Onboarding skeptics to AI-assisted workflows
A strong engineer joins your team from a shop that banned AI assistants entirely. Your team is AI-heavy: agents draft most boilerplate, and the unwritten norms are "verify before merge, keep the spec in the PR, don't let the agent touch the auth boundary." The new hire is skeptical and a little resentful — they feel it's "cheating" and worry their skills will atrophy. How do you onboard them to the workflow so they're productive without becoming a rubber-stamp, and address the skill-atrophy concern honestly?
check_ai_pr_norms(agent_generated: bool, touches_auth: bool, has_spec: bool, verified_before_merge: bool, review_minutes: int) → list[str][true,true,false,false,30]out["auth-boundary","spec-in-pr","verify-before-merge"][true,false,true,true,40]out[][true,false,true,true,2]out["rubber-stamp"]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.
Vibe & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.