Browse all 3,765 AI prompts
The complete, free PromptCorrectly library — research-backed prompts and skills for ChatGPT, Claude, and Grok. Every prompt opens to a full, copy-ready page you can fork into the visual Studio. Page 1 of 38.
Engineering
- Staff-Engineer Code ReviewReviews a PR like a senior who optimizes for the next reader, not style nits.
- Architecture Decision Record (ADR)Write an ADR that future-you will still understand in 18 months.
- Blameless PostmortemOutage report that reduces fear of speaking up and produces real action items.
- Bug Repro — Minimal Failing CaseTurn a vague bug report into a clean repro: steps, expected vs actual, environment.
- Tech Debt PrioritizationRank a backlog by leverage × pain × confidence. Output an ordered ranking.
GTM
- Cold Outbound — Peer-to-PeerReach a busy founder without AI-slop tone. Four lines, one ask, no hedging.
- Press Release — YC ToneAnnounce a B2B SaaS launch in the YC style. Sharp lede, two metrics, one founder quote.
- SaaS Pricing — First PrinciplesSet pricing for a new B2B SaaS. Three tiers, unit economics, anchor + decoy logic.
- Positioning — April Dunford MethodFive-step positioning canvas: competitive alternatives, unique attributes, value, ICP, market.
Founder Voice
- Calm + Concrete Investor UpdateMonthly update that earns trust by being honest about misses.
- Founder Voice — Long-Form PostSound like a founder with opinions. Tight thesis, two stories, one bet.
- Strategy Memo — Two-PagerDecision memo that earns the meeting. Context, options, recommendation, risks.
- Board Deck — Narrative FirstBuild a board deck that tells one story. Not 40 slides of metrics.
- Hiring Loop Design — Senior ICDesign a 5-stage interview loop that surfaces real signal, not theater.
- Performance Conversation — Hard TruthHave a hard performance conversation that respects both people. Script + recovery plan.
- Pitch Deck — The NarrativeBuild a 10-slide deck investors don't skim. Inevitability, wedge, traction, ask.
Sales
- Sales Discovery — 7 Questions That Surface PainAsk the questions that surface pain, not features. Seven questions, no leading the witness.
Marketing
- Cold Landing Page RewriteHeadline earns the scroll. Three benefits with proof. One CTA. No hero-image lies.
- Onboarding Email Sequence5-email onboarding that gets users to first value, not just first login.
Research
- Customer Interview SynthesisDistill 12 customer calls into themes, frequencies, and a top-3 list that survives committee.
- Research Paper TL;DRCompress a 30-page paper into 5 lines + 4 structured takeaways.
Writing
- Brand Voice RewriteTake any draft and rewrite it in your brand's voice. Keep meaning, drop hedges.
- Newsletter Issue — Specific Subject LineHook earns the open. 3 curated items, one personal note, soft CTA.
- Resume Rewrite — Tech ICCut every adjective. Quantify three things. Make the recruiter call you back.
- Product Changelog — User-FacingAnnounce a feature ship. Lead with the job it does, not the feature name.
- Conference Talk AbstractSubmit a talk that reviewers can't skip. Hook, claim, 3 takeaways, audience.
- Thought Leadership — Contrarian TakeArgue a contrarian position credibly. Steelman opposition, then dismantle.
Content
- YouTube Script — Built for RetentionHook → reframe → 3 acts → payoff. Designed to hold 60%+ retention.
Design
- UX Critique — First 90 SecondsWalk through an onboarding flow. Flag friction with severity ratings.
- Design Critique — Typography PassCritique a screen's type hierarchy: sizes, weights, leading, optical alignment.
- Empty State — Designed for ActivationAn empty state that teaches the user what to do next. Not just a blank screen.
- Form Validation MicrocopyError messages that respect the user. Specific, actionable, never condescending.
Customer Support
- Angry Customer Reply — De-escalateAcknowledge, explain, propose, follow up. Don't roll over.
Ops
- Meeting Notes → Action ItemsTurn messy notes into a clean owner+date action list.
- OKR Refactor — From Wishful to FalsifiableTake wishful OKRs and turn them into bets you can actually grade.
Legal
- SOC 2 Questionnaire — Vendor ReplyReply to a SIG Lite questionnaire using your SOC 2 report. Cite controls.
