Senior Code Reviewer Role Prompt
A principal-level code reviewer role prompt — blast-radius thinking, severity-ranked findings, and style left to the linter where it belongs.
View Resource →Prompt Builders
Role Prompt Generator
Turn "act as a product manager" into a role the AI can actually inhabit — with the perspective, responsibilities, and decision criteria a real expert brings. Pick a role, set the level and style, and generate. Runs entirely in your browser.
Who should the AI act as? A title, not a description — e.g. "Product Manager", "Technical Recruiter".
Focus Areas (optional, multi-select)
Recognized roles offer focus areas — selected ones get extra weight in the prompt.
Role Prompt
Copywriter Role Prompt
Make AI act as a copywriter that sells — clarity over cleverness, benefit-first, one clear action — instead of producing flat, generic marketing text.
View Resource →Customer Success Manager Role Prompt
A CSM role prompt built on leading indicators — churn is decided months before the cancellation, adoption beats satisfaction, renewals are earned in the boring quarters.
View Resource →Data Analyst Role Prompt
A data analyst role prompt with statistical honesty built in — clarify the decision first, treat correlation as a hypothesis, and never launder uncertainty into precision.
View Resource →DevOps Engineer Role Prompt
Make AI act as a DevOps engineer — CI/CD, infrastructure as code, observability, and reliability — instead of a generic assistant.
View Resource →Marketing Strategist Role Prompt
A marketing strategist role prompt that thinks positioning-first — channel saturation curves, attribution honesty, and one testable angle per recommendation.
View Resource →Operations Manager Role Prompt
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.
View Resource →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.
View Resource →QA Engineer Role Prompt
Make AI act as a QA engineer — test strategy, edge cases, regression prevention, and validation — instead of an assistant that writes happy-path tests.
View Resource →Sales Consultant Role Prompt
An expert sales consultant role prompt — qualification-first, discovery-before-pitch, with exact phrasings and the situations where each technique backfires.
View Resource →Security Engineer Role Prompt
Make AI act as a security engineer — threat modeling, secure design, risk assessment, and defensive recommendations — instead of a generic assistant.
View Resource →Software Architect Role Prompt
Make AI act as a software architect — system design, scalability, service boundaries, and trade-offs — instead of jumping straight to code.
View Resource →Software Engineer Role Prompt
Make AI act as a software engineer — design, implementation, and testing trade-offs — instead of a generic assistant that writes whatever you ask.
View Resource →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.
View Resource →Technical Recruiter Role Prompt
A technical recruiter role prompt that evaluates hiring quality at month six — screening design, evidence-based assessment, and bias flags built in.
View Resource →Tutor Role Prompt
Make AI act as a tutor that actually teaches — plain language first, understanding checks, building from what you know — not a wall of dense explanation.
View Resource →UX Researcher Role Prompt
A UX researcher role prompt that respects evidence — observation over opinion, sample-size honesty, and findings that name their own limitations.
View Resource →AI System Prompt Design Workflow
Design a system prompt that holds up in production — define the role precisely, engineer the behavior and guardrails on top of it, then check it reads clearly before you ship.
View Playbook →AI Agent Instruction Workflow
Instruct an AI agent that runs on its own without it wandering off — anchor it to a role, write the agent system prompt, then lay out the multi-step plan it works through.
View Playbook →How it works
Type the role the AI should act as — or pick a preset — then set the experience level, an optional industry, and a working style. Recognized roles unlock focus areas you can multi-select. Click Generate Role Prompt and the generator builds a complete persona from its browser-side role profile system: the perspective that role views problems through, the responsibilities it owns, the decision criteria it weighs, and output expectations that match how that expert actually communicates. Nothing leaves your browser. Unknown roles get an honest scaffold with [bracketed] placeholders instead of invented expertise.
Use cases
- Turning 'act as a product manager' into a persona that reasons like one
- Getting expert-shaped advice — decision criteria and trade-offs, not generic tips
- Standardizing the roles your team uses across AI conversations
- Building the role half of a larger prompt before adding your task
Pro tips
- Experience level changes behavior, not just the title: a junior flags uncertainty and asks clarifying questions, an expert reasons from first principles and takes positions.
- Use focus areas when you need depth over breadth — two selected areas tell the role where to go deeper than everywhere else.
- Pair the industry with the role: 'Product Manager — Finance' weighs compliance as a hard constraint; the same role in SaaS optimizes activation and churn.
- Paste the role prompt first, then your question as the next message. The role frames every answer that follows.
FAQ
How is this different from the System Prompt Generator?
The System Prompt Generator designs how an AI worker should behave — objectives, behavior rules, restrictions, escalation paths — for operational systems like a support agent or bug triage assistant. The Role Prompt Generator answers a smaller, different question: who should the AI act as? It defines an expert persona — perspective, responsibilities, decision criteria — in seconds. Building an AI worker → SPG. Wanting advice from a convincing expert → this tool.
What makes the output better than writing 'act as X' myself?
The role profile system. Each recognized role carries researched content: how that role actually thinks (a recruiter evaluates hiring quality at month six, not offer acceptance), what it owns, and what criteria it weighs. That's the difference between a model wearing a name tag and one that reasons in character.
What happens with a role the tool doesn't recognize?
You get the same professional structure with [bracketed] placeholders where the role-specific knowledge belongs — the lenses, responsibilities, and criteria only someone who knows that role can fill in. The generator never fakes expertise it doesn't have.
Which roles have full profiles?
Eleven, chosen for quality over quantity: Product Manager, Startup Advisor, Technical Recruiter, Senior Code Reviewer, UX Researcher, Marketing Strategist, Sales Consultant, Data Analyst, Customer Success Manager, Operations Manager, and SEO Consultant. Matching is fuzzy — 'PM', 'product owner', and 'tech lead' resolve to the right profiles.
Does the experience level actually change anything?
Yes — it changes the instructions, not just the adjective. Junior adds uncertainty-flagging and clarifying questions; Senior adds push-back and second-order effects; Principal adds systems-level reasoning and reversibility awareness; Expert adds first-principles reasoning and explicit opinions.
Can I edit the generated prompt?
Absolutely — it's a starting point built to be edited. Copy it, tighten the focus areas, and if you want to strengthen the wording further, run it through the Prompt Rewriter.