Free to read · no account needed

9 min · research

Interview or meeting prep brief

Goal: Generate interview questions and story prompts from *your* notes—no invented metrics; gaps go on a verify list.

Best for: Job interviews, sales calls, office hours with a professor, partner meetings.

AI can structure prep. It cannot live your career. Paste your own bullets. Ban invented metrics. For job search, pair with the career honesty guides: never let the model fabricate experience.

Why beginners skip this

Letting the model invent a full cheat sheet feels ready—the first company-fact question exposes invented numbers.

Step 1 — Prep brief prompt

Fill the brief from a real JD / about page; mark any model-invented company fact as unverified.

Role/meeting: [ ]
My goal for the conversation: [ ]
Build a prep brief:
- 8 questions to ask them
- 5 story prompts mapped ONLY to MY bullets (I paste below)
- Numbers / facts I must verify before I say them (do not invent)
- 3 red flags to watch for
Do not write a script for me to read verbatim.
My bullets:
[paste]

Step 2 — CSM interview example

Example

Filled prompt

Role: CSM interview at a ~50-person B2B SaaS
Goal: Learn territory scope; show retention habits without inventing metrics
My bullets:
- Owned 40 accounts in APAC chat support escalation
- Ran monthly QBR using customer-provided dashboards
- Reduced reopen rate on my queue after a checklist change (I will look up exact % tonight)
No invented company metrics. 8 questions + 5 story prompts from bullets only.

What good output looks like

  • Questions are specific to CSM work
  • Stories point at your bullets, not fictional wins
  • Verify list includes the reopen-rate %
  • No fake “I grew NRR 12%” line

Step 3 — Night-before verify pass

Night-before: open only the verify list; numbers come from your own docs—delete any story you cannot defend.

Example

Filled prompt

Interview with Head of CS.
Primaries only: careers page, latest blog, LinkedIn org.
5 questions + Unknowns. Ban chat-only "facts."

What good output looks like

  • Claim pack lists sources for “Walk in with questions, story prompts from *your* ”
  • Primary tab opened before share
  • Unknowns labeled; no vibe citations
  • Pass/fail: one primary URL saved

Unverified company facts

Mark model-invented company claims Unverified until careers/about pages confirm.

Keep it real

Run this guide’s Practice now on work you will actually ship this week—not a fictional scenario. Dated notes beat perfect theory.

Ship the practice

Close the tab only after Practice now is done on a real artifact.

Do not bookmark-only

Finish Practice now, then tick this guide on your path. Titles unread are not skills.

Close the loop

Write one line: next time a brief enters the room without source tiers, I refuse it.

One more pass

Re-read your Save-this-card line. If it is vague, rewrite it until a stranger could apply it.

Example

Filled prompt

Interview Thu with VP Eng.
Primaries: engineering blog, open roles page, latest 10-K snippet if public.
5 questions + Unknowns. Ban chat-only "culture" claims.

What good output looks like

  • Primary tab opened before share
  • Unknowns labeled; no vibe citations
  • Pass/fail: one primary URL saved
  • Claim pack lists sources for “Walk in with questions, story prompts from *your* ”

Red flag

Model-invented scripts; unverified numbers unmarked—throw away or mark before the call.

Save this card

Card: Walk in with your questions and unverified numbers marked—throw away model-invented scripts. Keep this beside the tool; read before you start.

Wear-test: show your Save card to a teammate for thirty seconds—if they cannot restate the refuse line, tighten the card tonight and date it (Asia/Shanghai).

Before you start

Open a blank claim pack. One claim about “Interview or meeting prep brief” plus a slot for a primary URL. Chat citations are not enough. Guide: research-interview-prep-brief. Keep the real job visible the whole time; a blank box means stop and fetch the artifact first.

How to use this week

This week add a source tier beside every claim on a real interview brief; mark unverified [unverified]; delete invented numbers.

Close the week by quoting aloud the refuse line you actually used once. If you cannot, rerun Practice now and date the pass/fail (Asia/Shanghai).

Pitfalls

PitfallFix
Asking AI to “write my success stories”Stories from your bullets only
Memorizing a full scriptQuestions + prompts, not a play
Invented employer metricsVerify list mandatory
Ignoring red flagsKeep the 3-watch list
Example

Filled prompt

Temptation: skip the habit for research-interview-prep-brief to save five minutes.
Job still: Walk in with questions, story prompts from
Smallest correct pass: Done visible · checkable artifact · Unknowns [?].
Boundaries: draft only; no silent send; no invented metrics.
Return: artifact + refuse-line said aloud.

What good output looks like

  • Names the shortcut refused (specific to research-interview-prep-brief)
  • Still delivers checkable output for “Interview or meeting prep brief”
  • Unknowns labeled; draft-only
  • Pass/fail: refuse-line dated (research-interview-prep-brief #4)

Field note: print or pin your question list with [UNVERIFIED] numbers highlighted. Walk in ready to say “I don’t have that figure” instead of improvising precision.

Practice now

Must-ask three: star the three questions you will definitely ask (Asia/Shanghai).

Interview-brief drill: three questions + evidence you want; one red-flag answer to avoid (Asia/Shanghai).

Thin-spot drill: rewrite the Save card with real nouns from your work (repo, doc, inbox). Generic placeholders fail the drill.

Tonight add a source tier beside every claim on a real interview brief; mark unverified [unverified].

Ship-check: artifact path ___ · refuse-line dated Asia/Shanghai ___ · never-do ___

One sentence takeaway

Source tier beside every claim; mark unverified [unverified].

Next

Resume without inventing · Claim–evidence matrix · Career path · Source tiers

← Back to home · Learn · Tools · Compare · Start