: Unoccupied Idling Raises Security Concerns”
2. “JLR Boss Called Out: Range Rover Left Idling Sparks Questions”
3. “Car Park Conundrum: Unmanned Range Rover Raises Eyebrows”
4. “Range Rover Riddle: Owner’s Remote Starter Mishap Spurs Controversy”
5. “JLR’s Security Quandary: Unattended Range Rover Raises Issues”
6. “Remote Start Mishap: Unmanned Range Rover Puzzles Onlookers”
7. “JLR Customer Education: Unmanned Range Rover Prompts Suggestions”
8. “Idle Investigation: Unattended Range Rover Spurs Security Discussion”
9. “Range Rover Dilemma: JLR Boss Urged for Customer Education”
10. “Mystery at the Station: Unmanned Range Rover Raises Alarms”

1. “Decoding Tipping Dilemmas: Insights from Jo Ellison’s Column”
2. “Tipping Tales: Navigating Cultural Differences and Digital Transactions”
3. “From Paris to Tips: Jo Ellison Sheds Light on Tipping”
4. “The Tipping Mystery: Jo Ellison’s Column Unveils Insights”
5. “Cultural Quirks: Jo Ellison Explores Tipping Challenges Abroad”
6. “Digital Transactions and Human Touch: Tipping Insights Unveiled”
7. “Parisian Tipping Woes: Jo Ellison’s Column Sparks Reflection”
8. “Small Change, Big Impact: Jo Ellison’s Perspective on Tipping”
9. “Tipping Etiquette Unveiled: Jo Ellison’s Column Sparks Discussion”
10. “From Tears to Tips: Jo Ellison’s Column Resonates with Readers”

1. “Rudeness and Noodles: Tim Harford Reflects on Wong Kei’s”
2. “Wong Kei’s Legacy: Tim Harford Explores Rude Service Charm”
3. “Rudeness Revisited: Tim Harford’s Take on Wong Kei’s Tradition”
4. “Chinatown Charm: Tim Harford on the Quirky Appeal of Wong Kei’s”
5. “Noodles and Blunt Humour: Tim Harford Recalls Wong Kei’s”
6. “Wong Kei’s Wit: Tim Harford Explores the Charm of Rudeness”
7. “Quirky Dining: Tim Harford’s Reflection on Wong Kei’s Signature”
8. “Rude Service Charm: Tim Harford’s Nostalgic Wong Kei’s Tale”
9. “Wong Kei’s Legacy Lives On: Tim Harford’s Humorous Memories”
10. “Dining with Attitude: Tim Harford Reminisces Wong Kei’s Style”

1. “McCarthy’s Ambition: A Tribal Tale in American Politics”
2. “Driven by Ambition: McCarthy’s Political Portrait Unveiled”
3. “Tribal Politics: McCarthy’s Ambition Revealed in FT Interview”
4. “US Speaker’s Ambition: A Reflection on McCarthy’s Legacy”
5. “Political Tribalism: McCarthy’s Ambition Under the Spotlight”
6. “Retrospective Ambition: Kevin McCarthy’s Political Journey Unveiled”
7. “McCarthy’s Legacy: Ambition and Tribalism in US Politics”
8. “Tribal Ties: Former US Speaker McCarthy’s Driven Ambition”
9. “Kevin McCarthy Unmasked: Ambition and Tribalism in Politics”
10. “Politics of Ambition: McCarthy’s Tribal Approach in the Spotlight”

1. “Cheers to Tech: AI and the Future of Wine Experts”
2. “Wine App Worries: Alice Lascelles Explores AI’s Impact”
3. “Tech vs. Terroir: Can an AI App Replace Wine Experts?”
4. “Sipping into the Future: Alice Lascelles on Wine and AI”
5. “I, Vin: A Catchy Alternative to AI Sommelier Apps”
6. “Pour Decisions: Alice Lascelles Ponders AI in Wine”
7. “Wine and Tech: Alice Lascelles Weighs in on AI Sommeliers”
8. “Sommelier or AI? The Future of Wine Expertise Explored”
9. “Wine Trends: Alice Lascelles Delves into AI’s Influence”
10. “I, Vin: A Quirky Suggestion for Wine App Enthusiasts”

Win some, lose some

Looking over these lists, it’s clear that generative AI cannot match the subs at their best. The Eugene Onegin pun went above and beyond the wit of the original letter. Other headlines from the FT were more pedestrian.

However, the AI text overdoes words like “unveiled” and “revealed”. It also inserts the article author’s name too frequently. However, I found it useful as a brainstorming tool, where the final headline can be cherry-picked from suggestions. I plucked my own alternate headline (“Rewiring brains for a return to feminine values”) from a previous list of ChatGPT suggestions. Among the ten suggestions for the visit to the Prado and the McCarthy letter is the exact text used by the FT. I liked “Rudeness and noodles: Chinatown charm” taken from that list of suggestions. “Tech vs. Terroir: Can an AI App Replace Wine Experts?” has appeal.

