Product Manager Role Prompt
A complete 'act as a product manager' role prompt — the perspective, responsibilities, and decision criteria a real PM brings, not just the job title.
An operations manager role prompt that thinks in flows — map the actual process, find the constraint that matters, and never automate a bad process into a faster bad process.
Operations advice from a bare model optimizes whatever you point it at — which is the classic ops mistake, because fixing a non-bottleneck changes nothing. This role prompt builds in the operating discipline: map the actual process before changing it, measure throughput and cost per unit, design handoffs so failures are visible, and check every proposal against the real constraint. Recommendations arrive in an auditable shape: current state, constraint, change, expected effect, measurement — rollback path included.
Open in the generator
Senior level, E-commerce, Analytical style, Bottlenecks + Automation focus — pre-set. Swap the industry to yours.
Describe the actual flow
Paste the role, then the process as it really runs — steps, owners, volumes, where it hurts.
Demand the rollback path
Every proposed change ends with measurement and rollback. If a change can't be rolled back, the role should flag it before you ship it.
Five parts plus a rollback path: current state, constraint, proposed change, expected effect, measurement — the Output expectations spell that out, and "always include the rollback path for process changes." That makes ops proposals reviewable like engineering changes. The role-prompt-generator produces this persona; you run it in your assistant, and the role should flag a change that can't be rolled back before you ship it.
It weighs every recommendation against constraint impact — "does this change move the actual bottleneck" — and maps the actual process, not the documented one, before changing anything. A built-in perspective warns "automate a bad process and you get bad results faster," so it won't automate a bad process into a faster one. It's constraint-first advice you evaluate; the role also pushes back "when the request itself is the problem."
Yes. The role opens in the generator preset to Senior level, E-commerce, with Bottlenecks and Automation focus, and workflow step 1 says "swap the industry to yours." The working style ties recommendations to conversion rate, average order value, and return rates — e-commerce metrics — so when you change the industry, adjust those tie-in metrics too, keeping the reasoning framework matched to your flow.
A complete 'act as a product manager' role prompt — the perspective, responsibilities, and decision criteria a real PM brings, not just the job title.
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.
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".