Humanity’s Last PRD
Latest drop: Haiku 5.5 · 8 Oct
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?

Task type v1.1 · 2 tasksLast changed 6 Oct 2026 · ChangelogDifficulty

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

From 16 graded outputs by 8 models. 63% were usable with at most a quick edit.

Reliably right

  1. Produces the required deliverable100% pass
    The output provides a complete loop, scorecard, and decision plan in the requested form, under 900 words, usable by Amara with light edits.
    GPT-6.1 Sol · API · A loop for the first growth PM
  2. 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
  3. Finds which rounds line up with performance100% pass
    It compares each round's scores with 12-month ratings, finding behavioral lines up and take-home, presentation, VP Engineering do not.
    GPT-6.1 Sol · API · What our interviews predict

Where it slips

  1. Avoids unsupported claims56% 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
  2. Identifies material uncertainty58% 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
  3. Defines good for this role first63% pass
    The memo does not explicitly name the competencies that matter most for this PM role and level, nor define what strong and weak look like before designing the interviews.
    Sonnet 5.5 · API · What our interviews predict

How it’s graded

Each check is built on how world-class product and growth leaders do this work, as they’ve described it on Lenny’s Podcast, and names the leader it comes from.

  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.

    Product and growth leadersOn Lenny’s Podcast

  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.

    Petra WilleLenny’s Podcast

  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.

    Product and growth leadersOn Lenny’s Podcast

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 compare up to three outputs, each with the LLM judge’s verdict on every check. Highlights mark what a PM had to fix.

The brief

You're helping Amara Osei, VP Product at Copperline, hire our first Growth PM (a senior role). She's shared her draft interview loop and asked you to redesign it. Write the loop you'd run (each round: who runs it, what it tests, how long it takes), the scorecard (what strong and weak look like for each thing we're testing), and how we'll make the decision at the end. No more than 900 words. What we know is below.

What the model was given6 items: About Copperline, The role, Amara's draft loop, The last two PM hires, From the recruiter, Who can interview
About CopperlineInvoicing and payments software for small accountancy firms. 60 people. Trial to paid conversion is 9%.
The roleOwns trial conversion and expansion revenue. Works with three engineers and a designer, reports to Amara, and has to ship experiments every week. Needs Sales and Marketing to change how they work, without managing them.
Amara's draft loop1. Recruiter screen. 2. Take-home: 'design a growth strategy for Copperline', a 10-page deck, five days to complete. 3. Presentation to a panel of six. 4. Culture fit with the CEO: 'would I grab a beer with them?' 5. Debrief: everyone discusses, then votes by show of hands. There's no scorecard.
The last two PM hiresOne left after five months: 'couldn't get Sales to change anything'. The other is doing well. Both sets of interview notes say mainly 'great presence' and 'very smart'.
From the recruiterOf the last 40 candidates given the take-home, 14 withdrew, saying they didn't have time. Nine of the 14 had young children or demanding current roles.
Who can interviewAmara, the Head of Engineering, a senior designer, the Head of Sales, a data analyst and the CEO. Each can give at most two hours to this hire. Amara wants an offer out within three weeks of the first interview.
What a strong answer doesThe answer key the graders mark against

A loop built on a scorecard written first: for a senior growth PM, experimentation and analytics, execution, and influence without authority (weighted up, since the last hire failed on it), with strong and weak signals for each. Rounds test the real job: a live diagnosis of Copperline's own trial funnel instead of a five-day generic deck (which loses candidates, mostly parents and people in demanding roles), a behavioural round on past experiments and metrics actually moved, and an influence round run by the Head of Sales. Replaces the 'grab a beer' culture fit with a structured values or collaboration conversation. Each interviewer writes their evaluation before the debrief, and the decision is made against the scorecard, not a show of hands. Fits each interviewer's two hours and the three-week target, and adds reference checks.

Critical failures (cap the score at 40)
  • Keeps a culture-fit test based on whether the interviewer would like a beer with the candidate
Task

Mid-level · v1.0

The outputs

8 setups answered this brief.

GPT-6.1 SolAPI96Usable with a quick editSonnet 5.5API92Usable with a quick editGPT-6 AstraChatGPT92Usable with a quick editOpus 5.5Claude88Usable with a quick editGPT-6 LunaAPI87Usable with a quick editHaiku 5.5API87Usable with a quick editGemini 3.8 FlashAPI85Usable with a quick editGemini 3.5 Flash-LiteGemini79Usable with a quick edit
Haiku 5.5API

Usable with a quick edit10 of 12 checks passed

The output is fully structured and actionable, needing only a one-sentence addition citing the recruiter's withdrawal data to complete the take-home justification.

