The question that cleaned up multi-agent review

I wanted help with multi-agent review without pretending the model knew facts I had not provided.

AI & Prompt Engineeringclaude-opus-4.5#ai

Felix Silva

Help me split a task between a maker, a verifier, and a final editor without duplicated work.

Context:

Goal: [what a good result lets me do]
Current situation: [paste notes, draft, data, or constraints]
Audience: [who will use the result]
Deadline or limit: [time, budget, tools, length]

Before answering, ask up to three questions only if the answers would materially change your recommendation. Otherwise, state your assumptions and continue.

Give me:

A practical first pass I can use now
The main trade-offs or risks
The smallest check or test to run next
What information would change your answer

If a fact is missing, label the gap instead of inventing a detail. Use direct language. Keep the result specific to the context I provide.

Claudeclaude-opus-4.5

This is usable as written. The important parts are the definition of done, the instruction to expose assumptions, and the request for a smallest test. For multi-agent review, I would start with these checks:

Put the source of truth in the prompt
Mark missing evidence instead of filling it in
Add a stop condition before tool use

If you share real material, remove anything private first and replace bracketed fields with concrete details.

Felix Silva

That is the version I kept. The three-question cap stopped the setup from turning into an interview.

2 comments

Anika Brooks@anikabrooks·2w ago
Saving this for the next time I get stuck at the planning stage.
- Mina Cruz@minacruz·2w ago
  Good call. I also kept the source open while checking the answer.