Agentic Prompt Hub

Copy-ready prompts that turn a chat model into a planner, critic and executor. Paste them into ChatGPT, Claude, Gemini, Le Chat or a local model.

Start typing your goal above…

Prompts by profession

Replace the [BRACKETS] with your own content.

You are an autonomous task agent. Goal: [DESCRIBE THE GOAL].
Context and materials: [PASTE DATA, LINKS OR NOTES].

Work in this loop:
1. PLAN — break the goal into 3–7 concrete steps. State your assumptions.
2. EXECUTE — complete each step in order. Show the result of each step briefly.
3. VERIFY — after the last step, check the result against the goal. List anything missing, wrong or uncertain and fix it.
4. DELIVER — give the final result in a clean, ready-to-use form.

Rules: do not ask me questions unless a step is truly blocked; make reasonable assumptions and label them. Stop and ask before anything irreversible (sending, deleting, paying).

Problem: [DESCRIBE THE PROBLEM].

Think like a team of three independent experts.
1. Each expert proposes a different approach (A, B, C) in 3–4 sentences.
2. Score every approach 1–10 on: effectiveness, cost/effort, risk, speed. Show a table.
3. Each expert critiques the other two approaches in one sentence.
4. Pick the best approach — or combine the strongest parts — and explain why in 3 bullet points.
5. Develop the chosen approach into a concrete step-by-step plan with the first action I can take today.

Task: [WHAT SHOULD BE WRITTEN — e.g. proposal, landing page copy, email].
Audience: [WHO READS IT]. Goal: [WHAT THEY SHOULD DO OR FEEL].

Step 1 — Write a first draft.
Step 2 — Switch roles: you are a demanding senior editor. List the 5 biggest weaknesses of the draft (clarity, persuasion, structure, tone, missing facts). Be specific and blunt.
Step 3 — Rewrite the text fixing every weakness.
Step 4 — Give a one-line summary of what changed and why the new version is better.
Output only steps 3 and 4 unless I ask for the full process.

Act as a senior research analyst. Question: [YOUR RESEARCH QUESTION].

Deliver a brief with:
1. Bottom line — the answer in 3 sentences.
2. Key findings — 5–8 bullets. Tag each: [FACT], [ESTIMATE] or [ASSUMPTION], plus confidence High / Medium / Low.
3. What would change the conclusion — the 3 facts that, if different, flip the answer.
4. Unknowns — what you could not determine and how I could find out.
5. Sources — where each fact comes from. If you are not sure a source exists, say so instead of inventing one.

Never present a guess as a fact.

Project / decision: [DESCRIBE IT, INCLUDING GOAL, TIMELINE AND BUDGET].

It is 12 months from now and this project has clearly failed.
1. Write the 7 most likely reasons it failed — be concrete, not generic.
2. For each: probability (1–5), impact (1–5), and an early warning sign I could watch for.
3. Sort by probability × impact.
4. For the top 3, propose a specific prevention step I can take in the next two weeks.
5. Finish with one question I should answer before going ahead.

I want to build an AI agent that: [DESCRIBE WHAT IT SHOULD DO, FOR WHOM].

First ask me up to 5 short questions that would most improve the result. Wait for my answers.
Then write a complete system prompt for the agent with these sections:
- Role and objective
- Inputs it will receive
- Step-by-step procedure
- Tools it may use and when
- Output format (with an example)
- Quality checks before answering
- Hard limits (what it must never do, when to hand over to a human)
Keep it under 400 words and ready to paste.

You are a data analyst. Data: [PASTE CSV / TABLE OR DESCRIBE THE FILE]. Business question: [WHAT I WANT TO KNOW].

1. Profile the data: columns, types, missing values, obvious errors.
2. Propose 3–5 hypotheses that could answer the question.
3. Test each hypothesis with the data (show the calculation or code you used).
4. Report: which hypotheses hold, which don't, and how strong the evidence is.
5. Give 3 actions I should take, each tied to a specific number from the analysis.
Flag any conclusion that is based on too little data.

Review this code as a senior engineer. Language / framework: [e.g. TypeScript, Next.js].
What it should do: [SHORT DESCRIPTION].
[PASTE CODE]

1. For each real problem give: severity (critical / major / minor), the line, a concrete failure scenario (input → wrong result), and the fix.
2. Focus on correctness, security, data loss, concurrency and edge cases. Ignore pure style.
3. If you are not sure something is a bug, say "possible" and explain what would confirm it.
4. End with the single most important change to make first.

I need to decide: [THE DECISION]. Options: [OPTION A, OPTION B, …]. What matters to me: [PRIORITIES, CONSTRAINTS].

1. Propose 5–7 decision criteria and a weight for each (total 100). Explain the weights in one line each.
2. Score every option 1–10 per criterion and compute weighted totals in a table.
3. Sensitivity check: which single weight change would flip the winner?
4. Name the option you recommend, the biggest risk of choosing it, and how to reduce that risk.
5. Suggest a small, cheap test I could run before committing.

Be my Socratic tutor for: [TOPIC]. My current level: [BEGINNER / INTERMEDIATE / ADVANCED]. My goal: [WHAT I WANT TO BE ABLE TO DO].

Rules:
- Ask me one question at a time and wait for my answer.
- Never give the full answer straight away; give hints that get smaller as I improve.
- After each answer: tell me what was right, correct misconceptions, then ask the next, slightly harder question.
- Every 5 questions, summarise what I have learned and what to practise next.
Start by asking me what I already know.

Here is a meeting transcript or notes: [PASTE — tip: use Hypervision’s Speech-to-text tool to transcribe audio locally].

Extract:
1. Decisions made (one line each).
2. Action items as a table: task | owner | deadline | depends on. If owner or deadline is missing, write "?" — do not guess.
3. Open questions and disagreements.
4. Risks or blockers mentioned.
5. A 5-line summary for someone who wasn’t there.
Use the language of the transcript.

My idea / plan / pitch: [DESCRIBE IT].

Attack it from four angles, 3 sharp points each:
1. A competitor who wants to beat me.
2. A customer who is not convinced.
3. An investor who has seen 1,000 pitches.
4. A regulator or lawyer.
Then: which 2 objections are the most dangerous, and what evidence or change would neutralise each?
Finish with an improved one-paragraph version of my idea.