Prompt Engineering for Public Speaking: How to Get Better Results from AI
Liam Sandford
Liam Sandford is a Head of Marketing, public speaking expert, and 2x Best Selling Author including the book Effortless Public Speaking. He helps ambitious professionals and entrepreneurs communicate with impact to get noticed, grow their career, and build their business.
Most speakers who try AI for the first time type something vague, get something generic back, and conclude that the tool is not that useful. The problem is rarely the AI. It is almost always the prompt.
The difference between a mediocre AI output and one that genuinely sharpens your preparation comes down to how clearly you communicate what you need. This is not a technical skill reserved for developers. It is the same skill that makes you a better communicator on stage: clarity, specificity, and knowing what outcome you want before you open your mouth.
If you have been experimenting with tools like Chat GPT or Claude to prepare for presentations and finding the results underwhelming, the fix is usually simpler than you think. You need to get better at asking.
Why Vague Prompts Produce Vague Speeches
A prompt like "help me write a speech about leadership" gives AI nothing meaningful to work with. It does not know your audience, your context, your experience, or what you want people to do after listening to you. So it fills the gaps with the most average, common version of a leadership speech it can assemble.
This mirrors a problem in public speaking itself. If your core message is vague, your delivery will be vague. The same rule applies to AI: the quality of your input determines the quality of the output.
The more specific you are about who you are speaking to, what matters to them, and what you want to achieve, the more useful every AI response becomes.
How to Structure a Prompt That Gets Useful Results
A strong prompt for public speaking preparation has four elements: context, audience, task, and constraints.
Context tells the AI what the situation is. "I am giving a 15-minute talk at a regional sales conference for financial advisers who are sceptical about adopting new technology."
Audience tells it who you are speaking to and what they care about. "They are experienced professionals who value client relationships over automation."
Task tells it exactly what you need. "Give me three opening hook options that acknowledge their scepticism while creating curiosity about the upside."
Constraints set the boundaries. "Keep each option under 40 words. Avoid jargon. Use conversational language I can deliver naturally."
When you provide all four, the output stops being generic advice and starts becoming material you can actually work with.
Why Your First Prompt Should Never Be Your Last
One of the most common mistakes is treating AI like a search engine: type one query, take the first result, move on. That approach wastes most of AI's value.
The real power sits in the follow up. After your first response, push back. Ask AI to challenge its own suggestion. Request alternatives. Tell it what felt off about the first attempt and why.
This iterative process mirrors how you would work with a speaking coach or a trusted colleague. You would not accept the first draft of an opening without testing it, questioning it, and refining it. AI works the same way, but only if you treat it as a conversation rather than a vending machine.
How Prompt Specificity Changes Every Stage of Speech Preparation
Prompt engineering is not just about one perfect prompt. It is about asking the right question at each stage of your preparation.
When you are exploring ideas, broad prompts work. "What are the biggest misconceptions about [topic] among [audience]?" gives you raw material to react to.
When you are structuring your talk, precision matters more. "Using the Nano Speech framework of Open, Body, Close, give me three structural options for a talk on [topic] aimed at [audience] where the goal is [outcome]."
When you are refining your close, the prompt should be even tighter. "Rewrite this closing paragraph to be more direct, under 30 words, and end with a clear action the audience can take today."
Each stage needs a different type of prompt, and knowing which to use when is what separates useful AI integration from frustrating trial and error.
How to Use Prompts to Stress Test Your Core Message
One of the most valuable uses of prompt engineering is pressure testing what you plan to say before you say it. Most speakers skip this step entirely and only discover weak points in their message when they are on stage and it is too late to fix them.
Ask AI to poke holes in your argument. "Here is my core message: [message]. What would a sceptical audience member challenge about this? Where is my reasoning weakest?" This forces you to confront gaps you might have overlooked.
You can also use prompts to test whether your message lands differently with different audiences. "How would a room of CEOs interpret this message versus a room of early career professionals?" The answers help you adjust your framing without changing your substance.
For a complete overview of how AI supports every stage of your public speaking preparation, the Ultimate Guide to Using AI for Public Speaking covers the full picture.
