#46Any LLMadvanced
Follow-Up Draft for Coding & Debugging
Use this coding & debugging prompt to create a follow up draft in any LLM, with role context, constraints, and a structured output you can adapt immediately.
You are an expert coding & debugging strategist. Help me create a follow up draft for [project / audience / offer]. Context: [describe the goal, audience, constraints, examples, and what has already been tried]. Output format: give me a concise recommendation, then a structured draft I can copy, then 3 improvement ideas. Keep it specific, practical, and avoid generic advice.
debuggingrefactoradvanced
Best use case
Use this prompt when you need a follow up draft for coding & debugging work and want the LLM to produce something structured instead of generic advice. It is strongest when you paste real context, examples, constraints, and the audience or workflow you are trying to support.
Expected output
A useful answer should include a concise recommendation, a ready-to-use draft or working structure, and practical improvement ideas. For Coding & Debugging, the best outputs usually touch debugging, refactor while staying specific to the pasted context.
How to customize it
- Replace the bracketed fields with the specific project, audience, offer, dataset, draft, source material, or decision you are working on. The more concrete the source material is, the more useful the output will be.
- Keep the role-setting sentence intact. It tells the model what kind of judgment to simulate before it starts drafting the follow up draft.
- Add any non-negotiable constraints before you run it, such as tone, length, format, compliance limits, brand voice, reading level, or what the answer must avoid.
Quality checks
- The answer names the audience, use case, and success criteria instead of staying abstract.
- The output is formatted so you can copy, edit, or hand it to the next workflow.
- The model avoids invented facts and calls out assumptions when source material is incomplete.
Customization passes
- Ask for a second pass that critiques the first answer against your constraints, then revises only the weak parts.
- If the output feels broad, add examples of what good and bad look like, then rerun the prompt with those examples labeled clearly.
- If the task is sensitive, require the model to separate facts from assumptions and mark anything that needs human review.
Related searches
Coding & Debugging AI promptsCoding & Debugging prompt templatescopy paste prompts for coding & debuggingfollow up draft prompt for any LLM