GPT Models Prompt Guide


Table of Contents


1. Define the Role

Give GPT-5 a clear persona so it knows how to respond.

Example Prompt


2. Be Specific with Tasks

Use action verbs and constraints so GPT-5 knows what “done” looks like.

Example Prompt


3. Provide Context

Tell GPT-5 why the task matters and who it’s for.

Example Prompt


4. Specify the Format

Be clear about the shape of the answer you want.

Example Prompts


5. Calibrate Agentic Behavior

GPT-5 can act autonomously with tools. You decide how much initiative it should take.

Constrained Prompt

Expansive Prompt


6. Use Tool Preambles

Ask GPT-5 to show its plan before it acts. This makes it predictable.

Example Prompt


7. Optimize Coding Prompts

Break coding tasks into steps: plan → implement → test → refine.

Example Workflow

  1. First, outline the steps for solving this issue.

  2. Now, implement the code.

  3. Run test cases and explain if any fail.

  4. Refactor for readability and efficiency.


8. Control Instruction Following

Be explicit about rules, limits, and edge cases.

Example Prompts


9. Encourage Reflection

GPT-5 performs best when it pauses to think.

Example Prompt


10. Practical Prompt Templates by Use Case

General Task Prompt

Analyze a Dataset

Summarize Emails and Recommend Next Steps

Coding Workflow Prompt


11. Checklist Before Sending a Prompt

  • Did I assign GPT-5 a clear role?

  • Is the task verb-driven and specific?

  • Did I give context (audience, purpose)?

  • Is the format defined (bullets, JSON, table, code)?

  • Did I control behavior (constraints, stop conditions, tool use)?

  • Do I want GPT-5 to reflect before answering?


12. GPT 5.2 Tips

  1. Prevent scope drift aggressively: add explicit “EXACTLY and ONLY what the user requested” constraints; forbid extra features/styling/tokens (especially frontend/UX)

  2. Force summarization & re-grounding: GPT 5.2 benefits with this especially with long-context tasks to reduce errors and improves recall

  3. Calibrate file extraction:

    1. Provide a schema or JSON shape for the output

    2. Distinguish between required and optional fields

    3. Ask for “extraction completeness” and handle missing fields explicitly

    4. For multi-tables: Include a stable ID (filename, contract title, page range)

Last updated