My 3-part series on ways generative A.I. can be of value to speechwriters started with a simple example of generating ideas for a Best Man’s wedding speech, reviewed how it can help corporate speechwriters, and concluded with a deep dive into political speechwriting. In all cases, I emphasized that generative A.I. is a tool and not a replacement for a flesh-and-blood writer, and in no way should be relied on for verbatim scripts.

Search engines

As technology evolves, there are now A.I. tools (often based on large language models like ChatGPT) that speechwriters can employ to speed the plow and hone their craft.

Gone are the days when writers would sharpen their quill pen, dip into an inkwell, and refer to dusty reference books for pertinent data. Some might still work this way. For the rest, a search engine, spell checker, and word processor are essential tools.

So, let’s look at how search can be improved beyond the ubiquitous Google machine.

Perplexity A.I.

Writing in today’s New York Times, Kevin Roose asks Can This A.I.-Powered Search Engine Replace Google? He is referring to Perplexity A.I., a year-old program built on ChatGPT that generates responses to questions “generally a paragraph or two long, sprinkled with citations to websites like NPR, The New York Times and Reddit, along with a list of suggested follow-up questions…”

Perplexity elaborates:

What are the unique features of Perplexity that set it apart from Google?

Perplexity AI offers several unique features that set it apart from Google. These include:

1. Comprehensive Responses: Perplexity AI has the ability to synthesize information from diverse sources to provide comprehensive responses, unlike Google, which often returns a list of links or snippets of information23.
2. Ad-Free User Experience: Perplexity AI provides an ad-free user experience, prioritizing the delivery of relevant and accurate information without ad interference, unlike Google, which relies on an ad revenue model3.
3. Focus on Accuracy and Context-Rich Answers: Perplexity AI focuses on providing accurate, context-rich answers, making it a powerful tool for users seeking in-depth understanding of complex subjects2.
4. Real-Time Information and Organization Features: Perplexity AI offers real-time information, accuracy, awareness, and organization features, providing users with the most current information in a well-organized manner4.
5. Accuracy in Text Generation: Perplexity AI is known for its knack for generating more accurate text compared to other AI language models like ChatGPT and Google Bard5.

While Perplexity AI has these unique features, it’s important to note that it is still under development and may occasionally face challenges in generating accurate text5.

Let’s consider how a speechwriter might use a search engine. I first addressed this question back in 2006 and suggested 29 tools that were current at the time, noting:

You can wander through a lush forest of ideas in an online encyclopedia, way-back machines, and other arcane sources as you prepare to select the timber for your next project. But when you are up against a deadline and need a fact, quote, or an opinion, then, like a master carpenter who reaches for just the right drill bit or chisel, the accomplished writer needs to know which search tool to use for the job. The faster you can cut through the crap and find the facts, the sooner you’ll finish the project, and the more pleasing the result will be.

That decades-old list was a Google-fest. Since then, as Roose notes, “Google seems less invincible these days. Many users have complained that their Google search results have gotten clogged with spammy, low-quality websites…”

My post on how political speechwriters could use generative A.I. was built around the example of the British HS2 train debate. Let’s say your principal wants to engage an audience about this topic, and, unlike me, you are not from the railway town of Crewe — a key terminus of the now-canceled HS2 project. So you need some background, either to refer to in the presentation, or for the briefing book and ask “What was the importance of the railway industry in the growth of Crewe, England?”

Here’s the top of the list of links Google provides in response to this query:

A savvy speechwriter can dig into these references and extract enough detail for a summary of the importance of rail to the town’s growth.

Ask Perplexity the same question, and a succinct paragraph–with references–is returned:

The railway industry has been of great importance in the growth of Crewe, England. Crewe owes its existence to the railways, with the arrival of its station in the 1830s thanks to the Grand Junction Railway, which transformed the small rural village into a significant hub of the UK’s railway network 4. At its height, about 20,000 people were employed at Crewe Works, and although it is no longer such a major employer, a significant proportion of the workforce is still connected to the railways 4. The town’s strong historical links to the railway industry make it an ideal location for the headquarters of Great British Railways, and its rail heritage is celebrated at the Crewe Heritage Centre 4. The railway industry has played a critical role in the town’s development and continues to be an important part of its identity 4.

Red Flag Warning!

