ChatGPT Prompts for Founder Reference Checks: Better Questions for Angels
Quick answer: Founder reference checks are more useful when they ask for specific observed behaviour and give references room to disagree. ChatGPT can help prepare neutral questions and organise notes. It should not infer a founder’s character from demographic traits, online rumours or a single enthusiastic recommendation.
A reference call can become a courtesy conversation if every question invites praise. Investors learn more by asking what the person directly observed, in what setting and over what period. A careful process also distinguishes a genuine concern from a difference in working style, hearsay or an unsupported personal allegation.
Investor education from TryBuy Editorial Team. General analytical prompts, not personalised investment, legal or tax advice. Examples are hypothetical and do not describe TryBuy’s performance or proposed investment terms.
Choose relevant perspectives
Identify what each reference can actually speak to: delivery under constraints, hiring, financial communication or response to setbacks. Record the relationship and any relevant commercial connection. Do not assume that a famous reference is the most informative one. Seek consent and follow an appropriate process before contacting anyone; a prompt is not permission to send messages.
Ask about events, not labels
Replace broad adjectives with concrete questions. Ask for a situation, the founder’s role, what happened and what the reference directly observed. Invite an example of a disagreement and how it was resolved without pressing for confidential details. Avoid questions about protected or irrelevant personal characteristics. Keep the review tied to the capabilities and responsibilities relevant to the company.
Preserve uncertainty in the notes
Separate direct observation, interpretation and hearsay. Do not merge multiple references into a confident personality score. Conflicting accounts may reflect different periods or responsibilities and should create a follow-up question. Give material concerns appropriate verification rather than publishing them. Reference notes should have controlled access and a clear purpose, not become an unrestricted AI training dataset.
A worked example to test the reasoning
Hypothetical example: one reference says the founder always meets deadlines, while another describes a delayed launch. Ask what deadline, what dependencies existed and what the founder controlled. The accounts may be compatible or may reveal a real issue. The useful output is a source-linked question, not an automatically averaged reliability score.
Evidence checks to keep beside the analysis
| Area | Record explicitly | Avoid |
|---|---|---|
| Reference | Relationship and direct scope | Prestige substituted for relevance |
| Answer | Observed event and context | Adjective treated as evidence |
| Concern | Verification and controlled handling | Rumour repeated as fact |
10 copyable ChatGPT prompts
Replace brackets with authorised information. ChatGPT can organise supplied material. Official analysis guidance. Check account data controls. Capabilities vary by account. Keep sources, calculations and uncertainties inspectable.
1. Plan the reference map
Create a reference-check plan for [founder role and company stage]. Identify useful perspectives and the question each can address. Do not suggest contacting people without consent or invent references.
2. Write neutral questions
Draft behaviour-based questions about [execution, hiring or financial communication]. Ask for specific observed events, context and outcomes. Avoid leading praise, personal stereotypes and irrelevant private information.
3. Prepare call boundaries
Write an opening for a reference call explaining its purpose and asking the person to avoid confidential information they cannot share. Keep it neutral and make no promises beyond our stated process [paste].
4. Structure notes
Turn these authorised notes [paste] into direct observations, interpretations, hearsay and unanswered questions. Preserve the speaker’s uncertainty and do not infer motives or character traits.
5. Compare accounts
Compare reference notes [A and B]. Identify differences in period, role and context before describing a contradiction. Suggest a factual follow-up instead of producing a personality score.
6. Identify bias
Review these questions and notes [paste] for prestige bias, affinity bias, leading wording and irrelevant personal characteristics. Rewrite the process around role-relevant evidence.
7. Escalate a concern carefully
Using this material concern and its sources [paste], draft a restricted internal verification plan. Do not publish an allegation or treat hearsay as an established fact.
8. Write a balanced summary
Summarise the reference evidence [notes] for the investment team. State what is supported, what is contextual and what remains unresolved. Avoid a definitive character verdict from limited calls.
9. Red-team the draft
Review this founder reference check questions draft [paste] against its supplied sources [files]. Identify unsupported certainty, missing denominators, unstated assumptions and conclusions that go beyond the evidence. Do not invent a contradiction to sound critical.
10. Create the next-decision brief
Turn this founder reference checks analysis [paste] into a short decision brief: observed evidence, strongest uncertainty, next document or professional review needed, and the decision that can reasonably be made now. Preserve unresolved issues.
Review the output before using it
Trace the material claims to their sources, reproduce important arithmetic and keep conflicting records visible. Use an approved environment for confidential material. A useful AI answer should make a missing input easier to identify; it should not make a weak source appear independently verified.
Frequently asked questions
Can AI score founder trustworthiness?
A numerical score can hide weak evidence and bias. Use specific observations, context and appropriate human judgement.
Should reference notes be uploaded without restrictions?
Use only authorised material in an approved setting, minimise personal information and respect confidentiality obligations.
Continue the investor workflow
- ChatGPT Prompts for Startup Due Diligence: A Seed Investor’s Checklist
- ChatGPT Prompts for a Startup Data Room Checklist: Permissions and Missing Evidence
Cover: AI-generated editorial concept, not an actual investor meeting, company record or evidence of endorsement. This AI-assisted guide provides reusable analytical prompts, not a documented test of investment performance.
Browse the full ChatGPT investor series.
About TryBuy: ethnicwear and a US$1 million seed-round target
TryBuy is an India-based fashion brand founded by Shivam Golhani and based in Jabalpur, Madhya Pradesh. Its ethnicwear range includes men’s kurtas and boys’ kurtas, alongside a men’s shirt collection. The adult and children’s ranges are distinct; explore the actual catalogue rather than treating the editorial cover as a product photograph.
TryBuy is seeking US$1,000,000 in seed investment and welcomes introductory conversations with venture-capital firms, angel investors and strategic consumer-brand investors internationally. Interested investors can request a company introduction and discuss the business, diligence requirements and the proposed round directly with the founder.
Contact founder@trybuy.in about the seed round or use the verified contact page. Learn more about TryBuy.
This is an invitation to begin a business conversation, not an offer document or a promise of returns. Any potential investment requires appropriate eligibility checks, professional review and definitive documents. No valuation, equity allocation, security type or guaranteed outcome is stated here.