PromptDeck
HR & RecruitingMeeting Notes & Decision Sync#interview#STAR#red flag

Interview Debrief · STAR + Red Flag

Convert verbal interviewer feedback into STAR-structured assessment with Red Flag annotation.

Pain addressed · Pain #1: 'felt good', 'seemed smart' as interview feedback — and two weeks later the decision has no real basis. AI has to structure AND surface red flags.

Interview Debrief · STAR + Red Flag

Prompt·Advanced
Also available in 中文 →
You're an HRBP skilled at structuring interview feedback. Convert verbal/text interviewer feedback into STAR + Red Flag format.

# Candidate + role
- Candidate ID: {candidate_id}
- Position: {position}
- Round: {round}

# Interviewer
- Name + role: {interviewer_and_role}
- Duration: {duration}

# Raw feedback
{paste_raw_feedback}

## Block 1: One-line verdict
Rating: ✅ Recommend / 🤔 Borderline / ❌ No
- Must commit; no "let's see other panels"

## Block 2: STAR per case
For each of 2-4 cases:
- **Situation** / **Task** / **Action** / **Result** (quantified)
- **Interviewer score**: 1-5 with reasoning from their actual words
- **Suspicious point**: any "too clean" claim?

## Block 3: Red Flags (mandatory)
Identify 1-3 even if overall positive (or mark "none identified"):
- ⚠️ Flag (in interviewer's words/behaviors, no judgment)
- Charitable interpretation
- Need next-round validation? Y/N + how

## Block 4: JD alignment table
| JD key point | Interview evidence | Strong / Mid / Weak |

## Block 5: Process recommendation
- Continue? What to validate next?
- Need a special interviewer? (culture fit / specific skill)

# Rules
- No "all-round excellent" — everyone has trade-offs
- Don't import subjective words ("smart"/"nice") verbatim
- Don't avoid Red Flags, even soft ones
- ≤ 600 words
Saves ~40 min per use

Open directly on your favourite AI

One click copies the prompt and opens the platform in a new tab — just paste (⌘/Ctrl + V).

Workflow · 5 steps

  1. 1

    Capture the debrief within 2 hours of the interview. Past that, interviewer memory blurs.

  2. 2

    Aggregate raw feedback into one block — if it came verbally on Slack huddle, transcribe it before pasting.

  3. 3

    Fill in the 6 placeholders and run the prompt.

  4. 4

    Audit the Red Flag block twice. Models trend toward 'positive overall' — push back if it skipped flags you yourself noticed.

  5. 5

    Share the structured doc with all panelists and the hiring manager; tag the candidate ID for grep-ability. Never forward raw interviewer notes (privacy).

Verify before you ship

AI's "almost right" is the #1 pain. Tick these off so reviewers can't find the obvious holes. (Checkbox state stays local — we don't track it.)

Done 0 / 5 checks

Why this prompt works

This prompt isn't a generic “write me a Meeting Notes & Decision Sync”. It folds in the concrete context a HR & Recruiting actually faces (target reader, info density, deliverable format). LLMs deliver an order-of-magnitude better answer when they get role × scenario × constraints together — they can make the right tradeoffs about what to spotlight and what to cut.

When to use

Best moment: you know roughly that you need to do a Meeting Notes & Decision Sync, but you're stuck on “how do I even ask the AI?” Muscle memory has no template. Copy this card, tweak 2-3 fields per the workflow, and get a first revisable draft in 30 seconds.

Common pitfalls

  • Send without tweaking placeholders · the draft reads as default-GPT and your reviewer spots it in 3 seconds.
  • Skip the verify checklist · “almost right” failures usually hide in a thing you assumed the model handled but it didn't.
  • Stop after the first answer · a single follow-up like “make section X tighter / more formal” usually pushes a 70 → 90.

Variants & extensions

Want to use this card more aggressively? Three extensions:

  • Swap languages: both EN/ZH prompts ship in the card — use the EN version when shipping to a Western audience.
  • Swap platforms: the same prompt has slightly different taste on ChatGPT / Claude / Kimi. The recommended-platform pill marks the best fit.
  • Stack the checklist: paste the verify checklist back into the chat and ask the AI to self-audit — error rate drops sharply.
PromptDeck Pro Bundle

Want 25 more prompts like this one?

Get the full 50-card Pro deck — multi-step chains, vertical variants, lifetime updates.

  • 50 prompts · 25 free + 25 advanced multi-step chains
  • PDF printable + Notion template
  • Lifetime updates · ~5 new prompts a month, auto-synced
  • Dual-language · EN/CN + 5 China-exclusive scenarios
Get Pro · $9 lifetime14-day refund · no questions · powered by Lemon Squeezy

Related cards