Output

Redesigned Growth PM Interview Loop

Principles: Every round tests a named criterion. Scoring happens in writing before anyone discusses. Candidate time is capped. Interviewer time is capped at two hours each.

The loop (about three weeks)

Round 1: Recruiter screen (30 min) Runs: Recruiter Tests: Evidence of shipping experiments on a weekly cadence, compensation, logistics. Explain the full loop and its time cap up front so candidates can decide early. Knockout: No recent experience running experiments with a regular cadence.

Round 2: Analytical work sample (candidate time capped at 2 hours; due within 5 days, candidate picks when) Runs: Data Analyst scores; Amara reviews. Tests: Diagnosis and experiment rigour. Brief: An anonymised trial dataset showing the 9% conversion rate. Where is the funnel leaking, what would you test first, and what would you need from Sales and Engineering? Output: A two-page memo, not a deck. One diagnosis, three ranked experiments, and one fully specified (hypothesis, primary metric, guardrail metric, sample size, engineering effort). Alternative: A 60-minute live version on a shorter dataset, for candidates who can't spare two hours. Both versions are scored on the same rubric. Interviewer time: 45 min review.

Round 3: Build session (60 min, joint) Runs: Head of Engineering and senior designer. Tests: Engineering partnership and design judgment. Can the candidate cut their top experiment to something shippable this week? Do they know what needs instrumentation and feature flags, and what the design needs to look like? Interviewer time: 60 min each.

Round 4: Influence role-play (45 min) Runs: Head of Sales. Tests: Influence without authority, and understanding of sales incentives. Scenario: Sales wants to keep manual follow-ups for trial users. The candidate needs reps to run a three-week test that changes their routine. The Head of Sales plays a realistic, sceptical rep. Interviewer time: 45 min.

Round 5: Ownership and judgment (60 min) Runs: Amara. Tests: Ownership, learning from failure, decisions on incomplete data. Format: Structured behavioural questions. Ask for three past experiments: one that failed, one where they changed a team's behaviour without authority, one decision made on incomplete data. Probe what the candidate personally did, not what the team did. Interviewer time: 60 min.

Round 6: Working norms (30 min) Runs: CEO. Tests: Candour, comfort with pace and ambiguity. This replaces "would I grab a beer with them" with defined questions: - Tell me about disagreeing with a senior leader. What happened next? - A test you championed lost. What did you do? - What pace and level of ambiguity do you need to do your best work? Interviewer time: 30 min.

Final debrief (45 min): Amara and all interviewers, using written scores.

Timeline: Days 1–2 screen and brief issued. Days 2–6 work sample. Week 2: Rounds 3–5. Week 3: Round 6, debrief within 48 hours, offer.

Interviewer load: Data Analyst about 1h; Head of Engineering and senior designer 1h each; Head of Sales 45 min; Amara about 2h 15m (Round 5 plus review and debrief; she can reduce this by handing Round 2 review to the analyst, as above); CEO 30 min plus debrief.

Scorecard

Rate each criterion 1–4. Scores of 3 or 4 are "meets bar." Criteria marked ★ are must-haves.

CriterionStrong (3–4)Weak (1–2)
★ Experiment rigourNames a clear hypothesis, primary metric, guardrail, and sample size. Has run experiments weekly. Kills losing tests cleanly and says what they learned.Describes strategy but not tests. Can't say how many experiments they ran or what changed as a result.
Funnel diagnosisReads the data before proposing ideas. Questions the metric and names where the leak is and how they'd confirm it.Jumps to features or ideas without evidence. Takes the 9% at face value.
★ Influence without authorityGives a specific example of changing a team that didn't report to them. Uses the other team's incentives. Names trade-offs and what they gave up."I presented it and they agreed." Blames Sales or others for the outcome.
Engineering partnershipScopes changes small and instrumentable. Knows about flags and staged rollouts. Asks about capacity before proposing.Proposes large builds without checking cost. Treats engineering as a delivery queue.
Ownership and judgmentDescribes their own decisions and what they'd do differently. Makes calls on incomplete data and says how they'd know if wrong.Only success stories. Vague about personal role. Waits for certainty.
Working normsGives examples of disagreeing with a senior leader and following through. Comfortable with a small company's pace and ambiguity.Needs everything defined first. Avoids disagreement. Can't name a time they were wrong.

"Presence" and "very smart" are not criteria. Don't record them as evidence.