Surprisingly, when I chose the option for Perplexity to ‘rewrite’ the answer with the ‘Copilot’ (offering “a more accurate and thorough search”), it started hallucinating:

The railway industry played a pivotal role in the growth and development of Crewe, England. Crewe owes its existence to the railways, with the arrival of its station in the 1930s transforming it from a small rural village into a significant hub of the UK’s railway network.1. The railway company owned and controlled almost everything in Crewe until 1938, when the Crewe Corporation Act was passed4. At its peak, the railway industry employed 20,000 people at Crewe Works, and even though it’s no longer such a major employer, a significant proportion of the workforce is still connected to the railways1. The town has retained and attracted many rail and rail supply chain businesses, which have innovated and evolved over time5. Crewe’s railway heritage has also contributed to its visitor economy, with its key role in the development of the railways attracting tourists 3. Today, while other industries such as automobile and clothing manufacturing have emerged, railways remain important to the town 4.The railway industry’s influence on Crewe extends to its future growth prospects. The town’s role in High Speed 2, a major UK rail project, has been evolving since 2014, ensuring Crewe’s continued relevance in the UK railway network6. In summary, the railway industry has been integral to Crewe’s growth, shaping its economy, workforce, and identity.

This is wrong in so many ways: It transposed the 1930s and 1830; the Crewe Corporation Act was passed in 1949; very few “tourists” ever visit what is, frankly, a depressed northern town; and HS2 was canceled in October 2023.

Verification and fact-checking remain vital functions of a professional speech writer. I triangulated the facts listed above with…Google!

But, putting aside that faux pas, the follow-up questions Perplexity suggests in response to the original prompt lead to a more thorough explanation (this time mostly accurate, except it still missed the October 2023 cancellation).

Perplexity suggested asking, “What was the role of Crewe in the development of the railways?”

Crewe, England, played a pivotal role in the development of the railways. The town’s significance in the railway industry is evident from its transformation from a small hamlet into a thriving community, largely due to the establishment of the Grand Junction Railway Company’s station in the mid-19th century 1 2. Crewe became renowned as the world’s greatest railway workshop, with the production of locomotives steadily increasing through the 19th century, and it was the birthplace of thousands of locomotives2. The town’s economy has been strongly influenced by its historical connection to the railways, with the railway industry being a major employer at its peak, and its impact extending to the diversification of industries such as motor cars, computers, higher education, and optical equipment12. Crewe’s status as a significant railway hub is set to be further reinforced by the proposed HS2 high-speed rail project, which is expected to bring economic benefits and contribute to the town’s continued association with the railways 3. In summary, Crewe’s role in the development of the railways has been fundamental, shaping its history, economy, and identity as a “railway town.”

Conclusion

Provided you remain vigilant and cross-check the data, Perplexity is a valuable addition to a speechwriters’ toolkit . Unlike Google, it returns succinct paragraphs and suggests follow-up questions.

But remember, AT NO TIME should ANY generative A.I. text be simply cut ‘n paste into a speech. OK?

This is the third and final part of the series of posts advocating how speechwriters can use generative A.I.

A division exists in the speechwriting profession between those well-paid speechwriters in the corporate world and political speechwriters. Political speechwriters often write for a person and cause they believe in.

The single best book on political speechwriting is Robert Lehrman’s classic “The Political Speechwriter’s Companion, which lists several core ideas that generative A.I. can tackle.

Monroe’s Motivated Sequence (MMS)

Lehrman identifies MMS as an important way to structure a political speech but cautions that “if MMS by itself could make speech moving, entertaining, or persuasive, the Cliff Notes of Hamlet would be as effective as the play. It won’t make your speech great, any more than a skeleton makes you human.”

Given that, can we ask Chat GPT to create a speech outline using MMS?

Prompt

Act as a speechwriter. Create an outline for a speech supporting the building of the High Speed Two rail line from London to the north of England using the structure of Monroe’s Motivated Sequence.

ChatGPT Output

• I. Introduction
  • A. Attention-grabbing opening: Share a compelling statistic or anecdote about the current state of transportation in the UK or the need for improved connectivity between London and the north of England.
  • B. Establish credibility: Briefly introduce yourself and your expertise or experience in the field of transportation or infrastructure.
  • C. Thesis statement: State the purpose of the speech and express support for the construction of the High Speed Two (HS2) rail line from London to the north of England.
• II. Need
  • A. Problem statement: Describe the current challenges and limitations of the existing rail infrastructure, such as overcrowding, delays, and lack of capacity.
  • B. Consequences: Explain the negative impacts of the current situation, such as hindered economic growth, increased congestion, and limited opportunities for regional development.
  • C. Evidence: Present relevant data and examples that highlight the need for an improved rail connection between London and the north of England, emphasizing the economic, social, and environmental benefits it can bring.
• III. Satisfaction
  • A. Proposed solution: Introduce the High Speed Two (HS2) rail project and provide an overview of its key features, including its high-speed capability, increased capacity, and reduced travel times.
  • B. Benefits: Highlight the advantages of HS2, such as improved connectivity, enhanced regional integration, job creation, reduced carbon emissions, and increased economic opportunities.
  • C. Evidence: Present supporting evidence, such as success stories from other countries with high-speed rail networks or examples of how HS2 could stimulate economic growth and development in specific regions.
• IV. Visualization
  • A. Paint a positive picture: Use vivid language and imagery to describe the future with HS2 in place, such as seamless travel experiences, vibrant regional economies, and reduced congestion on roads and existing rail lines.
  • B. Personal connection: Share a relatable anecdote or story that illustrates how HS2 can positively impact individuals, businesses, or communities, emphasizing the improved quality of life and opportunities it can bring.
  • C. Appeal to emotions: Use emotional language or storytelling techniques to engage the audience’s feelings and generate enthusiasm for the project.
• V. Action
  • A. Call to action: Clearly state the desired action, which is to support the construction of HS2.
  • B. Specific steps: Provide information on how individuals can get involved, such as contacting local representatives, joining advocacy groups, or spreading awareness about the project.
  • C. Final appeal: Reiterate the benefits of HS2 and the urgency of taking action, emphasizing that supporting this project will contribute to a brighter future for both the north of England and the entire country.
• VI. Conclusion
  • A. Summary: Recap the main points discussed in the speech, emphasizing the need for HS2 and its potential benefits.
  • B. Closing statement: End with a strong, memorable statement that inspires the audience to support the construction of HS2 and be part of a transformative transportation project.
  • C. Thank you: Express gratitude to the audience for their time and attention, and encourage them to take action and spread the message to others.