- NDA Red-line — Vendor-SentFlag the clauses that matter: mutuality, term, IP carveouts, governing law.
- Policy Doc — From First PrinciplesWrite a policy doc (e.g., remote work, AI usage) that's clear, lived, and won't gather dust.
Data
- Customer Churn DiagnosisGiven a cohort table, propose 3 falsifiable hypotheses with test queries.
- SQL → English ExplainerTranslate any SQL query into bullets that an analyst can act on.
- Experiment Design — A/B TestDesign an A/B test that's powered, falsifiable, and shippable. Hypothesis to readout.
Finance
- Cap Table Napkin MathRun dilution on a SAFE + Series A round. Pre, post, founder %, ESOP refresh.
Healthcare
- Patient Intake — SOAP NoteCompress a 20-min intake call into a structured clinical note a physician can scan in 60s.
Education
- Socratic Lesson PlanTeach a concept by asking, not telling. Five questions ordered by difficulty.
- Rubric Design — Creative WorkDesign a rubric for grading creative work that doesn't kill the creativity.
E-commerce
- Product Description — Job-to-Be-DoneSell without lying. Lead with the JTBD. Three specs. Risk reversal.
- Amazon Listing — Algorithm + BuyerWrite a listing that wins the algorithm AND the buyer. Keywords, bullets, A+ copy.
Real Estate
- Real Estate Listing — Sell the LifestyleSell the moment, not the square footage. 3 paragraphs.
Strategy
- Pre-Mortem — Imagine We FailedRun a pre-mortem on a decision. Imagine it's failed; trace back the most likely cause.
AI
- System Prompt — ArchitectBuild a system prompt for a custom agent that doesn't drift. Role, constraints, format.
- Prompt Debugging — SystematicDiagnose why a prompt is producing poor output and fix it.
Management
- Feedback — Radical CandorDeliver feedback that the recipient can hear AND act on. Specific, kind, future-focused.
Product
- Product Spec — Shippable v0.1Write a spec that fits on one page and ships in one sprint.
AI Agents & Autonomous Workflows
- Autonomous Agent System Prompt ArchitectDesigns a complete, production-grade system prompt for an autonomous agent including persona, tool contracts, …
- ReAct Loop Reasoning Trace DesignerBuilds a strict ReAct-style Thought/Action/Observation loop with explicit formatting and self-correction rules…
- Multi-Agent Orchestration BlueprintPlans a coordinated multi-agent team with roles, hand-off contracts, shared memory, and conflict resolution fo…
- Agent Tool Definition And Schema WriterWrites precise tool/function definitions with JSON schemas, descriptions, and usage hints that minimize wrong-…
- Self-Critique Verification Gate For Agent OutputAdds a rigorous self-review pass where the agent critiques its own draft action against a checklist before com…
- Goal Decomposition And Task Graph PlannerTurns a high-level goal into a dependency-ordered task graph with parallelizable branches, owners, and verifia…
- RAG Retrieval Agent Grounding ControllerDirects a retrieval-augmented agent to query, ground answers in sources, cite spans, and refuse when evidence …
- Agent Failure Recovery And Retry Policy DesignerDefines a structured error-handling policy covering retries, backoff, alternative tools, and graceful degradat…
- Human-In-The-Loop Approval Workflow SpecifierSpecifies where an autonomous agent must pause for human approval, what to present, and how to resume after a …
- Agent Memory Architecture And Summarization PolicyDesigns short-term, long-term, and episodic memory plus a summarization policy to keep an agent coherent acros…
- Browser Automation Agent Operating ProcedureDrives a web-browsing agent to navigate, extract, and act on pages reliably with verification and anti-halluci…
- Agent Evaluation Rubric And Trace GraderCreates an objective rubric and grades an agent execution trace on task success, tool use, efficiency, and saf…
- Agent Guardrail And Safety Constraint CompilerCompiles a layered guardrail set covering input validation, action allow-lists, output filtering, and prompt-i…
- Cron-Scheduled Autonomous Monitoring AgentSpecifies a recurring agent that monitors a signal, decides if action is warranted, and reports or escalates o…
- Agent Prompt-Injection Red Team GeneratorGenerates a structured battery of prompt-injection and jailbreak attacks to stress-test an agent before deploy…
- Cost And Token Budget Optimizer For Agent LoopsAnalyzes an agent workflow and proposes concrete changes to cut token cost and step count without losing task …
- Customer-Support Triage And Resolution AgentRuns an autonomous support agent that classifies tickets, resolves what it can, and escalates the rest with fu…
