Home · Business · Sales · Demos & follow-up
As of 13 August 2026, AI can only partly research a prospect before a demo.
Most people should hand this to a purpose-built tool.
Can you do it?
5 minutesto a draft.
30 minutesto something you’d act on.
Cost, all in£0
Skill neededchat-fluent
Who has to check ita colleague
What the alternative costsApollo.io is a prospect database with AI outreach sequences and enrichment.
If this goes wrong: you lead with an invented or irrelevant assumption, the prospect corrects you, and the demo loses credibility.
What to actually do
Use a tool built for this
The route this page recommends
Do it yourself
Second choiceA chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.
How to actually do it
- Open the prospect's company website, professional profile and any relevant public news or filings, and copy the URLs into a working document.
- Open your CRM record and gather the prospect's role, previous contact notes, stated needs, existing products and the agreed purpose of the demo.
- Paste the public links, CRM notes and your product description into the prompt, removing unnecessary personal or sensitive information.
- Ask the chatbot to produce the briefing and keep confirmed facts, inferences and unknowns in separate sections.
- Open every source link in the briefing and compare the cited facts, dates and job details with the original pages, deleting anything unsupported or stale.
- Send the checked briefing to a colleague who understands the account, then revise the discovery questions and demo plan to remove assumptions they cannot support.
- Use the final questions in the demo to test the remaining unknowns rather than presenting inferred priorities as facts.
Prompt
Research this prospect and account before a sales demo. Use only the information I provide and publicly accessible sources that you can link to. Do not invent facts, job responsibilities, business priorities, recent events or buying intent. Separate confirmed facts from reasonable inferences and unknowns. Account: [COMPANY NAME] Company website: [URL] Prospect name and job title: [NAME AND TITLE] Prospect or company profile URL: [URL] Known CRM notes: [PASTE NOTES OR WRITE NONE] Our product and target customer: [DESCRIBE PRODUCT, CUSTOMER AND MAIN USE CASE] Demo objective: [WHAT YOU WANT TO ACHIEVE] Return a concise briefing with these sections: 1. Confirmed account facts, with a source link for each important claim. 2. Confirmed prospect facts relevant to the meeting. 3. Likely business priorities, clearly labelled as inferences and linked to the evidence behind each one. 4. Relevant recent developments, with the publication or page date and source link. If you cannot establish that something is current, say so. 5. Possible problems our product may address, without claiming that the prospect has those problems. 6. Three discovery questions that test the most important assumptions without sounding scripted. 7. Likely stakeholders or departments to ask about, only where supported by the evidence. 8. A short meeting plan that uses the confirmed facts, avoids unsupported personalisation and states what I still need to verify before the demo. End with a table containing: claim, source, confidence, and what I should verify with the prospect. Keep private or sensitive personal information out of the briefing unless I explicitly provide it and it is necessary for the meeting.
Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.
Hand it to a person
The distant thirdA person who owns the outcome does this end to end, worth it when the failure is dear.
What it gets wrong
- AI cannot see private CRM context, internal account politics or information the prospect has not made public.
- AI cannot reliably distinguish a genuine buying priority from a plausible interpretation of a company announcement.
- AI cannot guarantee that public pages, job titles and business developments are current.
- AI cannot replace a salesperson's judgement about which detail will build trust with this particular prospect.
- AI cannot take responsibility for an awkward or misleading assumption used in the meeting.
What caps this at PARTLY: context depth, real time truth and private data access.
How we scored this
Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.
| Axis | Score (0–2) |
|---|---|
| Output | 2 |
| Inputs | 1 |
| Verification | 1 |
| Liability | 1 |
| Effort delta | 2 |
| Total | 7 / 10 |
The methodology and its thresholds are published in full.
FAQ
- Can ChatGPT research a prospect before a demo?
- Yes, it can gather public information, summarise the account and draft discovery questions. It cannot access private CRM context or reliably know which inferred priority matters, so check every important claim and label assumptions before using them.
- What information should I give AI to research a prospect?
- Give it the company website, relevant public profile links, the prospect's role, your CRM notes, your product context and the purpose of the demo. Remove unnecessary personal information and tell it to separate confirmed facts from inferences.
- How do I stop AI from making up facts about a prospect?
- Require a source link for each important claim and instruct it to say when information is unknown or cannot be established as current. Open the sources yourself and ask a colleague to challenge the assumptions before the meeting.
- Is AI prospect research worth using for sales demos?
- Partly. It can remove much of the searching, summarising and question-drafting work, but the value depends on the quality of the information you supply and the checking you do before relying on it.
Nearby answers
- Can AI send demo follow-up emails automatically?PARTLY
- Can AI book a follow-up meeting after a sales demo?YES
- Can AI create a follow-up sequence after a sales demo?YES
- Can AI create a sales proposal after a demo?YES
- Can AI forecast whether a sales demo will convert?PARTLY
- Can AI prepare answers to likely demo objections?YES
Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.
The newsletter
AI news, new answers and product picks, straight to your inbox.