Not bad, eh? ChatGPT clearly understands MMS and applied the framework to this topic.

Making Language Vivid

In Chapter seven, Lehrman shares examples of the ways a politician can “use language that the crowd remembers and reporters will quote.” This is achieved with various rhetorical devices. How can ChatGPT help with these?

PROMPT: Act as a speechwriter. Suggest 3 similes and 3 metaphors to describe to an audience why high speed train travel is enjoyable.

Sure! Here are three similes and three metaphors to describe why high-speed train travel is enjoyable:

Similes:

1. “Traveling on a high-speed train is like soaring through the air, as if you’re a bird gliding effortlessly on a current of steel and speed.”
2. “The experience of high-speed train travel is as smooth as silk, where every movement feels like a gentle dance, gracefully gliding across the tracks.”
3. “Riding a high-speed train is like being on a time machine, where minutes tick away like seconds, propelling you forward into the future with exhilarating speed.”

Metaphors:

1. “High-speed train travel is a symphony of motion, where the rhythmic chugging of the locomotive and the harmonious hum of the tracks create a melodious journey that enthralls the senses.”
2. “Embarking on a high-speed train is stepping into a sleek silver bullet, a futuristic capsule hurtling through time and space, carrying you to your destination in a blink of an eye.”
3. “The high-speed train is a magic carpet of modernity, whisking you away on an enchanting voyage, where landscapes transform like scenes from a kaleidoscope, unfolding before your eyes.”

Feel free to adapt or modify these descriptions to suit your speech and audience.

PROMPT: Act as a speechwriter. Use synechdoche and metonymy to surprise an audience with reasons why high speed trains are a good idea.

Ladies and gentlemen,

Today, I want to share with you some surprising insights about why high-speed trains are not just a good idea, but a transformative force in our modern world. And I’ll do so by using two powerful rhetorical devices: synecdoche and metonymy.

1. Synecdoche: Let me start by introducing you to the power of synecdoche, where a part represents the whole. Imagine, for a moment, a “single ticket” — a small, seemingly insignificant piece of paper. But within that modest ticket lies a world of possibilities. That single ticket represents more than just a seat on a high-speed train; it symbolizes access to a vast network of opportunities. It opens the doors to education, career prospects, and cultural enrichment. That tiny ticket encapsulates the entire experience of seamless travel, efficient connections, and the chance to explore the world beyond our immediate surroundings. It’s a synecdoche that encapsulates the incredible potential of high-speed train travel.
2. Metonymy: Now, let’s delve into the realm of metonymy, where an attribute or symbol is used to represent a larger concept. Consider the notion of “steel arteries.” When we think of arteries, we envision the life-giving pathways that course through our bodies, transporting oxygen and vital resources. In the same vein, high-speed train lines can be seen as the steel arteries of a nation, breathing life into its economic, social, and cultural vitality. They connect cities and regions, pumping lifeblood into local economies, fostering innovation, and invigorating communities. Just as our physical well-being relies on healthy arteries, the well-being of a nation thrives on a robust network of high-speed train lines, fueling progress and unity.

But there’s more to the story. Synecdoche and metonymy reveal another layer of surprise.

Synecdoche reveals that a single ticket represents more than just a journey—it’s a key that unlocks doors to a myriad of possibilities. And metonymy unveils high-speed train lines as the pulsating arteries that infuse life into our societies.

So, my friends, as we contemplate the benefits of high-speed trains, let us not be confined by the literal confines of tracks and stations. Instead, let us recognize the profound impact they have on our lives—their ability to propel us forward, their power to connect us, and their potential to shape a brighter, more interconnected future.

