Tasks / Leadership

Hire a PM

Can the model design a hiring process that finds the right PM, and make the call on real candidates from the evidence?

Measures the modelTask type v1.1 · 3 tasksLast changed 6 Oct 2026 · ChangelogDifficulty

What AI gets right here, and what you’ll still have to catch

From 19 graded outputs by 7 models. 79% were usable with at most a quick edit.

Reliably right

  1. Produces the required deliverable100% pass
    Complete recommendation memo with evidence, risks, and actionable next steps, usable as is.
    GPT-6 Luna · API · Two finalists, one Group PM role
  2. Judges on evidence, not presence100% pass
    Judges on concrete evidence (metric moved, team credit, learning from failure) and treats impressions like presence as weak signals.
    GPT-6 Luna · API · Two finalists, one Group PM role
  3. Tests what the last hire failed at100% pass
    The loop includes an influence simulation with the Head of Sales and a scorecard dimension on influence without authority, directly testing what the last hire failed at.
    GPT-6.1 Sol · API · A loop for the first growth PM

Where it slips

  1. Spots the interviewer pattern65% pass
    Does not notice that VP Engineering scores big-tech candidates higher and those hires were rated lower; only reports a negative correlation without the pattern.
    GPT-6 Luna · API · What our interviews predict
  2. Avoids unsupported claims70% pass
    The claim 'A growth PM in a senior role is likely to be exactly that kind of person' is presented as fact without evidence and is not labelled as an assumption.
    Opus 5.5 · Claude · A loop for the first growth PM
  3. Identifies material uncertainty72% pass
    The output does not name unknowns that could change the hiring decision or the loop design, nor does it say how they would be resolved.
    Sonnet 5.5 · API · A loop for the first growth PM

How it’s graded

The checks come from what the best product leaders have said about doing this job well on Lenny’s Podcast. Each one names the guest it comes from: follow a name to the idea on the Lenny’s Podcast wiki.

  1. Judges on evidence, not presence

    Does the output judge candidates, or design the process to judge them, on specific evidence of results they drove and how they worked with their team, rather than impressions such as presence, confidence or polish?

    Passes when Asks for or weighs concrete evidence: the metric a candidate moved, the part they played, how they shared credit, what they learned from a failure. Impressions are treated as weak signals.

  2. Defines good for this role first

    Does the output set out what good looks like for this specific role (the competencies that matter most at this level, and what strong and weak look like) before judging candidates or designing interviews?

    Passes when Names the competencies weighted for this role and level, with strong and weak signals, and the judgement or the process follows from them.

  3. Keeps each judgement independent

    Does the output keep each interviewer's judgement independent (written down before the group discusses it), and guard against the loudest voice or the first speaker deciding?

    Passes when Requires or relies on written, independent evaluations before discussion, and discounts views that changed under group pressure.

Plus our standard checks

Uses the supplied evidence correctly · Addresses the actual decision · Respects explicit constraints · Identifies material uncertainty · Avoids unsupported claims · Produces the required deliverable · and 3 written for each task, which you’ll see in the tasks below.

The tasks

Read the brief, then put up to three outputs side by side, each with the LLM judge’s verdict on every check. Highlights mark what a PM had to fix.

The brief

You're Director of Product at Medvia, and you're the hiring manager for a Group PM. The debrief was yesterday. Write your recommendation to Rosa Lindqvist, our VP Product, in no more than 1,000 words: who to hire (Dev, Joy, or neither), the evidence for it, the risks, and what you'd check before making the offer. The CEO wants a decision by Friday. The interview notes and everything else are below.