How we decide

  1. Score before discussing. Each interviewer submits scores and written evidence before the debrief. Nobody sees others' scores first.
  2. Apply the rules. Every must-have (★) needs a 3 or higher. Any 1 in any criterion is a no unless the panel explicitly discusses it. Don't average scores.
  3. Debrief on evidence. Go round the table. Each person states the evidence behind their score. Discuss in depth only where scores differ by two or more points. No show of hands.
  4. Amara decides. She writes a short rationale tied to the scorecard. The CEO must also score working norms at 3 or higher.
  5. If still split, run one 30-minute follow-up focused on the specific gap, then decide. Don't extend the loop.
  6. References. Ask referees for specific experiments the candidate ran and how they worked with Sales and Engineering.

Grades and run details

Decision model 88 · LLM judge 85
Decision model checks
  • passUses the supplied evidence correctly41%
  • passAddresses the actual decision85%
  • partialRespects explicit constraints46%
  • partialIdentifies material uncertainty51%
  • passAvoids unsupported claims37%
  • passProduces the required deliverable91%
  • passTests what the last hire failed at100%
  • passFixes the take-home's cost to candidates43%
  • partialFits the people and the time58%
  • passJudges on evidence, not presence100%
  • passDefines good for this role first85%
  • passKeeps each judgement independent100%
Run
Run
#1
API response time
32 s
Submitted
8 Oct 2026
GPT-6 AstraChatGPT

Usable with a quick edit11 of 12 checks passed

The output is complete and usable; the only missing piece is a brief mention of the recruiter's withdrawal data, which is a quick edit.

Output

Recommended loop

Replace the unpaid strategy deck, six-person presentation and “beer test” with structured evidence of doing this job. The previous hires’ notes cannot explain why one succeeded and one failed; cross-functional influence must be a hiring requirement, not a personality impression.

Rounds

RoundWho / durationWhat it tests and how
1. Structured screenRecruiter, 20 minutesConfirm scope, motivation, compensation and logistics. Ask for one conversion or expansion initiative: personal contribution, measured result and partner teams involved. Use consistent questions; accept relevant experience without requiring a Growth PM title. Advance at most two finalists under the interviewer-time budget.
2. Ownership deep diveAmara, 35 minutesExamine one growth initiative and one unsuccessful attempt to change another team’s behavior. Probe baseline, decision-making, individual contribution, results, uncertainty and lessons. Test senior ownership, growth judgment and influence through specific actions—not polished storytelling.
3. Live growth work sampleHead of Engineering + data analyst, 40 minutesGive everyone the same short, synthetic packet: a funnel beginning at Copperline’s 9% trial conversion, cohort/segment data, expansion opportunities, customer observations and delivery constraints. Allow eight minutes of quiet reading within the session. Ask candidates to diagnose, prioritize conversion versus expansion opportunities, and scope the first weekly experiment with three engineers and a designer. Introduce one standardized complication. Test analysis, prioritization, experimentation and delivery. No deck or advance work.
4. Cross-functional working sessionHead of Sales + senior designer, 35 minutesCandidate proposes a trial-conversion change. Sales resists because it changes incentives or workload; Design flags customer friction. Use identical opening objections, while responding naturally thereafter. Candidate must uncover interests, negotiate an achievable pilot and establish responsibilities and follow-through. Finish with reflection on what they would change. Test influence, customer judgment and collaboration—not whether they “win.”
5. Offer conversation—not another assessmentCEO, 20 minutes, selected candidate onlyExplain company direction, answer questions and help close. No informal culture-fit veto.

Allow candidate questions in each assessment round. Share the format, competencies and preparation expectations beforehand; offer scheduling flexibility, breaks and reasonable accommodations. Assess reasoning and decisions, not presentation polish. The work sample is fictional, not free consulting.

Scorecard

Use 1 = clear contrary evidence, 2 = below bar, 3 = meets senior-role bar, 4 = exceptional evidence. “Not observed” is separate from a low score and must be resolved before deciding.

Competency / primary evidence ownerStrong: meets or exceeds barWeak: below bar
Growth diagnosis and measurement / analystDefines conversion and expansion denominators, examines cohorts and segments, distinguishes correlation from causation, identifies missing evidence. Treats 9% as a starting point, not a diagnosis.Jumps to tactics; misreads funnels; claims causality from movement; ignores retention or expansion economics.
Experiment design and prioritization / analyst, AmaraChooses a defensible hypothesis, outcome and guardrails; weighs impact, effort and confidence; handles limited traffic and inconclusive results.Produces a tactic list; promises unsupported lifts; assumes every weekly release can deliver statistically conclusive results.
Weekly delivery with a small team / EngineeringSlices a useful first release, identifies instrumentation and dependencies, trades scope deliberately, and plans the next decision.Requires a major rebuild or more staff; ignores technical uncertainty; equates speed with skipping measurement or quality.
Influence without authority / SalesInvestigates incentives and constraints, makes a credible mutual-value case, secures specific commitments and establishes follow-through. Past examples show personal action and honest limits.Relies on title, escalation or charisma; blames Sales; mistakes agreement in a meeting for changed behavior.
Customer and commercial judgment / DesignConnects accountancy-firm workflows to conversion and expansion; protects trust and usability; considers downstream retention and revenue quality.Optimizes conversion through friction, pressure or misleading choices; ignores customer costs or churn.
Senior ownership and learning / AmaraSeparates own contribution from team results, owns misses, changes course with evidence and creates a repeatable operating rhythm.Offers vague achievements, cannot explain decisions, takes all credit or externalizes failures.

Interviewers record concrete actions, quotes and reasoning alongside scores. “Smart,” “great presence” and “likeable” are not evidence.

Decision, capacity and timeline

Week 1: recruiter screens and schedules two finalists. Week 2: complete assessments. Week 3: decide, close and issue the offer.

Reserve each assessor 10 minutes for calibration, five minutes per finalist for scoring, and 20 minutes for debrief. Including interviews, Engineering and the analyst each use exactly 120 minutes; Amara, Sales and Design each use 110. CEO uses at most 40 minutes. If neither finalist qualifies, reopen rather than lower the bar or silently exceed the budget.

Submit scores independently before seeing others’ notes. In debrief, review evidence competency by competency; Amara speaks last. No show-of-hands vote.

Require at least 3 on every competency, especially influence and weekly delivery. Resolve disagreements through recorded evidence, not averaging or seniority. Missing critical evidence means no offer yet. Amara owns the final decision and documents the rationale, remaining risks and onboarding support.

Grades and run details

Decision model 92 · LLM judge 92
Decision model checks
  • passUses the supplied evidence correctly54%
  • passAddresses the actual decision93%
  • passRespects explicit constraints23%
  • partialIdentifies material uncertainty51%
  • partialAvoids unsupported claims29%
  • passProduces the required deliverable91%
  • passTests what the last hire failed at100%
  • passFixes the take-home's cost to candidates80%
  • passFits the people and the time75%
  • passJudges on evidence, not presence100%
  • passDefines good for this role first95%
  • passKeeps each judgement independent100%
Run
Run
#1
Time to output
62 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 1

Identifies material uncertaintyWrongRight
Haiku 5.5 · API

It does not explicitly name specific unknowns that could change the hiring decision (e.g., true past influence on Sales) and how they would be resolved, even though reference checks and a split-decision follow-up are included.

GPT-6 Astra · ChatGPT

It names the condition that would change the decision (if neither finalist qualifies, reopen) and that missing critical evidence means no offer.

All mixed 1

Fixes the take-home's cost to candidatesMixedMixed
Haiku 5.5 · API

The output replaces the 5-day deck with a short exercise but never cites the recruiter's withdrawal data (14 withdrew, 9 had young children or demanding roles) to explain who it was driving away.

GPT-6 Astra · ChatGPT

The output replaces the take-home with a live exercise but never cites the recruiter's withdrawal data or who the take-home was driving away.

All got right 10

Uses the supplied evidence correctlyRightRight
Haiku 5.5 · API

The only factual claim about the current situation is the 9% conversion rate, which is directly supported by the brief; no other present-state facts are invented.

GPT-6 Astra · ChatGPT

The output uses the 9% conversion rate and the insufficient interview notes correctly, and invents no facts about the current situation.

Addresses the actual decisionRightRight
Haiku 5.5 · API

Output commits unambiguously to a fully redesigned interview loop, scorecard, and decision process, framed for Amara.

GPT-6 Astra · ChatGPT

The output commits to a specific redesigned loop and decision process, with Amara owning the final call and a clear condition to reopen if no candidate meets the bar.

Respects explicit constraintsRightRight
Haiku 5.5 · API

Output is under 900 words, removes the 5-day take-home and beer test, fits each interviewer within 2 hours (with a minor hand-off to stay under), and meets the 3-week target.

GPT-6 Astra · ChatGPT

The output is a loop, scorecard, and decision process within 900 words, addressed to Amara, and respects all stated constraints.

