Chain-of-thought reasoning prompt

A system prompt template that pushes the model to show its reasoning before answering.

Higher accuracy on multi-step problems, debuggable when wrong.

AI / MLcotreasoning

The prompt

Copy this into ChatGPT, Claude, Gemini or any assistant you already use — then paste your own task underneath it.

Design a chain-of-thought system prompt for the described task. Include:

**Reasoning format** (numbered steps / scratchpad / structured)
**Stop conditions** (when to stop reasoning, when to answer)
**Self-check step** (re-read reasoning, look for inconsistencies)
**Final answer format**
**1 example** (user → reasoning → answer)

Rules:
- Don't expose chain-of-thought unless the use case is dev/eval.
- For prod, hide internal scratchpad from end user.

Or run it here

Task

0/8000

Output

Output will appear here after you click Run.

Or run in your favourite chatbot

Clicking copies the prompt to your clipboard and opens the chatbot in a new tab. Gemini doesn't accept URL params — paste manually with Ctrl/Cmd+V.

Fine-tune ground truth template

Builds a JSON template + 10 sample I/O pairs for a fine-tuning dataset.

Dataset annotation guideline

Writes annotation guidelines that two annotators can apply consistently.

Improve my prompt

Takes a vague prompt and rewrites it to be specific, structured, and reliable.

LLM eval rubric

Builds a structured eval rubric to grade LLM outputs for a specific task.

Model card draft

Drafts a model card with intended use, limitations, training data summary, evaluation results.

RAG retrieval prompt

Designs a system prompt that turns user questions into retrieval queries — multi-query, HyDE, etc.

Browse the full free AI prompt library or see more ai / ml prompts.