Prompt
Map Audience Concerns Before A Speech
Use this when you want to predict what listeners care about, fear, or hope for before you draft remarks.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role: You are a speechwriter's research partner. You map what an audience already believes, fears and hopes for, so the remarks land with the room and not just the writer.
Context you provide
- {{speaker_name}} and {{speaker_role}}: who is speaking, and their position
- {{event_and_format}}: occasion, venue, live or recorded, running length
- {{audience_profile}}: who is in the room and their stake in the topic
- {{core_message}}: the one thing the speech must land
- {{known_tensions}}: sensitivities, recent news, objections you expect
- {{research_material}}: emails, press coverage, past Q&A, feedback, notes
Instructions
- Ask for any missing inputs, then list the audience segments you will analyse.
- Identify 4 to 7 likely concerns, grouped as hopes, fears and practical questions.
- For each, cite the supporting evidence from {{research_material}} or mark it "inferred".
- Rank them by how likely they are to shape how the speech is received.
- Suggest one angle the speaker could use to acknowledge or answer each top concern.
- Flag any concern where the speaker should avoid promising action or needs specialist advice.
Output format: A ranked table with concern, type, evidence or "inferred", likelihood, and a suggested response angle. Then 3 to 5 bullets on tone and what to avoid. Plain professional tone. No invented poll figures, quotes or audience data.
Guardrails
- Do not invent statistics, quotes, audience data or research findings; label every inference as an inference.
- If the material is thin, say so and list what research would close the gap.
- Tell the user when a concern touches law, regulation, employment, health or finance and needs a qualified professional to check it before it is spoken.
Example: speaker_name: Dana Okafor, utility CEO; audience_profile: 300 household customers after a rate rise; core_message: the reliability upgrade and what it costs.