What the model was given6 items: The role and the scorecard (agreed before interviews began), Dev Malhotra: interview notes, Joy Adeyemi: interview notes, Scores (1 to 4, entered after the debrief discussion), References, Compensation
The role and the scorecard (agreed before interviews began)Group PM for patient payments, leading three PMs. Must set the strategy for patient payments, lift the online payment rate (now 41%), and lead PMs while working closely with Finance and Compliance. Weighting: execution and influence 35%, product sense 25%, analytics 20%, people leadership 20%.
Dev Malhotra: interview notesProduct sense (Head of Design): 'Brilliant. Redesigned our statement flow live, lots of ideas, very creative.' Notes show six feature ideas in the first five minutes, before asking who pays and why. Analytics (Data lead): 'Strong.' Notes: asked what metric he moved at his last job, he said 'we grew the payments platform massively'; pressed, 'the team shipped 40+ features'. No number. Leadership (VP Engineering): 'Confident, inspiring.' Notes: every story in the first person; said his last PM team 'struggled to keep up with me'. Presentation: 'the best deck we've ever seen'.
Joy Adeyemi: interview notesProduct sense (Head of Design): 'Solid, slower.' Notes: spent 15 minutes asking who pays and why they don't pay online, then proposed one change: text-to-pay for the 58% of patients who pay by phone, with its trade-offs. Analytics (Data lead): notes say she raised payment completion at her last company from 33% to 47% over 18 months, and walked through an experiment that failed and what it taught her. Leadership (VP Engineering): notes say she coached a struggling PM into a different role, promoted another, and named her engineers when describing wins. Debrief comments: 'Not much presence.' 'Not sure she'd command the room with the CFO.'
Scores (1 to 4, entered after the debrief discussion)Dev: 4, 4, 4, 4. Joy: 3, 3, 3, 3. The Head of Design spoke first in the debrief. The VP Engineering's own notebook, written before the debrief, says: 'Joy: 4, strongest leader we've seen.' They entered a 3 after the discussion.
ReferencesDev: two references, both people who report to him now. Rosa knows someone at his previous company, who says: 'great in front of execs; his team turned over a lot.' Joy: her former manager and a peer, both strongly positive. Nobody has asked either reference about working with a CFO.
CompensationBand $220k to $250k. Dev is asking for $245k, Joy for $230k.
What a strong answer doesThe answer key the graders mark against

Recommends Joy, or at minimum not Dev on this evidence. Weighs both against the agreed scorecard rather than presence or the deck: Joy gives a metric she moved (33% to 47%), learns from failure, credits her team and coaches PMs, which fits execution, analytics and people leadership; Dev couldn't name a metric he moved, frames everything as 'I', jumped to features before asking about users, and the back channel reports high team turnover, all red flags. Points out that the scores were entered after a discussion the Head of Design opened, and the VP Engineering moved Joy from 4 to 3, so they show anchoring, not independent judgement. Treats 'presence with the CFO' as the one real open question and proposes a targeted reference check on how Joy worked with Finance leaders before the offer. Suggests the next loop collect written scores before the debrief.

Critical failures (cap the score at 40)
  • Recommends hiring Dev on the strength of the debrief scores or the presentation, without addressing that he couldn't name a metric he moved
Task

Staff-level · v1.0 · synthetic · healthcare, fintech, hiring, staff-level

The outputs

7 setups answered this brief. Pick up to three to read side by side.

Usable with a quick edit10 of 12 checks passed

The output is well-structured and evidence-based; a quick edit to add the condition that would change the call (e.g., 'if the reference reveals she struggled with finance, we will not proceed') would make it fully complete.

Output

MEMORANDUM

TO: Rosa Lindqvist, VP of Product FROM: Director of Product, Medvia DATE: October 24, 2023 SUBJECT: Hiring Recommendation: Group PM, Patient Payments

*

Rosa,

Following yesterday’s debrief, I have reviewed the scorecards, interview transcripts, and reference notes for our open Group PM role. We are tasked with finding a leader who can set strategy, lift our online payment rate from its current 41%, lead a team of three PMs, and collaborate effectively with Finance and Compliance in a regulated healthcare environment.

The CEO needs our decision by Friday. My recommendation is that we extend an offer to Joy Adeyemi at $230k. We should not hire Dev Malhotra.

Below is the evidence, the associated risks, and the pre-offer checks required to secure Joy.

---

1. The Evidence: Why Joy Adeyemi over Dev Malhotra

While the final entered scores (Dev straight 4s; Joy straight 3s) suggest a clear winner, the raw interview notes and hidden dynamics of our debrief tell a different story.