Let us embrace the surprising depths and transformative potential that lie within the synecdoche of a single ticket and the metonymy of steel arteries.

Thank you.

OK, so that was maybe too literal. But there are nuggets of information in the response that could easily be extracted and used in a speech. I asked ChatGPT to ‘regenerate’ the response and the second version contained, I think, richer content than the first.

Ladies and gentlemen, today I stand before you to reveal the hidden marvels of high-speed trains, where the mere parts represent a greater whole, and where a single word encompasses an entire concept. Let’s explore the surprising reasons why these trains are a brilliant idea, through the lens of synecdoche and metonymy.

1. “Wheels in Motion” (Synecdoche) Imagine the wheels of a high-speed train, rotating tirelessly on the tracks. These wheels are not just metal and rubber components; they represent the unstoppable progress and development that high-speed trains bring to our nation. Each rotation signifies the wheels of the economy in motion, generating jobs, boosting industries, and creating a ripple effect of prosperity. These seemingly simple wheels symbolize the transformative power of high-speed rail, propelling us towards a future of growth and prosperity.
2. “The Silver Streak” (Metonymy) “The Silver Streak” refers to the high-speed train’s sleek, silver exterior, but it symbolizes something much grander. This nickname represents a meteoric advancement in transportation technology, a streak of brilliance that surges forward with unmatched velocity. It stands for the precision and efficiency that high-speed trains offer, redefining how we connect, commute, and coexist in a seamless web of modern infrastructure. Just as a silver streak across the sky captures our attention and sparks wonder, these trains capture our imaginations and revolutionize our travel experience.
3. “The Beacon” (Metonymy) Think of the high-speed train stations that emerge as beacons in bustling cities and remote regions alike. These stations are not just physical structures; they represent the very essence of connectivity and integration. Like a guiding light in the darkness, these beacons beckon people from various walks of life to come together and experience the unity and cultural exchange that high-speed trains enable. They symbolize progress, bridging the gaps between communities and creating a shared sense of belonging, irrespective of distance. These stations become the heartbeat of a nation, pulsating with life and opportunity.
4. “The Engine’s Heartbeat” (Synecdoche) The rhythmic throb of the high-speed train’s engine is more than just mechanical; it’s a metaphorical heartbeat of innovation and environmental consciousness. Each pulse represents the sustainable and eco-friendly nature of high-speed trains, offering a green alternative to air travel and road congestion. Just as a strong heartbeat sustains life, this eco-conscious engine sustains our planet, nurturing a greener tomorrow for generations to come.

In conclusion, high-speed trains are not merely transportation vehicles; they are vessels of progress, unifiers of people and places, and stewards of a sustainable future. They epitomize the power of synecdoche and metonymy, where the parts signify the grander whole, and a single word encapsulates a world of possibilities. Embrace the surprising brilliance of high-speed trains, and together, let’s embark on a journey that will shape our nation’s destiny and leave an indelible mark on history. Thank you.

Again, the over-literal interpretation, from which key concepts and phrases could be extracted, or used as a springboard for brainstorming.

Flesch-Kincaid score

Early in his book, Lehrman makes a strong case that ‘politicians need to be understood’ and points out the US population has an average seventh-grade (12-year-old) reading level. “In fact, speeches written at a seventh-grade level might be too complicated for a lot of Americans; unlike readers, listeners can’t go back if they’re confused.”

He recommends the Flesch-Kincaid Readability Test that is part of Microsoft Word’s Spelling and Grammar Check which returns the Grade Level of any speech.

Let’s see how ChatGPT can proactively assist a political speechwriter looking to get it right.

PROMPT: Act as a speechwriter. Revise this speech to be written at an 8th grade level

ChatGPT output

Thank you, everyone. I agree with the previous speaker that high-speed trains are a good idea. They will improve productivity, create jobs, and enhance connectivity. It’s important that we all support and promote this idea. However, we also need to consider the reality of balancing high-speed rail with sustainable public finances and responding to global events like the situation in Ukraine and the impacts of COVID-19. The recently announced changes reflect our efforts to address these challenges.

We are not only focused on high-speed trains but also on improving rail connectivity throughout the country. Our goal is to reverse the cuts made in the 1960s and expand the rail network while also enhancing existing infrastructure.

I want to address some specific concerns raised by other speakers. We are aware of the issues related to the M4 connection to Dorset and have commissioned a study to address them. We are also committed to rail electrification, and our transport decarbonisation plan aims to achieve a net-zero railway by 2050. Since 2010, we have already electrified over a thousand miles of track, and we are determined to do more.

To finance these projects, we are not relying solely on government funds. We are actively seeking private investment through partnerships. In fact, almost half of the future infrastructure projects in the UK are expected to be financed privately. We have strong regulations, a solid legal framework, and a robust financial sector that attract private capital investment.