Why Role Based Prompts Produce Better Feedback
One of the most underused prompt techniques is asking AI to adopt a specific perspective before responding. Instead of "give me feedback on this opening," try "act as a sceptical audience member who has heard dozens of talks on this topic. What is your honest reaction to this opening?"
Role based prompts force the AI to filter its response through a particular lens, which produces more targeted and useful feedback than a generic review.
You can use this technique for:
Simulating a hostile Q&A panel to prepare for tough questions
Getting feedback from the perspective of someone unfamiliar with your topic
Testing whether your close works for decision makers versus influencers in the room
The key is to define the role clearly. The more specific the persona, the more specific the feedback.
How to Avoid Over Engineering Your Prompts
There is a tipping point where prompts become so elaborate that they defeat the purpose. If you spend more time crafting the perfect prompt than you would spend just thinking through the problem yourself, you have overcomplicated the process.
A good prompt is specific, not exhaustive. It gives AI enough context to be useful without turning every interaction into a 200 word briefing document.
The test is simple: could you explain what you need to a knowledgeable colleague in under 30 seconds? If so, that is roughly the right level of detail for your prompt. If you find yourself writing a page of instructions, step back and break the task into smaller pieces instead.
How to Build a Prompt Library for Recurring Speaking Situations
If you speak regularly, you will find yourself facing the same preparation challenges repeatedly. Building a small library of proven prompts saves time and improves consistency.
Keep prompts that have produced genuinely useful results. Organise them by preparation stage:
Ideation prompts: for generating fresh angles on familiar topics
Structure prompts: for testing different talk frameworks
Refinement prompts: for tightening language and cutting filler
Rehearsal prompts: for simulating audience questions and objections
This is not about creating a rigid system. It is about reducing the friction of starting so you can spend more time on the work that matters: understanding your material deeply enough to deliver it with confidence and flexibility.
What Prompt Engineering Cannot Replace
No prompt, however well crafted, replaces the work of internalising your material. AI can help you think more clearly, structure more efficiently, and prepare more thoroughly. But the moment you step on stage, what matters is how well you understand your content, not how polished the AI output was.
Prompt engineering is a preparation skill. It makes the preparation phase faster and sharper. It does not make you a better speaker in the room. That comes from practice, presence, and the willingness to connect with the people in front of you.
Frequently Asked Questions About Prompt Engineering for Public Speaking
What is the best prompt format for preparing a speech with AI?
The most effective format includes four elements: context (the speaking situation), audience (who they are and what they care about), task (exactly what you need the AI to produce), and constraints (length, tone, style boundaries). Providing all four consistently produces more relevant and usable output than open ended requests.
How many prompts should I use to prepare one speech?
There is no fixed number, but most effective preparation involves at least four to six exchanges per section of your talk. Start broad to explore ideas, then narrow with follow up prompts that refine, challenge, and tighten the material. Treat it as a conversation, not a single query.
Can prompt engineering help with nerves before a talk?
Indirectly, yes. Better prompts lead to sharper preparation, which builds genuine familiarity with your material. That familiarity is one of the most reliable ways to reduce anxiety. When you know your content deeply rather than superficially, you feel less dependent on memory and more able to respond to what happens in the room.
Should I use the same prompts for every speech?
Reuse the structure of prompts that have worked, but always adapt the context and audience details. A prompt library gives you a starting point, not a template you paste without thinking. The specificity of each prompt is what makes AI outputs useful, and that specificity must change with every speaking situation.
TL;DR: Prompt Engineering for Public Speaking
Better prompts produce better AI outputs, which produce better speech preparation.
Structure every prompt with context, audience, task, and constraints
Use follow up prompts to refine, challenge, and improve initial outputs
Match your prompt specificity to the preparation stage you are in
Build a prompt library for recurring speaking situations to save time
Remember that no prompt replaces the work of understanding your material deeply enough to deliver it with confidence
More From Liam Sandford
Read my book: Effortless Public Speaking. Learn how to speak confidently, reduce stress, and turn public speaking into your competitive advantage. These actionable public speaking tips will help you improve your presentation skills for any audience.
Join the free 5-day email course: Get daily lessons packed with practical strategies to deliver effective presentations and speak confidently. This course is designed to build your public speaking skills step by step. Sign up below: