Prepared for Handler · Executive search AI workflows

Candidate-to-role fit analysis, rebuilt as a repeatable AI workflow and tested for real

One of the use cases from your brief, worked end to end. Same search, same candidates, run the way most teams prompt today and then through a structured workflow your consultants can reuse on every assignment. Every AI output on this page is a real model run. Wording is as it came back; I only trimmed length and swapped dashes for commas.

Sample role and candidates are fictionalNo real candidate data usedRuns made 2 October 2026
36real model runs behind this page
5unsupported claims in one typical single-prompt answer
5 of 5identical scorecards for Candidate A once scores were anchored
3 of 3slips caught by the separate check step

Before and after: Candidate A

Left: the actual answer to one prompt, "Analyze this candidate's fit for the role below. Give a fit score out of 10 and a recommendation." Right: the same inputs through the workflow. Both came from the same model on the same day.

Single prompt · actual output, run 1 of 5 (excerpt)

Fit Score: 8.5/10

Exceptional PE Exit Readiness

Currently managing board reporting and sponsor communications at similar revenue scale. Proven ability to build QoE-ready financials and data room processes.

M&A Integration Track Record

Led 9 clinic acquisitions in 3 years, exceeds the 2-3/year planned integration pace.

CFO Title Gap

Currently VP Finance, not CFO, lacks formal P&L ownership and board-level reporting experience.

Recommendation: STRONG MOVE FORWARD

Why he works: This candidate has the rare combination of PE transaction DNA + healthcare operations chops. Many sponsors actually prefer finance leaders with this profile over career CFOs.

  • "Led 9 clinic acquisitions": the record says they led the finance integration of 9 acquisitions. A different, smaller claim.
  • "Data room processes", "sponsor communications": not in the record.
  • "Lacks board-level reporting": contradicts the record, which says they built the board reporting package.
  • "Why he works": the record gives no gender.
  • 8.5/10: stable across runs (8.0 to 8.5) but nobody can say where it comes from or defend it to a client.

Red = stated as fact but not supported by the record. Amber = hype or opinion with nothing behind it.

Workflow · actual output, after the check step (trimmed)

Candidate A, VP Finance, PE-backed Healthcare Services

Candidate A brings strong technical readiness for a healthcare CFO role. They built and own sponsor-grade board reporting and a 13-week cash model, demonstrating fluency with PE financial governance. They manage finance across a multi-state physical therapy network (~$140M revenue) and delivered a measurable revenue cycle improvement, reducing days in A/R from 58 to 41. They have led finance integration of 9 clinic acquisitions over 3 years and hold a CPA. On the exit front, they bring 6 years of sell-side transaction advisory experience at Big Four, providing diligence and QoE exposure from the advisor perspective.

Areas to explore

  • Has Candidate A led a company-side exit or buyer diligence process as a finance leader (beyond advisor-side experience)?
  • What is the scope of board interaction: do they present regularly to a board or board committee, or is their current role limited to sponsor reporting package delivery?
  • Is Candidate A willing to relocate to Atlanta? They are currently based in Charlotte, NC with no stated relocation intent.

Recommendation: Advance, pending answers on company-side exit experience and board governance scope.

What the check step fixed in this draft: the writer called Candidate A "Director of Finance". The checker compared it with the record and corrected it to VP Finance.

Every claim traces to a line in the record. Gaps are asked, not filled in. Weighted score 4.25 / 5, calculated by the template, not the model (see below).

How the workflow works

Most drift comes from asking one prompt to read, judge and write in a single pass. Splitting the jobs gives each step one task, a fixed format and clear rules. A final check, done by a separate prompt that did not write the draft, catches what slips through.

1

Extract the criteria

Turns the brief into weighted criteria with score anchors: what a 5, a 3 and a 1 look like. Agreed once per search, reused for every candidate.

2

Score against evidence

Picks the anchor that matches and quotes the exact line. No evidence means NOT EVIDENCED. The model never does the arithmetic.

3

Write in house style

Turns the scorecard into a client-ready summary with a fixed tone guide. Gaps become questions to probe.

✓

Check before it goes out

A separate checker compares the draft with the record. The template also checks each score against its anchor and does the weighting.

Criterion (Step 1)WeightScoreAnchor matched · evidence (Step 2, actual output)
PE exit readiness (QoE, data room, diligence)25%4 / 5Sell-side QoE from the advisor side. "Senior Manager, Big Four transaction advisory, 6 years (sell-side QoE)"
Sponsor / board-grade FP&A and reporting20%5 / 5Built and owns reporting used by a sponsor. "Built monthly board reporting package and 13-week cash model for sponsor"
Multi-site healthcare operations and revenue cycle20%5 / 5Multi-site with a measured result. "Owned revenue cycle turnaround: days in A/R from 58 to 41"
Add-on acquisition integration15%5 / 5Led 3 or more. "Led finance integration of 9 clinic acquisitions over 3 years"
Prior CFO / reports to a board10%2 / 5NOT EVIDENCED. Prepares board materials. "Built monthly board reporting package…"
Template check: model wrote 3, but its own note matched anchor 2. Corrected to 2.
CPA5%5 / 5"CPA (Georgia)"
Atlanta based or will relocate5%1 / 5Lives elsewhere, relocation not confirmed. "Based in Charlotte, NC"
4.25 / 5 weighted by the templateAdvance to first interview

What testing showed

I didn't want to show you a workflow that only looks good once. So I ran each version several times on the same inputs and kept every result. Here are the numbers that came back.

