Which prompt gives Copilot the most useful context?
Why D is the answer
Add retries with backoff to fetchUser, keeping its return type
A good prompt names the target, the change and the constraints. Longer wording that says nothing specific does not help.
In detail
- It names the function, the change and a constraint.
- That gives Copilot a clear, specific target.
- Name the function, the change and the constraint.
Use case
An illustrative scenario, not a real incident.
"Fix this" gets a guess. "Add retries with backoff to fetchUser, keeping its return type" gets what the developer wanted, the first time.
See it in different ways
flowchart LR A["Start general"] --> B["Add specifics"] B --> C["Give examples"] C --> D["Break up big tasks"] D --> E["Review and refine"]
mindmap
root((Prompting))
Examples
Zero-shot
One-shot
Few-shot
Structure
General, then specific
Small tasks
Target
Tests first
Context
New thread when stalemindmap
root(("Good prompt"))
n1["Target"]
n2["fetchUser"]
n3["Change"]
n4["Retries with backoff"]
n5["Constraint"]
n6["Same return type"]Key point: Specific prompts get specific results.
Why the other options are wrong
- A. Fix this
- "Fix this" gives no detail.
- B. Write better code than the code that is in this file right now
- "Better" has no definition.
- C. Make it work the way that it should work for all of the users
- "The way it should" says nothing specific.