Tasks / Experiment

Find the growth loop

Can the model find a product's real growth loop, show whether it compounds, and say which lever to pull?

Measures the modelTask type v1.0 · 2 tasksLast changed 2 Oct 2026 · ChangelogDifficulty

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

From 14 graded outputs by 7 models. 33% were usable with at most a quick edit.

Reliably right

  1. Sees the cross-side effect100% pass
    It traces the chain from the tutor bounty to oversupply, thinner bookings, new profiles without reviews, and weaker ranking, and acts on it by pausing broad tutor referrals.
    GPT-6.1 Sol · API · Growing on the surface, decaying underneath
  2. Addresses the actual decision96% pass
    The memo commits early to putting both engineers on idea 4, names the primary loop and its compounding status, and specifies what results would change the call (kill thresholds, quarter-end loop gain).
    Sonnet 5.5 · API · The badge on every form
  3. Produces the required deliverable96% pass
    The memo answers all parts of the brief (primary loop, compounding, engineer allocation, success measurement) in a usable form for the Head of Growth.
    Sonnet 5.5 · API · The badge on every form

Where it slips

  1. The loop maths holds46% pass
    The memo does not give a plain verdict of 'decaying' for the content loop despite showing its decline, and it does not compute a numeric yield or coefficient for that loop.
    GPT-6.1 Sol · API · Growing on the surface, decaying underneath
  2. Uses the supplied evidence correctly57% pass
    The claim that the base settles at 10,700 creators is unsupported by the pack's arithmetic, and the claim that cost per sign-up usually rises with spend is not in the supplied evidence.
    Opus 5.5 · Claude · The badge on every form
  3. Avoids unsupported claims59% pass
    Presents the 10,700 equilibrium and the rising cost-per-sign-up claim as facts without labelling them as hypotheses or supporting them from the pack.
    Opus 5.5 · Claude · The badge on every form

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 a Staff PM at Tutorly. Our CEO, Rachel Dunn, wants to triple paid acquisition for the next two quarters so we reach 50,000 booking parents before the Series B. Before the planning offsite she's asked you for an honest view of how we actually grow. Write a memo of no more than 1,300 words for Rachel and the exec team that: 1. Maps our growth loops in a simple text diagram, says which is primary and why, and whether each is compounding, contributing or decaying, with the numbers. 2. Responds to the plan to triple paid acquisition. 3. Says where our three squads should go for the next two quarters, with the test, threshold and stop condition for each. The pack is below. Not all of it matters equally.

What the model was given8 items: About Tutorly, Twelve months, at the top line, Search and profiles, Where new booking parents come from, and how long they stay, Referral programmes, Paid acquisition, Rachel's note, Constraints
About TutorlyAn online tutoring marketplace: parents book one-to-one lessons with tutors. The average lesson costs $40 and we keep a fixed 18% commission. Each tutor has a public profile page, with reviews from parents.
Twelve months, at the top lineBooking parents (at least one booking a month): 31,000 → 37,000 (+20%). Active tutors: 14,200 → 23,000 (+62%). Organic search sessions to tutor profiles: +40%. Bookings per active tutor a month: 9.1 → 6.8.
Search and profilesProfiles with three or more reviews get 81% of organic profile sessions; profiles with none get 4%. Of tutor profiles created in the last six months, 61% had no booking within 60 days, so they have no reviews. Click-through from search results on our top 200 keywords fell from 6.1% to 5.0% since March, after changes to the results pages.
Where new booking parents come from, and how long they stayOrganic search: 52% of new booking parents; 48% still booking after six months; net lifetime value $260. Parent referrals: 9%; 51% after six months; net lifetime value $275. Paid search and social: 39%; 22% after six months; net lifetime value $120. Across all sources, net lifetime value averages $210.
Referral programmesParents: $20 of lesson credit for each referred parent who books. Each active parent sends 0.31 invites a month, and 14% of invites become booking parents. Tutors: $50 for each referred tutor who completes onboarding. 44% of new tutors last year came through tutor referrals.
Paid acquisitionAverage cost per new booking parent over the year: $95. Last quarter we raised spend from $60,000 to $90,000 a month, and the cost per new booking parent rose from $82 to $109.
Rachel's note“Our LTV to CAC is 2.2. Every dollar we don't put into paid is growth we're leaving on the table. Triple it to $270k a month and we hit 50,000 parents before the raise.”
ConstraintsReviews can only be left after a completed, paid lesson. Our policy, and consumer protection rules in our main markets, forbid paying or rewarding anyone for reviews. The commission stays at 18%. Three squads are available for the next two quarters; the raise is about six months away.
What a strong answer doesThe answer key the graders mark against

Maps four loops: content (profiles and reviews rank, parents book, bookings create reviews, profiles rank better), parent referral, tutor referral, and paid. Names content as primary: organic is the biggest source of new booking parents (52%) and among the stickiest (48% at six months, $260). Finds that it's decaying behind 40% session growth. Profiles grew 62% against 40% sessions, so sessions per profile fell about 14%. 61% of new profiles never get a booking, so they never get reviews, and profiles without reviews get 4% of sessions. Bookings per tutor fell from 9.1 to 6.8. Traces the cross-side cause: tutor supply growing about three times faster than demand (+62% against +20%), much of it from the $50 tutor-referral programme (44% of new tutors), which spreads bookings too thin for new tutors to earn the reviews the loop runs on. Treats the click-through drop (6.1% to 5.0%) as a separate, external hit. Sizes the parent referral loop at about 0.043 (0.31 × 14%): small but high quality. Answers Rachel with marginal cost: the extra $30,000 a month bought about 94 more parents (60,000 ÷ 82 ≈ 732 → 90,000 ÷ 109 ≈ 826), roughly $319 each, against $120 of value for a paid parent. The 2.2 ratio blends sources and uses the average cost, so tripling would burn cash on parents who mostly leave. Sends the squads to: getting new tutors their first booking and review (for example, routing demand in under-supplied subjects to new tutors, with a threshold such as the share of new profiles booked within 60 days rising from 39% to 55%); concentrating search value on reviewed profiles (keeping unreviewed profiles out of the index, and a fix for the click-through drop); and pausing or targeting the tutor-referral bounty while improving the parent loop. Each comes with a stop condition, and the memo is honest about what 50,000 parents by the raise would really take, without rewarding reviews.

Critical failures (cap the score at 40)
  • Proposes paying, crediting or otherwise rewarding parents or tutors for reviews
  • Treats the 40% growth in organic sessions as proof the content loop is healthy
Task

Staff-level · v1.0 · synthetic · marketplace, network effects, SEO, unit economics, staff-level

The outputs

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

Usable with a quick edit11 of 12 checks passed

The analysis is complete and evidence-based; a quick edit to clarify the content loop's decaying verdict would make it fully aligned, but the core reasoning is sound and actionable.

Output

To: Rachel Dunn and Executive Team From: Staff PM, Tutorly Subject: Grow booking demand, not acquisition spend Planning horizon: Next two quarters

Recommendation

Do not commit to $270,000/month in paid acquisition. Our primary growth engine is organic discovery of proven tutors, reinforced by completed lessons and reviews. That engine is growing, but its distribution is concentrated and its conversion into bookings is weakening. Meanwhile, tutor supply is growing much faster than demand, and paid acquisition has deteriorating marginal economics.

Put our three squads on organic discovery, demand-led tutor activation, and parent referrals. Keep paid acquisition as a tightly gated contributor—not the engine assumed to deliver 50,000 booking parents.