- Code-Writing Agent Plan-Then-Execute ProtocolGoverns a coding agent to explore, plan, implement in small verifiable steps, and self-test before declaring d…
- Research Agent Multi-Source Synthesis WorkflowRuns a research agent that fans out queries, cross-checks claims across sources, and synthesizes a cited, conf…
- Agent State Machine And Transition DesignerModels an agent's behavior as an explicit finite state machine with states, transitions, guards, and terminal …
- Tree-Of-Thoughts Strategy Explorer For AgentsHas an agent branch multiple solution strategies, evaluate each, prune weak branches, and commit to the strong…
- Data-Pipeline Orchestration Agent RunbookOperates an agent that runs a multi-stage data pipeline with validation gates, idempotency, and quarantine for…
- Agent Clarifying-Question Gate Before ActionForces an agent to detect underspecified requests and ask the minimum high-value questions before taking irrev…
- Sales-Outreach Agent Sequence OperatorRuns a personalized multi-step outreach agent that researches prospects, drafts touches, respects opt-outs, an…
- Agent Observation Logging And Reflection LoopAdds a structured reflection step where the agent reviews its own trajectory mid-run to catch drift and re-pla…
- Spec-To-Agent Requirements TranslatorConverts an informal product spec into a precise agent specification: capabilities, tools, constraints, metric…
- Workflow-To-Agent Automation Opportunity MapperAnalyzes a human workflow and identifies which steps to automate with an agent, which to keep manual, and the …
- Agent Output Contract And Structured-Response EnforcerDefines a strict machine-parseable output contract for an agent and a self-validation step that guarantees con…
- Long-Horizon Autonomous Project Agent CharterCharters an agent to own a multi-day project: milestones, daily standups, checkpoints, drift control, and a de…
RAG & Knowledge Retrieval
- Grounded Answer With Inline CitationsAnswers a user question strictly from retrieved passages, attaching an inline citation to every factual claim.
- Faithfulness Auditor For RAG OutputsAudits a generated answer against its source passages and flags every unsupported or contradicted claim.
- Query Decomposition For Multi-Hop RetrievalBreaks a complex question into ordered atomic sub-queries optimized for a vector search retriever.
- Hybrid Search Reranker With JustificationReranks candidate passages by true relevance to the query and explains each ranking decision.
- Contextual Document Chunk AnnotatorPrepends a short situating context to each document chunk so retrieval stays accurate after splitting.
- Insufficient-Context Refusal GuardDecides whether retrieved context is sufficient to answer and refuses gracefully when it is not.
- Conversational RAG With History RewriteRewrites a follow-up question into a standalone query using chat history, then answers from sources.
- Knowledge Conflict Resolver Across SourcesDetects and adjudicates contradictions across multiple retrieved sources using recency and authority.
- Citation-Verified Research SynthesisSynthesizes a multi-source literature answer where every claim maps to a verifiable quoted excerpt.
- Metadata Filter Builder For Vector StoresTranslates a natural-language query into structured metadata filters plus a semantic search string.
- HyDE Hypothetical Document GeneratorWrites a hypothetical ideal answer document to improve dense-retrieval recall for sparse queries.
- Support Knowledge-Base Answer BotAnswers customer support questions from help-center articles with steps, links, and escalation rules.
- Legal Clause Retrieval And ComparisonRetrieves and compares contract clauses against a standard, citing exact clause numbers and language.
- Retrieval Recall Gap DiagnoserDiagnoses why a RAG pipeline failed to retrieve the right passage and prescribes concrete fixes.
- Structured Extraction From Retrieved DocsExtracts a strict JSON record from retrieved documents with per-field source spans and null for unknowns.
- Few-Shot Grounded QA PatternUses worked examples to teach the model the exact grounded-answer and refusal behavior expected.
- Semantic Chunking Strategy PlannerRecommends an optimal chunking and metadata strategy for a corpus given its structure and query types.
- Self-Querying Retrieval Plan With CritiquePlans a retrieval, critiques its own plan for blind spots, then revises before any documents are fetched.