Avoids unsupported claimsRightRight
Haiku 5.5 · API

No interpretations, causes, or forecasts are presented as established facts; the role-play scenario is clearly labelled as a hypothetical.

GPT-6 Astra · ChatGPT

The only interpretation (notes can't explain outcomes) is directly supported by the brief; no other claims are presented as established fact.

Produces the required deliverableRightRight
Haiku 5.5 · API

The loop, scorecard with strong/weak signals, and decision process are present and complete, within the word limit, and usable by Amara.

GPT-6 Astra · ChatGPT

The output provides a complete loop, scorecard, and decision process that a PM could act on with light edits.

Tests what the last hire failed atRightRight
Haiku 5.5 · API

Round 4 (influence role-play with Head of Sales) and Round 5 (behavioral questions on changing team behavior without authority) directly test influence, with strong/weak signals on the scorecard.

GPT-6 Astra · ChatGPT

Round 4 is a cross-functional working session with the Head of Sales, and the scorecard includes 'Influence without authority' with strong/weak signals.

Fits the people and the timeRightRight
Haiku 5.5 · API

Each interviewer stays at or under 2 hours (Head of Sales 45 min + debrief 45 min, etc.), and the timeline fits within three weeks.

GPT-6 Astra · ChatGPT

Interviewer times are explicitly kept within two hours (Engineering and analyst 120 min, others 110 min, CEO 40 min) and the three-week schedule is detailed.

Judges on evidence, not presenceRightRight
Haiku 5.5 · API

Scorecard explicitly excludes 'presence' and 'smart' as criteria, demanding concrete evidence of experiments run, metrics moved, and influence gained.

GPT-6 Astra · ChatGPT

The scorecard demands concrete actions, quotes, and reasoning, and explicitly rejects 'smart', 'great presence', and 'likeable' as evidence.

Defines good for this role firstRightRight
Haiku 5.5 · API

The scorecard sets out the competencies weighted for this role (experiment rigour, influence, ownership) with distinct strong and weak signals before any round descriptions.

GPT-6 Astra · ChatGPT

The scorecard defines six competencies with strong and weak signals before any interview design, weighting influence and delivery for this role.

Keeps each judgement independentRightRight
Haiku 5.5 · API

Interviewers submit written scores before the debrief, nobody sees others' scores first, and the group discusses evidence only, preventing groupthink.

GPT-6 Astra · ChatGPT

Interviewers must submit scores independently before seeing others' notes, and Amara speaks last; no show-of-hands vote.

Results

Every setup we’ve tested on this task type, across all its tasks and repeats, graded on the current checklist. Calibrated.

#Model · HarnessTask scoreDecision modelLLM judgeRunsCritical failures
1GPT-6.1 SolAPI91.7100.02None
2Sonnet 5.5API91.792.32None
3GPT-6 AstraChatGPT93.880.82None
4Opus 5.5Claude87.580.82None
5GPT-6 LunaAPI89.676.92None
6Haiku 5.5API87.573.12None
7Gemini 3.8 FlashAPI75.065.42None
8Gemini 3.5 Flash-LiteGemini66.753.82None

What you get for the cost

No setup scores within 5 points of the leader at half its cost or less here, so the leader is also the best value.

Task score against relative cost for each setup. The table below has the same figures.50607080901001×3×10×30×Cost per output, relative to the cheapest setup (log scale) →↑ Task scoreGPT-6.1 Sol · API: task score 96, 10.0× the cheapestSonnet 5.5 · API: task score 92, 36× the cheapestGPT-6 Astra · ChatGPT: task score 86, 53× the cheapestOpus 5.5 · Claude: task score 83, 51× the cheapestGPT-6 Luna · API: task score 82, the cheapestHaiku 5.5 · API: task score 79, 1.7× the cheapestGemini 3.8 Flash · API: task score 69, 6.2× the cheapestGemini 3.5 Flash-Lite · Gemini: task score 60, 1.7× the cheapestGPT-6.1 Sol · APISonnet 5.5 · APIGPT-6 Astra · ChatGPTOpus 5.5 · ClaudeGPT-6 Luna · APIHaiku 5.5 · APIGemini 3.8 Flash · APIGemini 3.5 Flash-Lite · Gemini
Nobody beats these on both score and cost

Cost is each output’s tokens at the model’s list price, shown relative to the cheapest setup. Runs done in an app have no usage meter, so theirs are estimated from the same setup’s measured runs. How we compare cost

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