  • Product Sense & Problem Solving: Dev is a classic "feature factory" ideator. The Head of Design noted Dev pitched six features in five minutes before asking who pays and why. Conversely, Joy spent her first 15 minutes investigating the root causes of friction—asking who pays and why others don’t—before proposing a targeted, high-leverage solution: text-to-pay tailored to the 58% of patients currently paying via phone. For a critical metric like our 41% online payment rate, we need clinical execution, not a scattershot feature list.
  • Analytics & Rigor: The Data Lead’s notes on Dev are a red flag. When pressed on metrics, Dev offered vague marketing speak ("grew massively," "shipped 40+ features") with zero data attribution. Joy provided hard, demonstrable impact: she raised payment completion at her previous company from 33% to 47% over 18 months. Crucially, she also walked through a failed experiment and extracted lessons—proving she understands the complex trade-offs of healthcare payments.
  • People Leadership & Culture: Dev speaks entirely in the first person ("I," "my wins") and casually remarked that his last team "struggled to keep up with me." Rosa, you likely noted your contact’s warning that his team suffered high turnover. Joy is the inverse: she coaches struggling reports, promotes talent, and attributes wins directly to her engineers. The VP of Engineering’s pre-debrief notebook literally rated Joy as a "4, strongest leader we've seen," before social pressure in the debrief caused the scores to normalize.
  • The "Presence" Bias: The primary knock on Joy during the debrief was a lack of "presence" and a concern about whether she could "command the room with the CFO." This is a subjective trap. We do not need a charismatic showman to present slide decks; we need a strategist who can build bulletproof business cases with Finance and navigate Compliance. Joy’s methodical, customer-first approach is precisely what Finance will trust.

---

2. Risks to Manage

  • The CFO/Executive Presence Risk: Because the interview panel worried Joy might be quiet in front of executive stakeholders, we must validate her ability to defend her strategy to our CFO and Compliance leads.
  • Compensation and Closing: Joy is asking for $230k (right in the middle of our $220k–$250k band), making her a financially sound hire. However, because she is measured and thoughtful, she may take a few days to deliberate. We need to move decisively.

---

3. Pre-Offer Checks (To Be Completed by Thursday EOD)

Before we release the offer to Joy, I will execute two final validation steps:

  1. Backchannel/Targeted Reference Check: Since our previous reference calls did not explicitly probe her dynamic with Finance or Compliance, I will spend 10 minutes with her former manager specifically asking: “How did Joy handle budget cross-examinations with Finance? How did she partner with Legal/Compliance when building payment flows?”
  2. The "CFO Alignment" Test: I’d like to spend 30 minutes with Joy and our current Director of Finance (or you and I) presenting a mock 10-minute briefing on our 41% online payment bottleneck, asking her to walk us through how she would construct the business case for the Q1 roadmap.

Conclusion

Dev is dazzling in a pitch meeting, but his metrics are hollow, his leadership style is toxic to retention, and his instinct is to build before understanding. Joy is rigorous, customer-obsessed, metrics-driven, and a multiplier for her team and cross-functional partners.

Let’s trust the substance over the theater. I am ready to initiate the final check and prepare the $230k offer for Friday morning.

Grades and run details

Decision model 92 · LLM judge 11 of 13 checks
Decision model checks
  • passUses the supplied evidence correctly26%
  • passAddresses the actual decision76%
  • passRespects explicit constraints60%
  • passIdentifies material uncertainty78%
  • partialAvoids unsupported claims56%
  • passProduces the required deliverable98%
  • passWeighs against the agreed scorecard94%
  • passCatches the red flags in Dev's evidence100%
  • passSays what would change the call48%
  • passJudges on evidence, not presence98%
  • partialDefines good for this role first18%
  • passKeeps each judgement independent68%
Run
Run
#1
Time to output
6 s
Submitted
5 Oct 2026

Usable with a quick edit12 of 12 checks passed

The output is well-structured, evidence-based, and actionable with only minor wording tweaks needed; no re-checking of evidence or redoing of reasoning is required.

Output

To: Rosa Lindqvist, VP Product Subject: Group PM, Patient Payments — recommend Joy, subject to targeted checks by Friday

Rosa,

I recommend hiring Joy Adeyemi, contingent on validating her ability to set strategy and influence Finance and Compliance. The interview evidence is stronger for Joy on the work this role requires: improving payment outcomes, making customer-grounded product decisions, and developing PMs. Dev’s presentation strength is clear, but the evidence does not support his uniformly exceptional scores.

We should complete focused checks before Friday rather than let either the debrief’s consensus or the deadline substitute for evidence.

Why Joy

Our agreed scorecard—not presentation polish—should drive the decision.

DimensionWeightEvidence and assessment
------:---
Execution and influence35%Joy described raising payment completion from 33% to 47% over 18 months: a concrete outcome, with an example of learning from a failed experiment. Dev described platform growth without quantifying it, then cited 40+ features shipped—output, not demonstrated impact. Neither candidate has established CFO or Compliance influence. This remains the most consequential gap.
Product sense25%Joy investigated who pays and why patients do not pay online before proposing text-to-pay for the reported 58% who pay by phone, including trade-offs. That is stronger evidence of problem selection and prioritization than six ideas before understanding the payer. Dev demonstrated creativity, but creativity alone does not establish strategy.
Analytics20%Joy supplied a baseline, endpoint, timeframe, and failed-experiment learning. Dev supplied no outcome metric even when pressed. Joy’s result still needs verification of her contribution and how it was measured; her prior completion metric should not be assumed equivalent to our online payment rate.
People leadership20%Joy gave specific examples of coaching, promotion, and shared credit. Dev’s first-person accounts and comment that his PMs “struggled to keep up with me” raise questions about his ability to develop three PMs. The report of turnover warrants investigation, not acceptance as fact.

Why I would not rely on the recorded scores

The 4s for Dev and 3s for Joy were entered after the discussion, so they are not independent assessments. The VP Engineering’s contemporaneous note—“Joy: 4, strongest leader we’ve seen”—conflicts with the submitted 3. Combined with the Head of Design speaking first and enthusiasm about Dev’s deck, this creates a credible risk of anchoring and presentation halo.

“Not much presence” and “command the room” are not sufficiently specific hiring criteria. We need evidence of gaining alignment, handling disagreement, and changing consequential decisions—not a proxy based on communication style. This does not prove bias or invalidate every judgment; it means the scores need reconciliation with observed behavior.

I would ask each interviewer to independently reassess their dimension against the original rubric, cite evidence, and explain any change from their pre-debrief assessment. I would not manufacture replacement scores from these notes.

Risks in hiring Joy

  • Executive and cross-functional influence is unproven. Strong product judgment will not be enough if she cannot resolve disagreements with Finance and Compliance.
  • Group-level strategy remains under-tested. One well-reasoned product proposal does not establish an ability to set a portfolio strategy or allocate work across three PMs.
  • Her reported impact needs attribution. We need to understand what she owned, what other changes contributed, and whether the gains were durable.

Dev’s executive presentation skill is a genuine strength. However, selecting him now would require overlooking gaps in measurable outcomes and substantial unanswered leadership questions. His current direct-report references offer a limited perspective; the informal turnover report is also insufficiently substantiated.

Checks before an offer

1. Focused, structured working session with Finance and Compliance. Ask Joy to outline a patient-payments strategy from our 41% online payment baseline, identify missing data, prioritize opportunities, and explain how she would organize three PMs. Introduce a realistic conflict involving collections, patient experience, cost, and compliance constraints. Assess decision quality, listening, trade-off handling, and ability to reach a workable decision—not performance style. A CFO or senior Finance delegate and Compliance partner should score independently before discussing.

2. Targeted reference follow-ups, with Joy’s consent. Ask her former manager and peer for concrete examples of disagreement with a CFO or Finance leader, work with Compliance, strategy ownership, and developing PMs. Verify the 33%–47% result, her contribution, and measurement. Seek an additional relevant cross-functional reference if those references lack direct visibility.

3. Reconcile the interview record. Complete the independent score review and explicitly resolve the leadership-score discrepancy. Document remaining uncertainty rather than forcing consensus.

