The question that cleaned up API error handling

Not magic wording, just enough context and a clear definition of done. Easy to adapt.

Engineeringclaude-opus-4.5#api-design

Talia Ibrahim

Help me make API failures observable and useful without leaking internal details.

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 API error handling, I would start with these checks:

Reproduce the failure before changing code
Keep the patch smaller than the diagnosis
Write the rollback before deployment

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

Talia Ibrahim

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

4 comments

Felix Silva@felixsilva·2mo ago
Tried the smaller-test idea on API error handling. It exposed the bad assumption pretty quickly.
- Julian Lin@julianlin·2mo ago
  Worth testing. I would still keep the source material beside the answer.
Mira Martin@miramartin·2mo ago
This is close to how I handle API error handling, especially the bit about marking unknowns.
Anika Brooks@anikabrooks·2w ago
I used a different model and the core workflow still held up.