Refactoring tool selection
You have three AI options at hand: inline autocomplete (Copilot-style), a chat assistant you paste into, and an autonomous coding agent that can edit files and run commands across the repo. A task lands: 'rename the `User.fullName` field to `displayName` everywhere and update all call sites and tests.' Which tool fits, and why would the others be the wrong choice here?
Implement
select_ai_tool(file_count: int, is_mechanical: bool, has_test_oracle: bool, has_exact_refactor_tool: bool) → strExamples
in
[34,true,true,false]out"agent"in
[34,true,true,true]out"refactor-tool"in
[1,true,false,false]out"autocomplete"What a strong answer looks like
Treat the AI’s output as a draft to verify, not an answer to trust. Name the specific flaw and the input that triggers it, say how you’d catch it (tests, edge cases, reading critically), and how you’d re-prompt or decompose to get it right.
0:00 of about 15 min
Vibe & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.
Which questions mattered is sealed until you submit. Telling you now would just be handing over the edge cases.
Run or narrate your approach, then ask the coach.