Friday decision: If these checks substantiate Joy’s strategy and influence capabilities, proceed with her offer. If they reveal a material gap—or cannot establish the essential evidence—I recommend neither, not defaulting to Dev.

Joy’s $230k request and Dev’s $245k request are both within the $220k–$250k band. Compensation should not decide this choice; set Joy’s offer based on scope and internal equity, not simply her lower ask.

Grades and run details

Decision model 100 · LLM judge 13 of 13 checks
Decision model checks
  • passUses the supplied evidence correctly88%
  • passAddresses the actual decision98%
  • passRespects explicit constraints55%
  • passIdentifies material uncertainty100%
  • passAvoids unsupported claims72%
  • passProduces the required deliverable94%
  • passWeighs against the agreed scorecard100%
  • passCatches the red flags in Dev's evidence100%
  • passSays what would change the call100%
  • passJudges on evidence, not presence100%
  • passDefines good for this role first81%
  • passKeeps each judgement independent88%
Run
Run
#1
Time to output
36 s
Submitted
5 Oct 2026

Usable with a quick edit12 of 12 checks passed

The output is well-structured, evidence-based, and actionable; a PM could use it with minor wording edits without re-checking evidence or redoing reasoning.

Output

To: Rosa Lindqvist, VP Product Subject: Group PM recommendation — Joy Adeyemi

Recommendation: Hire Joy, subject to focused reference and influence checks before the offer. She has the stronger evidence against the role’s core needs: measurable payment outcomes, thoughtful product judgment, and the ability to lead through other people. The CEO needs a decision by Friday; I would not let the debrief scores alone drive it.

Evidence

  • Execution and influence (35%): Joy gave a specific result from her last company—payment completion rose from 33% to 47% over 18 months—and explained a failed experiment and what she learned. Her leadership examples showed investment in others: coaching a struggling PM into a different role and promoting another. Dev’s evidence was less concrete: he described platform growth and 40+ shipped features but supplied no outcome metric when pressed. His stories were consistently framed around his own contribution, and he said his team struggled to keep up with him.
  • Product sense (25%): Joy investigated who pays and why before proposing text-to-pay for the 58% who currently pay by phone, including trade-offs. That is relevant to our 41% online payment rate and reflects problem-first judgment. Dev’s creativity and presentation were strengths, but six ideas in the first five minutes—before clarifying who pays and why—are a concern for this role.
  • Analytics (20%): Joy’s quantified result and discussion of a failed experiment are stronger evidence of analytical ownership. Dev did not provide a measurable result.
  • People leadership (20%): Joy’s examples demonstrate coaching, development, and shared credit. Dev’s confidence and presentation are positives, but they do not offset the limited evidence of developing a team or his comment about the team struggling to keep up.

Risks and scorecard

Joy’s main risk is whether she can influence senior stakeholders, particularly the CFO and Finance. The “not much presence” and “command the room” comments are concerns to test, not proof that she cannot do it; we should assess her ability to make a clear, evidence-based case rather than equate influence with a particular presentation style.

Dev may be compelling with executives, but we need to understand the team-turnover signal and whether his leadership style scales. His two references are current direct reports, which may limit candor. His former-company reference’s report of high turnover is important but unverified.

I would treat the 4/4/4/4 versus 3/3/3/3 ratings as weak evidence. The VP Engineering’s pre-debrief note called Joy the strongest leader seen and rated her a 4, then the score became a 3 after discussion; the Head of Design also spoke first. This does not establish why the ratings changed, but it is reason to rely on the underlying evidence and check for independent calibration.

Before making the offer

  1. Ask Joy’s former manager and peer specifically about her influence with Finance/CFO-level stakeholders, including a difficult disagreement and the outcome.
  2. Ask for one additional Joy reference who can speak to cross-functional execution; ask Dev’s references about team turnover, feedback, and how he develops PMs. Seek candid, comparable evidence where possible.
  3. In a short structured conversation, ask Joy to make the case for a payment-rate strategy to a skeptical CFO. Evaluate clarity, use of evidence, and handling of challenge—not polish alone.
  4. Confirm Joy’s 33%→47% result, her role in it, and the scope of her people leadership.