Single prompt

Steady score, shaky facts

Candidate A fit score, 5 runs
8.58.58.08.58.5
Candidate B, 5 runs
6.56.56.56.56.5

The number barely moves, which is the trap: it looks reliable. But it has no criteria or weights behind it, and the text around it made five unsupported claims in run 1 alone.

3 steps, first version

Better, with two leaks

"Prior CFO" score for A, 5 runs
23224
Model's own weighted maths, 10 runs
wrongwrongwrongwrongrightwrongwrongwrongwrongwrong

Judgment criteria drifted between 2 and 4, and the model got its own weighted total wrong in 9 of 10 runs, typically by 0.1 to 0.2.

3 steps + anchors + check

Same answer every time

Candidate A scorecard, 5 runs
samesamesamesamesame
Candidate B scorecard, 5 runs
samesamesame1 shiftsame

Anchors for each score and moving the arithmetic into the template made A identical across all 5 runs. B moved one nice-to-have criterion by one point in one run. The check step caught all 3 facts the writer slipped in.

How this was run: one mainstream AI model through its API at default creativity settings, 2 October 2026. 36 runs in total. Single prompt and scoring were run 5 times each per candidate, plus the summaries, the checks and the content post. Fictional inputs only. The prompts are plain text, written to work in ChatGPT, Claude or Copilot. Your own runs will vary a little, which is why the workflow measures consistency instead of assuming it.

Content development from the same brief

The same discipline works for content. Here, a search announcement for LinkedIn, written from the brief with a fixed tone guide, then put through the same check.

Actual output, after the check
We're recruiting a Chief Financial Officer for a Southeast-based outpatient healthcare group headquartered in Atlanta. The company operates ~$180M in revenue across multiple sites and is backed by private equity. This role is right for you if you have: Healthcare operations expertise. You understand payer mix, revenue cycle management, and the financial rhythms of multi-site clinical delivery. PE exit experience. You understand sale preparation, quality of earnings, data room readiness, buyer diligence, and you know what sponsors need from their finance leader. Acquisition integration skills. The company plans 2 to 3 add-ons annually, and you've done this before. The CFO will build FP&A and board reporting to sponsor standards, lead the finance function through a planned exit in 3 to 4 years, and report to the board. Prior CFO or senior finance leader role required. CPA preferred. Atlanta-based or willing to relocate. Message me directly or reply here. #Healthcare #CFO
What the check caught
  • "You've led a company through sale preparation": the brief lists leading an exit as a responsibility of this role, not a past requirement. Reworded.
  • "report directly to the board": the brief doesn't say "directly". Softened.

The client stays confidential (sector, size, region and ownership only), there are no hype words, and the post adds no requirements beyond the brief. A consultant still gives it a final read before posting, and that is built into the workflow.

Prompt library

The exact prompts behind this page, for the use cases in your brief. Paste into ChatGPT, Claude or Copilot and fill in the brackets. In a full engagement these get tuned to Handler's house style and saved as a shared library for the team.

You are a research analyst at a retained executive search firm.

TASK: Turn the role brief below into a scoring rubric. Do not evaluate any candidate.

RULES
- List 5 to 8 criteria. Each must be something a candidate's record can show or not show.
- Mark each as MUST-HAVE or NICE-TO-HAVE.
- Assign weights that add up to 100%. Must-haves carry most of the weight.
- For each criterion, write SCORE ANCHORS: one line each for what a 5, a 4, a 3, a 2 and a 1 look like, in terms of evidence a record could contain.
- Use only what is in the brief. If something important is unclear, list it under OPEN QUESTIONS FOR THE CLIENT instead of assuming.

OUTPUT FORMAT (table)
Criterion | Must/Nice | Weight | Score anchors (5 / 4 / 3 / 2 / 1)
Then: OPEN QUESTIONS FOR THE CLIENT (bullets)

ROLE BRIEF:
[paste brief]

Why this holds up: each prompt has one job, a fixed output format and an explicit "do not invent" rule. Scores are tied to anchors, the arithmetic lives in the template, and a separate check reads every draft before a client does.

What a full engagement looks like

Built around the deliverables in your brief: improved prompts, reusable templates, output-quality guidance, documentation and team training.

Week 1

Audit your current prompting

Review the prompts and outputs your team uses today across search launch, candidate profiles, content and fit analysis. Run them the way this page does, so we can see where drift and inaccuracy come from.

Week 2

Build the library

Workflows and templates for each use case, tuned to Handler's tone and formats, with score anchors, a scoring template that does the maths, an output-quality checklist and short documentation.

Week 3

Train the team

Working sessions with your consultants on live searches, then a refinement pass based on what they find in real use.