Prompts
AI prompt packs you can copy and adapt
Every pack states who it is for, which models it was tested on and when. Copy a prompt, fill in the variables and compare the result with the example.
All prompt packs
AI Output Evaluation Rubric Prompts
Evaluate AI outputs using hard-failure gates, task-specific quality criteria, evidence and actionable revisions.
For: Prompt designers, QA teams, content teams and agent builders.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Structured Data Extraction Prompts
Extract machine-readable data from messy text with an explicit schema, source evidence, null handling and validation rules.
For: Developers, analysts and automation builders.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
AI Agent Instructions and Guardrails Prompts
Define an agent's role, tools, action boundaries, confirmation rules, escalation paths and observable completion criteria.
For: Agent builders, automation teams and developers.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Automation Workflow Design Prompts
Design an automation from trigger to outcome, including data contracts, branches, approvals, failures, logs and recovery.
For: Operators, automation specialists, agencies and founders.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Unit Test Generation AI Prompts
Derive behavioral test cases from requirements and boundaries, generate framework-specific tests and audit their assertions.
For: Developers, QA engineers and technical teams.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Risk-Based Code Review AI Prompts
Review changes for correctness, security, data loss and regressions, with evidence and precise references instead of style noise.
For: Developers, reviewers and engineering leads.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Debugging from Logs AI Prompts
Diagnose software failures from logs, environment details and reproduction steps using falsifiable hypotheses rather than guesses.
For: Developers, support engineers and technical founders.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
AI Prompts for PRDs and User Stories
Turn validated product context into a scoped PRD, atomic user stories and testable acceptance criteria without inventing requirements.
For: Product managers, founders, designers and engineering leads.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Stakeholder Interview Question Prompts
Design neutral stakeholder interviews tied to explicit learning objectives and a real decision.
For: Product managers, researchers, consultants and transformation teams.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Research Paper Summary AI Prompts
Summarize research by question, method, sample, findings and limitations without strengthening the authors' claims.
For: Students, analysts, researchers and evidence-led teams.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Weighted Decision Matrix AI Prompts
Compare options using explicit criteria, evidence and uncertainty, then test whether the recommendation survives changed assumptions.
For: Buyers, product teams, managers and founders.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Compare Sources and Find Contradictions Prompts
Compare sources claim by claim, distinguish genuine contradictions from scope differences and preserve traceable evidence.
For: Researchers, analysts, journalists and decision-makers.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Voice of Customer Analysis Prompts
Extract recurring pains, desired outcomes, objections and exact language from supplied customer evidence without fabricating consensus.
For: Marketers, product teams, researchers and sales enablement teams.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Content Repurposing AI Prompts
Transform one verified source into channel-specific assets while preserving facts, qualifications, links and brand voice.
For: Content marketers, founders, agencies and social teams.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Search Intent Analysis AI Prompts
Analyze intent from current result-page evidence and decide whether to create, update, merge or avoid a page.
For: SEO strategists, content leads and site owners.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
AI Prompts for SEO Content Briefs
Build a writer-ready SEO brief from actual search evidence, audience needs and existing-site context without invented metrics.
For: SEO specialists, editors, agencies and content teams.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Task Prioritization and Daily Planning Prompts
Rank work with explicit criteria and turn priorities into a realistic schedule that respects time, energy and dependencies.
For: Knowledge workers, managers, freelancers and founders.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Long Document Summary AI Prompts
Summarize long documents without losing attribution, limitations, uncertainty or the distinction between source facts and interpretation.
For: Analysts, operators, consultants and decision-makers.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
AI Prompts for Better Meeting Agendas
Create outcome-led agendas with realistic timings, preparation requirements, decision points and ownership.
For: Team leads, facilitators, account managers and project owners.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Meeting Notes to Action Items AI Prompts
Turn meeting notes into traceable decisions and action items with owners, deadlines, dependencies and explicit gaps.
For: Managers, project leads, operations teams and meeting participants.
- OpenAI GPT-5 (Codex) — editorial dry run
Tested Oct 3, 2026
Want to see prompts used in a full process? Browse workflows.