If those checks reveal a material gap in Joy’s influence or ownership, I would choose neither rather than default to Dev on presentation strength. Otherwise, proceed with Joy at her requested $230k, within band.

Grades and run details

Decision model 100 · LLM judge 13 of 13 checks
Decision model checks
  • passUses the supplied evidence correctly87%
  • passAddresses the actual decision100%
  • passRespects explicit constraints76%
  • passIdentifies material uncertainty100%
  • passAvoids unsupported claims60%
  • passProduces the required deliverable99%
  • passWeighs against the agreed scorecard100%
  • passCatches the red flags in Dev's evidence100%
  • passSays what would change the call100%
  • passJudges on evidence, not presence100%
  • passDefines good for this role first69%
  • passKeeps each judgement independent87%
Run
Run
#1
API response time
12 s
Submitted
5 Oct 2026

Check by check

Where the outputs differ comes first. Open a check to read the judge’s reasons. “Mixed” means the two graders disagreed.

Where they differ 2

Says what would change the callMixedRightRight
Gemini 3.5 Flash-Lite · Gemini

It names the CFO influence open question and proposes a targeted reference check and mock briefing, but does not state what answer or result from those checks would change the hiring decision.

GPT-6 Astra · ChatGPT

It identifies Joy's unproven influence with senior finance leaders as the open question and proposes a targeted reference check and a working session with Finance and Compliance, with a clear decision trigger.

GPT-6 Luna · API

Identifies Joy's influence with CFO as the open question and proposes specific reference checks and a structured conversation to test it.

Defines good for this role firstWrongRightRight
Gemini 3.5 Flash-Lite · Gemini

It does not explicitly set out the weighted competencies and what strong and weak look like for this role before judging the candidates.

GPT-6 Astra · ChatGPT

It sets out the weighted competencies for the role and describes strong and weak signals for each before judging the candidates.

GPT-6 Luna · API

Sets out the weighted competencies and what strong evidence looks like before comparing candidates.

All got right 10

Uses the supplied evidence correctlyRightRightRight
Gemini 3.5 Flash-Lite · Gemini

Every claim about the current situation is directly supported by the supplied context, with no invented facts.

GPT-6 Astra · ChatGPT

All factual claims about the current situation are taken directly from the supplied context without invention.

GPT-6 Luna · API

All factual claims about the current situation are directly from the brief, with no inventions.

Addresses the actual decisionRightRightRight
Gemini 3.5 Flash-Lite · Gemini

The output unambiguously recommends hiring Joy and not Dev, framed for Rosa, and implies the offer is contingent on the pre-offer checks resolving the CFO concern.

GPT-6 Astra · ChatGPT

The output commits to hiring Joy contingent on checks, and says it would recommend neither if checks reveal a material gap, giving a clear conditional answer.

GPT-6 Luna · API

Recommends hiring Joy early, framed for Rosa, and states that material gaps in influence or ownership would change the call to neither.

Respects explicit constraintsRightRightRight
Gemini 3.5 Flash-Lite · Gemini

The memo is addressed to Rosa, stays under 1,000 words, and includes the required elements: who to hire, evidence, risks, and pre-offer checks.

GPT-6 Astra · ChatGPT

The output is a recommendation to Rosa Lindqvist, well under 1,000 words, and respects the requested form and reader.

GPT-6 Luna · API

Memo to Rosa, under 1000 words, respects the Friday deadline by making a decision now with pre-offer checks.

Identifies material uncertaintyRightRightRight
Gemini 3.5 Flash-Lite · Gemini

It names the CFO presence concern as the key unknown, bounds it to the panel's impression, and proposes specific checks to resolve it.

GPT-6 Astra · ChatGPT

It names the unknowns (Joy's influence with Finance/Compliance, strategy scope, attribution) and specifies how to resolve them with a working session and reference checks, and what would change the call.

GPT-6 Luna · API

Names unknowns (Joy's CFO influence, Dev's turnover, debrief score reliability) and specifies how to resolve them with targeted checks.

