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.