Reviews a client relationship or pitch that was won or lost: a dated timeline, expected against actual at each stage, the reason the client gave and what the evidence suggests, what to keep and what to change in BD, and three questions to ask the client. For a single lost search, use Lost Search Post-mortem.
Pipeline and ATScategory
No scriptsinstructions only, sends nothing
Any AI appupload, or copy and paste
Free, no signup
Upload the file to Claude, ChatGPT Business or Gemini Enterprise. On ChatGPT Plus, the free Gemini app or Grok, copy and paste it instead.
---
name: client-win-loss-review
description: Reviews a client relationship that was won or lost, or a pitch that went another way, to learn why at the account level: a dated timeline, what was expected against what happened, the real reason (from the client where possible), what to keep and what to change in BD, and questions to ask the client. Use when a recruiter or owner says "we lost the account", "they went with another agency", "why did we win", "win/loss", "client stopped sending roles", or "we lost the PSL".
license: MIT
metadata:
author: Work Insiders
version: "1.0"
pack: agency-growth-pack
---
# Client win/loss review
"They went another way" teaches nothing. You help a recruiter find out why a client was won or lost, so the next pitch and the next account plan improve. For a single lost search, use lost-search-post-mortem (Agency Desk Pack) instead; this is about the relationship or the pitch.
## Input
Whatever exists: the account history, placements, proposals and terms sent, emails, notes from calls, anything the client said about the decision.
## Step 1: timeline
Dated steps from first contact to the outcome: first call, proposal, terms, first job order, placements, problems, the decision. Mark gaps over three weeks.
## Step 2: expected versus actual
For each stage, what the recruiter expected to happen and what did. Where the two split is usually where the outcome was decided.
## Step 3: the reason
- **What the client said,** in their words, if anything.
- **What the evidence suggests,** marked as a guess to confirm.
- Check the usual causes: price, speed, candidate quality, communication, a relationship that was single-threaded, a new decision maker, an internal TA team, a competitor's relationship.
## Step 4: keep and change
- Two things to keep (for wins especially).
- Two to three changes, each tied to a skill or habit: "build a key client plan for any client over [n] placements a year", "ask for exclusivity on hard roles", "reconnect with the new HR leader within 30 days".
## Step 5: ask the client
Three short questions to send or ask, framed to learn, not to argue: what decided it, what we could have done differently, whether the door is open.
## Output
```
WIN/LOSS: [Client] | [won / lost / pitch lost] | [date]
Timeline: [ ]
Expected vs actual: [stage: expected / actual]
Reason: client said [ ] | evidence suggests [ ] (to confirm)
Keep: [ ] | Change: [ ]
Questions for the client: [ ]
```
## Rules
- Write about the process and the relationship, not people's character.
- Never guess the client's internal politics as fact. Mark it unknown.
- No blame. The point is the next account.
The agency profile it reads (fill this in so it uses your real details)
# Agency profile
Fill this in once. Every skill in the pack reads it, so every output comes out in your agency's voice with your real terms. Delete any line you do not want the AI to use. Leave a line blank rather than guessing.
## Who we are
- Agency name:
- Recruiter name and title (for sign-offs):
- Phone:
- Mailing address (needed for US commercial email):
- Years in business:
- Specialties (roles we fill):
- Markets (cities, regions or "US remote"):
- Industries we know best:
## Terms
- Direct hire fee basis (e.g. % of first-year base):
- Guarantee period and type (free replacement / pro-rata refund / credit; conditions, e.g. fee paid within terms):
- Contract markup or bill rate approach:
- Exclusive or retained options:
- Payment terms (e.g. net 30 from start date):
- Introduction period (how long a candidate we introduce stays ours):
- Contract-to-hire conversion fee:
- Concessions we allow, and their limits:
## Proof points we can share
- Placements, time to fill, or retention figures we are happy to quote:
- Client names we may mention (only with permission):
## How we work
- ATS:
- Do we text candidates? (yes/no):
- Name the client in first candidate messages? (yes/no):
- Blind profiles: always / new clients only / never:
- Include pay expectation in submittals? (yes/no):
- Job post apply instructions:
- EEO statement:
## Words we never use
-
Yes. It is part of the free Work Insiders Agency Growth Pack, MIT licensed, so you can edit and share it.
Does Client Win/Loss Review work in Gemini?
Yes. Upload it in Gemini Enterprise or drop the folder into Gemini CLI's skills folder. In the regular Gemini app, paste its instructions into a Gem.
Can I trust it with my data?
It has no scripts and sends nothing anywhere. Whatever you paste goes only to your AI assistant, under that assistant's own data terms, so remove candidate details you do not need first. It can still steer how the assistant answers, so read it before you use it.
Written by Work Insiders for agency recruiters. Fill in the agency profile before you use it so it never invents fees or proof points. How we make money.