This was not totally fair, since the speech was given in the Houses of Parliament, not to an outside audience (Funding for Major Infrastructure Projects, Hansard Volume 732: debated on Wednesday 3 May 2023 – Gareth Davis speaking). However, it clearly shows how ChatGPT can take complex political rhetoric and simplify it for the average person.

Still too complex? How about this?

PROMPT: Act as a teacher. Revise the following text so that it can understood by 8 year old children. [Insert 8th grade text above]

Hello, everyone! I want to talk about something really exciting: high-speed trains! They are super fast trains that can help us in many ways. First, they will make us more productive, which means we can get things done faster. Second, they will create jobs, so more people will have work to do. And third, they will help us stay connected to different places, making it easier for us to travel and visit our friends and family.

But there are some important things we need to think about too. We have to make sure we can afford to build these high-speed trains and take care of our money. We also need to pay attention to what’s happening in the world, like the situation in Ukraine and the effects of COVID-19. We want to make sure we can handle any challenges that come our way.

Now, high-speed trains are not the only thing we’re working on. We also want to make the regular trains better and more connected all around the country. A long time ago, there were some cuts made to the train system, and we want to fix that. We want to make the train network bigger and better while also improving the existing train tracks and stations.

Some people have raised concerns about connecting the M4 to Dorset. We know there are issues with that, and we’re doing a special study to find solutions. We also care about the environment, so we want to make the trains run on electricity instead of polluting fuels. Our plan is to have a train system that doesn’t produce any pollution by the year 2050. We’ve already made progress by electrifying over a thousand miles of train tracks since 2010, and we want to keep going.

To pay for all these projects, we’re not only using money from the government. We’re also asking for help from private investors through partnerships. In fact, almost half of the future projects in the UK will be funded by private money. We have rules and laws in place to make sure everything is done correctly, and our financial system is strong, which means people want to invest their money in our projects.

So, let’s get excited about high-speed trains and improving our train system! We’re working hard to make it happen, and we appreciate everyone’s support.

In conclusion

This three-part series has, I hope, shown ways in which speechwriters can use generative A.I. tools like ChatGPT. The number of tools is expanding rapidly. No doubt some public speeches — be they at a wedding, in the conference center, or on the hustings — will use material simply cut and paste from GPT output. This is not a clever way to proceed. The language can be silted, repetitive, filled with factual errors, and unconvincing.

However, in the hands of a professional, research tasks, speech outlines, alternative points of view, and more are available for review.

I believe these tools will enrich and make life easier and more productive for professional speechwriters and concerns about their use are misplaced.

This is the second in the three-part series of posts examining how speechwriters can use generative A.I. tools like ChatGPT.

In Part 1 of this series, I looked at ways ChatGPT could help write a best man’s speech for a wedding. I’ll now turn to the type of corporate speechwriting I did for over 15 years at technology companies in Silicon Valley: Sun Microsystems, H-P, and Cisco.

Perhaps my most succinct, if offbeat, summary of what that job involved was my 2008 post, The Medieval Speechwriter. I’ll use it as a framework to show how the speechwriting of the 21st century (explained in terms of the 14th) works using generative A.I. tools.

Caution: Please remember that you should never take A.I. output at face value — it can suffer from ‘hallucinations’ and generate misinformation. Google’s Bard program famously supplied incorrect data about which satellite first took pictures of a planet outside the Earth’s solar system. Result: Alphabet Inc (Google’s parent company) lost $100 billion in market value.

The speechwriter employing these tools should double-check everything. Also, I’m not suggesting you take any of the content and cut and paste it into a script. Use common sense and make this your point of departure.

The Motley Fool

I wrote that the role of the corporate speechwriter, like the Fool in the Medieval court, includes looking at issues and topics with fresh eyes. Indeed, Justina Chen, in an awesome presentation on corporate speechwriting at the 2012 Ragan conference notes

Don’t be afraid of discussing failures, the crucible moments in the company history is where we see character emerge. Speechwriters can research the times the company has failed and show the lessons, the backbone, and the spine of the organization.

Given the current limitation that ChatGPT has only ‘learned’ from data prior to September 2021, it might be necessary to switch to Bing for current information. However, for a quick list of the risks of failure in a flagship product that an executive might wish to acknowledge and address, take this example:

PROMPT: Act as an industry analyst. List five pros and cons about Meta’s VR headsets

As an industry analyst, I can provide you with a list of five pros and cons about Meta’s VR headsets (formerly known as Facebook’s Oculus VR headsets). Please note that the information provided is based on my knowledge cutoff in September 2021, and there may have been updates or changes since then. Here are the pros and cons:

Pros of Meta’s VR headsets:

