AgentClaude · jobseeker

Interview prep agent

Interview prep is research + anticipation. This agent workflow condenses public information about company and role into the 10 most likely questions, and scaffolds your answer for each using STAR logic.

Prompt

You are an interview coach. Prepare me for an interview.

Role & job ad: [paste]
Company (public info): [website excerpt, news, products]
Interviewer (if known): [role/background]
My 3–4 most relevant experiences: [bullets]

Task:
1. Derive the 10 most likely questions from ad + company context, grouped: technical, behavioral, motivation, critical probes (gaps, reasons for switching).
2. For the 5 most important, scaffold my answer: for technical, behavioral and critical questions as situation → task → action → result; for motivation questions a core statement with 1–2 proofs is enough instead of full STAR, each filled with MY experiences (invent nothing; mark gaps or missing examples as [PROOF MISSING]).
3. Suggest 3 smart questions back that show real interest in THIS company.

How to use this prompt

Open Claude (e.g. claude.ai or chatgpt.com) in a new chat.
Hit “Copy” above and paste the text in.
Replace every [square bracket] with your real details before you send.
Check the result. If it is too generic, just tell it what to change, e.g. “shorter, with one concrete number” or “give me variant 2 in my voice”.

The workflow around it

Collect the job ad + public company info
Fill the scaffolds with real details, resolve [PROOF MISSING] spots
Rehearse the 5 core answers aloud: scaffold, not script

Safety note

Uncritical. Two notes: use only public company info (no confidential documents in AI tools), and scaffolds stay scaffolds: memorised AI answers sound hollow in the room.

Hands-on tested with Claude · as of 2026-07