Candidate & Employee Feedback Synthesis · Onboarding + Exit Signal
Synthesize candidate NPS, onboarding feedback, and exit interviews — 50 items — into an HR brief: hiring funnel leaks, onboarding friction, retention risk signals.
Pain addressed · HR feedback comes from scattered sources (candidate / new hire / exit). Each one alone reads as benign — only synthesis surfaces the systemic process issues.
Candidate & Employee Feedback Synthesis · Onboarding + Exit Signal
You're my HR feedback synthesis partner. Compress 90 days of candidate NPS + onboarding feedback + exit interviews — 50 items — into an HR brief.
# Raw feedback
{paste_feedback}
Tag: [source candidate/new-hire/exit][role family][summary][sentiment 1-5].
# Current HR KPIs
{hr_kpi} (time-to-hire / candidate NPS / 90-day churn / 12-month churn)
# Output five sections
## 1. Funnel leak (60 words)
Top 3 candidate drop-off points (apply → screen → interview → offer → onboard). Each with data + one direct quote.
## 2. Onboarding friction (60 words)
Top 3 pain points from new hires in their first 30/60/90 days:
- Friction + frequency + one direct quote
- One line: "this tells us our onboarding's step N is broken".
## 3. Retention risk (60 words)
Signals from exit interviews:
- Not individual reasons (those are outliers) — systemic signals (e.g. "manager relationship" appearing in 5+ exits).
- Signal + suggested retention action.
## 4. 1 systemic gap (80 words)
A theme appearing across ALL 3 sources (e.g. "role clarity" showing up in candidate + new-hire + exit feedback). This is the highest-leverage fix.
## 5. 3 actions + 1 explicit non-action (30 words each)
- One funnel action
- One onboarding action
- One retention action
- One explicit "don't do" (e.g. some candidates complain "process too long", but that's actually signal-positive — don't shorten)
# Boundaries
- Distinguish individual vs systemic signals — outliers don't drive conclusions.
- Quote in quotes, no paraphrasing.
- The "don't do" must be real — HR's hardest job is resisting public pressure.Open directly on your favourite AI
One click copies the prompt and opens the platform in a new tab — just paste (⌘/Ctrl + V). Recommended platforms are ordered by content fit.
Workflow · 5 steps
- 1
Pull 90 days of candidate NPS, onboarding surveys, and exit interviews into one block, tagged by source.
- 2
Run in Claude or DeepSeek R1. Fill the 2 placeholders.
- 3
The systemic-gap section is the highest-value output. If the model didn't surface one, push back: 'find a theme that appears in all three sources'.
- 4
Audit the 'don't do' item. If missing, ask the model explicitly to name one.
- 5
Send the brief to your People lead + CEO. Tackle the systemic gap first — highest ROI fix.
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.)
Why this prompt works
This prompt isn't a generic “write me a Customer Feedback Synthesis”. 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 Customer Feedback Synthesis, 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.
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