1. Immersive Virtual Reality Experience: Meta’s VR headsets offer a highly immersive virtual reality experience, allowing users to feel fully immersed in a virtual environment. The headsets typically have high-resolution displays and a wide field of view, enhancing the visual experience.
2. Strong Content Ecosystem: Meta has built a robust content ecosystem for its VR headsets. The Oculus Store provides a wide range of VR games, applications, and experiences, offering users a diverse selection of content to enjoy on their headsets.
3. Growing Developer Community: Meta has cultivated a strong developer community around its VR platform. This has resulted in a steady stream of innovative and engaging content being developed for the platform, including games, educational apps, and creative experiences.
4. Advanced Tracking and Controllers: Meta’s VR headsets often come with advanced tracking technology and controllers. These tracking systems allow for precise and accurate movement tracking, enhancing the overall immersion and user experience. The controllers provide a natural and intuitive way to interact with the virtual environment.
5. Cross-Platform Compatibility: Meta’s VR headsets are compatible with various platforms, including Windows and, in some cases, even standalone operation. This compatibility broadens the potential user base and allows for flexibility in using the headsets with different devices.

Cons of Meta’s VR headsets:

1. High Cost: VR headsets, including Meta’s offerings, can be quite expensive. The cost of the hardware itself, along with additional accessories and games, can make VR an investment that is out of reach for some consumers.
2. Limited Mobility: Most of Meta’s VR headsets require being tethered to a powerful gaming PC, limiting the mobility and portability of the experience. While there are standalone options available, they may have limitations in terms of processing power and graphical capabilities.
3. Potential Discomfort: Extended use of VR headsets can cause discomfort for some users. Factors like motion sickness, eye strain, and discomfort from wearing the headset for extended periods may affect certain individuals.
4. Limited Field of View: Although Meta’s VR headsets offer a wide field of view compared to earlier iterations, some users may still find the field of view to be restrictive. This limitation can impact the overall sense of immersion and visual experience.
5. Privacy and Data Concerns: Meta’s VR headsets, like many other connected devices, raise concerns about privacy and data collection. The company collects user data to provide personalized experiences and targeted advertising, which may raise privacy concerns for some users.

Please note that as the VR industry evolves rapidly, it is essential to stay updated with the latest information and product developments to have the most accurate and relevant analysis.

Let’s ask Bing for an update.

PROMPT: List the advantages that Apple’s VR headset has over Meta’s VR headset.

Apple’s VR headset has not been released yet, so it is difficult to compare the two headsets. However, based on what we know so far, here are some advantages that Apple’s VR headset has over Meta’s VR headset:

1. Apple’s VR headset is expected to have a higher resolution than Meta’s VR headset ¹.
2. Apple’s VR headset is expected to have a higher refresh rate than Meta’s VR headset ¹.
3. Apple’s VR headset is expected to have a longer battery life than Meta’s VR headset ¹.
4. Apple’s VR headset is expected to be lighter than Meta’s VR headset ¹.
5. Apple’s VR headset is expected to have a more comfortable design than Meta’s VR headset ¹.

That being said, it is important to note that these are just expectations and we will have to wait for the release of Apple’s VR headset to see how it compares to Meta’s VR headset.

The Ploughman

In 2008 I wrote: Tedious but necessary work plays a large part in speechwriting. Doing research. Fact-checking. Ploughing through the background papers which spew from Subject Matter Experts like weeds sprouting on a April morning after a few sweet showers.

Back in the day, we used the Google machine for much of this work. That, plus asking SMEs to share their research, will occupy much of the time of a corporate speechwriter. A significant advantage of generative A.I. tools is feeding in documents and extracting a summary.

As an example, the scientific paper A Review on Kombucha Tea-Microbiology, Composition, Fermentation, Beneficial Effects,Toxicity, and Tea Fungus on the KBI website has a section on ‘The Chemical Composition of Kombucha Tea’ (p 540-542). Pasting this text into ChatGPT and asking for a 10-point summary generates:

The main points covered in the paper “Chemical composition of kombucha tea” can be summarized as follows:

1. Chemical analysis of kombucha tea reveals the presence of various organic acids, including acetic, gluconic, glucuronic, citric, L-lactic, malic, tartaric, malonic, oxalic, succinic, pyruvic, usnic acids, among others.
2. Kombucha tea also contains sugars such as sucrose, glucose, and fructose, as well as vitamins B1, B2, B6, B12, and C.
3. The beverage contains 14 amino acids, biogenic amines, purines, pigments, lipids, proteins, hydrolytic enzymes, ethanol, antibiotically active substances, carbon dioxide, phenol, tea polyphenols, minerals, anions, DSL (insufficiently known products of yeast and bacterial metabolites).
4. The composition of kombucha can vary based on factors such as the duration of fermentation, the content of black tea, and the parameters of fermentation (temperature, time, initial content of sucrose and black tea), as well as the composition of the kombucha culture.
5. The metabolic activities of yeasts and bacteria in kombucha involve the utilization of different substrates and the production of various metabolites, including acetic acid, gluconic acid, glucuronic acid, lactic acid, and citric acid.
6. The content of acetic acid in kombucha increases over time during fermentation and then gradually decreases.
7. Glucuronic acid and gluconic acid are major organic acids produced during the kombucha fermentation process. The concentrations of these acids can vary based on the duration of fermentation and the composition of the substrate.
8. L-lactic acid is detected and determined in kombucha, although it is not a characteristic compound of the traditional beverage. Its concentration can vary based on the type of tea used for fermentation.
9. Sucrose, the most common carbon source in kombucha fermentation, is not completely fermented during the process, with a portion remaining unfermented.
10. Kombucha tea contains a variety of minerals, including manganese, iron, nickel, copper, zinc, lead, cobalt, chromium, and cadmium, although the concentrations of these minerals can vary.

