Searchable AI prompt library
Structured instructions for completing individual tasks with an AI tool. Filter by outcome, category, tool, difficulty or keyword.
Open a Prompt to copy its instructions, run supported Prompts privately in Workplace, or prepare a task for Codex where available. Copying text does not run the Prompt.
Use ChatGPT to produce a prioritized, evidence-traceable SEO refresh brief for an existing article, covering intent alignment, content gaps, metadata, links, citations, schema eligibility, verification, and post-refresh measurement without claiming unperformed changes.
Map a manual business process, evaluate AI and deterministic automation opportunities, define human controls, and produce an evidence-linked implementation and validation plan.
Analyze unmanaged workplace AI use with explicit evidence, uncertainty, severity scoring, data-exposure analysis, acceptable-use controls, and a phased governance roadmap.
Design an implementation-ready RAG architecture with governed retrieval, citations, tool boundaries, safety controls, evaluation tests, rollout gates, and evidence-based acceptance criteria.
Design a reusable, risk-aware evaluation harness for an AI prompt, with traceable requirements, realistic test cases, weighted scoring, execution records, release gates, and evidence-based improvement priorities.
Audits AI-generated content against supplied evidence, acceptance criteria, and authorized checks, producing a claim-level verification register, risk controls, and a human release recommendation without overstating what ChatGPT inspected or executed.
Expert ChatGPT prompt for evidence-constrained security analysis of autonomous AI workflows, including permissions, trust boundaries, prompt injection, data exposure, approval controls, observability, containment, rollback, and residual risk.
Use Codex to conduct a read-only, evidence-grounded review of a Laravel pull request across application behavior, authorization, data migrations, queues, caches, compatibility, deployment safety, and test coverage. Findings are tied to code locations or execution evidence, while unverified work and merge authority remain explicit.
Guide Codex through evidence-based diagnosis of Laravel checkout and webhook failures, including signature validation, idempotency, retries, event ordering, payment-state integrity, and gateway compatibility. The prompt permits only authorized workspace changes and requires explicit separation of proposed, executed, unavailable, and unverified work.
Design an implementation-ready multi-agent workflow with explicit agent responsibilities, routing logic, shared-state rules, evidence-backed review gates, authority boundaries, failure recovery, and acceptance tests.
Assess whether an analysis can support a causal claim by examining identification assumptions, design-specific threats, diagnostics, and alternative explanations.
Design a lightweight, evidence-based personal knowledge system for capturing, organizing, retrieving, reviewing, and safely migrating notes and references.