Startup Advisor Role Prompt
An expert startup advisor role prompt — stage-aware, capital-efficiency-minded, and built to name the riskiest assumption in any plan instead of cheering it on.
A complete 'act as a product manager' role prompt — the perspective, responsibilities, and decision criteria a real PM brings, not just the job title.
'Act as a product manager' gives the model a name tag; a role prompt gives it a reasoning framework. A real PM judges features by the problem they solve, treats prioritization as the core job, and weighs every call against impact, effort, and risk. This resource carries the full role prompt with that framework built in — paste it, then ask your roadmap, prioritization, or requirements question, and the answers come back shaped like PM thinking: options, trade-offs, and a metric.
Open in the generator
The inputs load pre-set: Senior level, SaaS industry, Strategic style, Discovery + Prioritization focus.
Generate and adjust
Switch level or focus areas and watch the prompt change — Principal adds systems-level reasoning, different focus areas shift the depth.
Paste, then ask
Role prompt first, your question second. The decision criteria shape every answer that follows.
It shapes the AI's answers like a working PM: each recommendation comes back as the problem, the options considered, the recommendation, and the trade-off accepted. It quantifies impact where it can and says "unknown — here is how to find out" where it can't, judging every call against user impact, effort, and risk instead of just agreeing with your idea.
Paste the role prompt first, then your roadmap, prioritization, or requirements question with the real user problem and the constraints around it. Its focus areas are discovery and prioritization, so the more you say about who the users are, how often the problem bites, and what you have already tried, the sharper the trade-off it names. Thin context gets generic product tips.
No — it is a sparring partner that argues in-discipline and names the trade-off, not the owner of your roadmap. Run it in your own AI tool to pressure-test a decision; it weighs impact, effort, and risk and will push back when the request itself is the problem, but you own the roadmap, the strategy, and the final call. It structures the decision; it doesn't make it.
Use the role prompt when you want PM-shaped reasoning — a second opinion on a roadmap call, a prioritization argument, or the trade-off behind a feature. It produces the thinking, not the finished artifact: to write the requirements document itself, pair this role with a task prompt that specifies the format. Reach for it for the judgment behind the decision, not a polished deliverable.
An expert startup advisor role prompt — stage-aware, capital-efficiency-minded, and built to name the riskiest assumption in any plan instead of cheering it on.
Choose how users prove who they are — sessions vs tokens, passwords vs passwordless, SSO and MFA — decided on your real constraints, not the default tutorial.
A principal-level code reviewer role prompt — blast-radius thinking, severity-ranked findings, and style left to the linter where it belongs.
Convert scattered bug notes, Slack messages, or user complaints into structured engineering tasks with reproduction steps, severity, and root cause hypothesis.
'Make it good', 'be detailed', 'keep it interesting' — vague prompts get vague output. The fix is mechanical: replace every fuzzy word with a checkable instruction.
A reusable AI agent task template with variables for objective, context, available tools, constraints, success criteria, failure handling, and output format.
Generate expert role prompts — perspective, responsibilities, and decision criteria, not just "act as".
Ask AI which option to pick and it names one in the first sentence — no criteria, no options laid side by side, its assumptions hidden. Here's how to make it compare the choices against explicit criteria first, then recommend with caveats you can actually check.
AI hands back a clean "yes" with no sign of what it's resting on or what would flip it. Here's how to make the model show its load-bearing assumptions and the specific changes that would flip, narrow, or defer its recommendation — so you see how fragile the answer really is.
Weeks later, all that survives a decision is "we chose export first" — the why, the rejected option, and the assumption are gone. Here's how to have AI write a decision log: the decision, the reasoning, the options turned down, the assumptions, and a trigger to revisit it.
Before asking AI which option to pick, have it classify the decision's reversal cost — reversible, hard-to-reverse, or irreversible — so you move fast on the easy calls and slow down on the one-way doors. A candidate reading you confirm, not a verdict it issues.