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.
A principal-level code reviewer role prompt — blast-radius thinking, severity-ranked findings, and style left to the linter where it belongs.
'Review my code' without a role gets you a line-by-line commentary that treats a typo and an injection risk as equals. This role prompt builds the reviewer experienced teams actually have: one who reviews the change's blast radius rather than just its lines, separates must-fix from nit explicitly, and leaves style to the linter so attention goes to correctness, security, and design. The principal level adds reversibility awareness — extra caution exactly where mistakes are expensive.
Open in the generator
Principal level, Technology industry, Risk-Aware style, Correctness + Security focus — pre-set.
Generate, paste, then add the diff
Role prompt first, then the code or diff with one line of context about what it's supposed to do.
Demand the severity split
The must-fix/should-fix/nit contract is the difference between a review and a reaction.
It outputs findings tagged by severity — must-fix, should-fix, or nit — each with a file reference, so a typo and an injection risk never sit at the same priority. When it rejects an approach it proposes the alternative rather than just objecting. You paste your diff and run it in ChatGPT, Claude, or Gemini — the severity contract is the format, not an automated pipeline.
By design it treats style as the linter's job and points the reviewer's attention at logic, security, and design instead. That's why it won't fill the review with spacing and naming nits — those are cheaper to enforce automatically, so spending a human-style review on them wastes it. Configure a linter for formatting and let this prompt focus on correctness and security, its two weighted focus areas.
Don't reach for it when you need an automated PR-review pipeline with a fixed output contract wired into CI — this is a conversational role prompt you drive by hand, one diff at a time. It also won't replace a linter for style enforcement. Use it when you want a principal-level pass on correctness and security before you open the PR, not an unattended gate.
You run it yourself — NewPrompt gives you the role prompt, and you paste it plus your diff into your own AI tool to get the review. The findings are a prioritized, senior-level read on correctness and security, not a guarantee that every bug or vulnerability is caught. Treat must-fix items as a strong signal to verify, and keep a human reviewer accountable for merging.
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".
"Act as a lawyer" makes AI answer with authority it doesn't have — a verdict or a diagnosis from partial context. Here's how to write a role prompt that gives an expert lens without the overreach: scope, allowed and forbidden actions, and decision ownership that stays yours.