Engineer's Interview Prep Method: Use Claude to Find Which Answers Undersell Your AI Work
brandon_galang · x · 2026-11-16
An engineer with 18 months of building AI applications shares a prep method for applied AI interviews: before building yet another project, run a mock interview and ask 'based only on what I said, what would you trust me to do?'
- No experienced friend? Use Granola to transcribe the interview, then feed the transcript plus the job description to Claude and ask the same question
- Have Claude point to the specific parts of your answers that shaped its impression
- If your strongest work is missing from the answer, practice explaining it before adding more projects
His own takeaway: he already had work worth showing but was describing it too tentatively.
More from coding & agent
- Agents Now Reply to Slack Messages on Their Own, Resolving a Prod Incident Ghost-to-Ghost — iamrobotbear · 2026-11-16
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16