Vetting unfamiliar dependencies
Your AI assistant, building a JavaScript date feature, generated `import { parseRelative } from 'date-helpers-lite'` and listed it in package.json. You don't recognize the package. What's your process for deciding whether to trust this dependency, and what are the two distinct things that could be wrong with an AI-added package?
Implement
vet_ai_added_dependency(name: str, exists_on_registry: bool, weekly_downloads: int, days_since_first_publish: int, has_source_repo: bool, popular_names: list[str]) → strExamples
in
["date-helpers-lite",false,0,0,false,["date-fns","dayjs","luxon"]]out"hallucinated"in
["date-fns",true,21000000,3400,true,["date-fns","dayjs","luxon"]]out"trusted"in
["date-fnss",true,40,3,false,["date-fns","dayjs","luxon"]]out"typosquat"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 12 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.