These points highlight the diverse chemical composition of kombucha tea, which is influenced by various factors and the metabolic activities of yeasts and bacteria during fermentation.

More impressive, perhaps, is the ability of ChatGPT to perform similar time-saving tasks for the corporate speechwriter ploughing through source material in other languages. Take Section 3.2 from this French paper on the Relationship Between Comprehension Ability and Verbal Areas of the Neocortex: A Brief Study. Google Translate gave me the title in English. But pasting section 3.2 ‘Relation entre intelligence et facilité d’expression‘ (in French) and asking for the 10 main points (in English) generates:

Here are the 10 main points of the paper:

1. The concept that each person possesses a fixed and genetically determined degree of intelligence is completely false.
2. The degree of ease with which individuals understand things varies from person to person and is not fixed or genetically determined.
3. The degree of intelligence can vary throughout a person’s life based on the level of verbal expression and the habit of questioning one’s own conclusions.
4. Verbal expression and the willingness to question one’s own conclusions can increase or decrease based on intellectual activities practiced.
5. Engaging in activities such as constant reflection, problem-solving, reading, and speaking on various subjects can lead to a deeper understanding.
6. Starting to engage in intellectual activities that were previously not practiced can increase one’s understanding.
7. If a person stops engaging in these activities, their overall understanding capacity gradually decreases.
8. Changes in intellectual state occur progressively and are often unnoticed, similar to the growth process of a tree.
9. Human thought processes can be categorized into two forms: thinking through association of images and thinking through association of words.
10. The use of language enables us to describe and understand sensory perceptions, leading to verbal thought processes and increased comprehension abilities.

This took less than no time, a clear advantage for speechwriters who need to research material outside their monoglot backyard.

The Miller

As mentioned above, generative A.I. can condense and summarize the most turgid information.

The Alchemist

This is the heart of the matter. Speechwriters like Murray celebrate the ‘mystique’ of the human touch, where, as I wrote in 2008, “you’ll take their words and sit in your room all night spinning them into gold. And next morning no-one will know how you did it.”

Undoubtedly, great speechwriters will beat generative A.I. at this part of the game — at least for now. But when machines can win at chess and Go, don’t bet against them in the long term. And quite frankly, most corporate executives who writers work long hours to support couldn’t care less about sparkling rhetoric. While Justina Chen claims that “It’s important that a leader be a good storyteller, but equally important that the leader embody that story,” understand she was working with people at the top of the executive hierarchy. For every Steve Jobs keynote, there’s a hundred less able executives unwilling to engage with a writer to the level needed to create compelling content.

I’ll just say that any speechwriter searching for that perfect turn of phrase or summary story should be able to use generative A.I. to grease the creative wheels. I’ve had fun in this regard playing with A.I.’s take on literature and had it suggest a screenplay. Within the confines of most corporate presentations, it should be able to offer more than sufficiently good creative ideas and turns of phrase.

Suggestion: Take the transcript of a past talk by your executive and ask ChatGPT to revise a first draft in that voice.

The Monk

The Medieval analogy I chose to reflect the intense effort corporate speechwriters put into creating PowerPoint slides was the work of monks in the Scriptorium. There’s a whole industry designed to help develop effective presentations for ‘visual storytelling.’ Obviously, a text-based generative A.I. tool like ChatGPT can only help with this in a limited way.

I’ve experimented with MidJourney to produce interesting, creative images which could be included in slides (e.g. the images at the top of this series). But, to be honest, most companies employ graphics people for their logos, product pictures, and other branded images.

However, there’s a growing list of A.I. tools specifically designed to help with slides. These claim to be able to create designs for you in a jiffy, organize your slides to help you tell a story, and include design templates.

Canva has text-to-image generation capabilities specifically tailored to presentations.

Professional designers can now access Adobe Photoshop’s Firefly with generative fill capability.

The Wandering Minstrel

I concluded my trip through Medieval speechwriting with advice about making a living as a freelance speechwriter. The need to work fast and stay at the top of your game demands, for today’s freelancer, embracing generative A.I. as a competitive advantage.

Next: The political speechwriter.