Avoids unsupported claimsRightRightRight
Gemini 3.5 Flash-Lite · Gemini

Interpretations like 'feature factory' are clearly presented as conclusions drawn from the evidence, not as established facts.

GPT-6 Astra · ChatGPT

Interpretations like anchoring risk are clearly labelled as risks, and confident claims are backed by the evidence.

GPT-6 Luna · API

Interpretations are clearly labelled as risks or weak evidence, not presented as established facts.

Produces the required deliverableRightRightRight
Gemini 3.5 Flash-Lite · Gemini

The recommendation memo is complete, in the correct form, and could be acted on with light edits.

GPT-6 Astra · ChatGPT

The memo is complete with recommendation, evidence, risks, and pre-offer checks, and Rosa could act on it directly.

GPT-6 Luna · API

Complete recommendation memo with evidence, risks, and actionable next steps, usable as is.

Weighs against the agreed scorecardRightRightRight
Gemini 3.5 Flash-Lite · Gemini

The output evaluates candidates on product sense, analytics, and people leadership, and explicitly dismisses presence and the deck as not on the scorecard.

GPT-6 Astra · ChatGPT

The recommendation explicitly weighs both candidates against the agreed scorecard dimensions and weightings, and notes that presence and the deck are not on it.

GPT-6 Luna · API

Weighs both candidates against the agreed competencies (execution, product sense, analytics, people leadership) and notes that presence and deck are not on it.

Catches the red flags in Dev's evidenceRightRightRight
Gemini 3.5 Flash-Lite · Gemini

It catches Dev's missing metric, first-person credit and team struggle, jumping to features, and the back-channel turnover report—all four red flags.

GPT-6 Astra · ChatGPT

It names at least three red flags: no metric moved, first-person credit and team struggled to keep up, jumping to features, and the turnover report.

GPT-6 Luna · API

Names at least three red flags: no metric moved, first-person credit and team struggled to keep up, jumping to features, and back-channel turnover report.

Judges on evidence, not presenceRightRightRight
Gemini 3.5 Flash-Lite · Gemini

It judges on concrete evidence (metric moved, team credit, learning from failure) and treats presence as a weak, subjective signal.

GPT-6 Astra · ChatGPT

It judges on concrete evidence (metric moved, team credit, learning from failure) and treats impressions like presence as weak signals.

GPT-6 Luna · API

Judges on concrete evidence (metric moved, team credit, learning from failure) and treats impressions like presence as weak signals.

Keeps each judgement independentRightRightRight
Gemini 3.5 Flash-Lite · Gemini

It relies on the VP Engineering's independent pre-debrief rating and discounts the score that changed under group pressure.

GPT-6 Astra · ChatGPT

It requires written independent evaluations before discussion and discounts scores that changed under group pressure, citing the VP Engineering's notebook.

GPT-6 Luna · API

Relies on the VP Engineering's independent pre-debrief note and discounts group-influenced scores, keeping judgement independent.

Results

Every setup we’ve tested on this task type, across all its tasks and repeats, graded on the current checklist. Provisional The checklist is still being calibrated against our PM.

#Model · HarnessTask scoreDecision modelLLM judgeRunsCritical failures
1GPT-6.1 SolwithAPI94.4100.03None
2Sonnet 5.5withAPI95.896.22None
3Gemini 3.8 FlashwithAPI89.692.32None
4GPT-6 AstrawithChatGPT95.887.23None
5Opus 5.5withClaude91.787.23None
6GPT-6 LunawithAPI93.184.63None
7Gemini 3.5 Flash-LitewithGemini75.064.13None

About the task

The PM job

Hiring product managers.

Why it matters

A bad PM hire costs a team a year. Most loops reward polish and presence, and the debrief goes to whoever speaks first.

What good looks like

  • Defines what good looks like for this role before judging anyone
  • Judges on evidence of results and how they work with a team
  • Tests the real job, not a rehearsed framework
  • Keeps each interviewer's judgement independent

Deliberately not measured

  • Employment law
  • Compensation benchmarking
Capability tested

Hiring judgement

The failure we’re looking for

Hiring for presence and polish over evidence

Grading

Decision model and LLM judge, calibrated against a blind PM review