1. How we actually grow

```text PRIMARY: Organic discovery / reputation Search → tutor profile → booking → completed paid lesson → genuine review → stronger discovery/conversion → more bookings

Parent referrals Booking parent → invitation → new booking parent → invitations

Tutor referrals Active tutor → referred tutor → onboarding → additional supply → bookings only if matching parent demand exists

Paid acquisition / reinvestment Spend → new booking parent → repeat lessons → commission → acquisition budget → more spend ```

Organic/reputation: our primary compounding mechanism, but uneven and constrained. Organic supplies 52% of new booking parents, versus paid’s 39% and referrals’ 9%. These parents have 48% six-month retention and $260 net LTV. Completed lessons generate reviews, which can improve subsequent discovery and conversion without buying every next customer.

Profiles with at least three reviews capture 81% of organic profile sessions; unreviewed profiles capture only 4%. This supports the mechanism, but does not establish that reviews alone cause the traffic difference.

The warning signs are substantial:

  • Organic profile sessions rose 40%, but booking parents rose only 20%.
  • Search CTR fell from 6.1% to 5.0%, an 18% relative decline.
  • 61% of recently created profiles had no booking within 60 days—and therefore no reviews.

This is a reinforcing loop concentrated in established profiles, not proof that adding more profiles compounds demand.

Parent referrals: contributing, not yet demonstrably self-sustaining. Each active parent generates:

`0.31 invites/month × 14% conversion = 0.0434 new booking parents/month`

That is 4.34 new booking parents per 100 active parents per month. Even six fully active months produce only 0.26 referred booking parents per parent. We lack lifetime active-month data to calculate a full reproduction rate.

Referral customers are valuable: 51% six-month retention and $275 net LTV, with a $20 credit per successful referral. But the credit alone is not the fully loaded, incremental CAC.

Tutor referrals: contributing supply, with decaying demand yield. They produced 44% of new tutors, incentivized by $50 per onboarded tutor. Tutor count grew 62%, while bookings per active tutor fell 25%, from 9.1 to 6.8.

Multiplying those figures suggests monthly bookings increased roughly 21%—from 129,000 to 156,000—while supply expanded three times as quickly. Onboarding more tutors is not equivalent to growing the marketplace. We cannot establish that tutor referrals are self-compounding; their booking yield is deteriorating.

Paid: contributing customers, with decaying marginal economics. Paid delivers 39% of new booking parents, but only 22% remain booking after six months, and their net LTV is $120. Each $40 lesson yields $7.20 commission, before other costs. Reinvestment is possible only if acquisition leaves enough economic surplus; spend itself is not a compounding advantage.

2. Why tripling paid is not the current answer

The quoted 2.2 LTV:CAC divides blended LTV, $210, by paid CAC, $95. It combines different customer populations.

Paid’s actual ratios are:

  • Annual average: $120 / $95 = 1.26
  • Latest quarter: $120 / $109 = 1.10

That leaves only $25, then $11, of lifetime surplus per acquired parent on the supplied net-LTV basis.

The marginal picture is worse:

  • $60,000/month at $82 CAC bought approximately 732 parents.
  • $90,000/month at $109 CAC bought approximately 826 parents.
  • The extra $30,000 bought only 94 additional parents: approximately $319 per additional parent.

This before/after comparison is not a controlled incrementality estimate, but it is a strong warning against extrapolating average CAC.

Even if CAC stayed at $109, $270,000/month would acquire approximately 2,477 parents/month. Relative to current spend, that adds roughly 9,900 gross parents over six months, before churn—not the 13,000 net increase required to reach 50,000. Organic and referrals could close part of that gap, but the pack lacks monthly cohort flows needed to forecast it honestly.

Decision: Freeze paid at no more than $90,000/month during a four-week incrementality audit; reduce spend where marginal economics fail. Release additional budget in steps of at most 25%, not a single tripling. Require incremental CAC of $80 or less—a proposed 1.5× paid LTV:CAC hurdle—and no deterioration in cohort quality. Stop any expansion that fails that hurdle. These are management thresholds, not observed performance.

3. Three squads for two quarters

Squad 1 — Recover organic booking demand

Test: Diagnose the CTR decline, then test search-facing changes we control—titles, snippets, profile information and relevant landing experiences—using matched keyword/profile holdouts. Prioritize proven tutors with available capacity. Do not assume we can reverse external search-results changes.

Threshold: Within 8–10 weeks, achieve at least 10% lift in organic first-booking conversion per eligible search impression, with CTR trending toward 5.8% or better, and no deterioration in cancellations or early repeat booking versus control.

Stop condition: Stop variants that improve clicks without incremental bookings. If two adequately powered iterations fail, redirect from presentation fixes to intent and landing-page mismatch.

Quarter two: Scale winning changes; continue measuring completed lessons and cohort retention, not sessions alone.

Squad 2 — Activate supply where demand exists

Test: Pause broad tutor-referral expansion. In underserved subject/time/location segments, test availability guidance and matching that help new tutors earn their first paid, completed lesson. Randomize at market-cluster level to detect displacement from existing tutors.

Threshold: Reduce the 60-day no-booking rate from 61% to 50% or lower, while increasing total completed bookings in treated markets by at least 5%. Require non-negative incremental contribution after intervention costs.

Stop condition: Stop if new-tutor activation merely redistributes existing bookings or worsens cancellations and lesson quality.

Quarter two: Expand only in demonstrated demand gaps. Request honest reviews after completed lessons; never reward reviews or require positive feedback.

Squad 3 — Grow retained demand through parent referrals

Test: Keep the $20 referral credit unchanged. Test referral prompts after successful lessons and repeat bookings against randomized holdouts. Own the paid incrementality audit as the common acquisition-measurement workstream.

Threshold: Raise invitations from 0.31 to at least 0.45 per active parent/month, maintain 14% conversion, and demonstrate at least 25% lift in incremental referred booking parents, with fully loaded incremental CAC below $80 and early repeat booking no worse than control.

Stop condition: Stop prompts that cause annoyance, reduce repeat booking, or merely relabel parents who would have arrived organically. Do not scale on invitations alone.

Quarter two: Scale proven referral treatments; validate six-month retention as cohorts mature.

The offsite should approve these experiments and gates—not an unsupported acquisition forecast. Our objective is 50,000 booking parents, not 50,000 acquired accounts or an ever-larger tutor directory.

Grades and run details

Decision model 88 · LLM judge 12 of 13 checks
Decision model checks
  • passUses the supplied evidence correctly41%
  • passAddresses the actual decision98%
  • passRespects explicit constraints40%
  • passIdentifies material uncertainty97%
  • passAvoids unsupported claims34%
  • passProduces the required deliverable69%
  • passFinds the decay behind the growth44%
  • passSees the cross-side effect64%
  • passAnswers the CEO on paid100%
  • partialA closed loop, not a channel73%
  • partialThe loop maths holds42%
  • partialProposes tests that could fail54%
Run
Run
#1
API response time
84 s
Submitted
2 Oct 2026

Needs more than a quick edit8 of 12 checks passed

Key calculations (marginal cost, sessions per profile decline, loop yields) are missing, so a PM would need to redo that reasoning before using the memo.

Output

Memo

To: Rachel Dunn and Executive Team From: Staff PM Subject: How Tutorly grows—and where to invest before Series B

The growth loops

```text More completed lessons → more genuine reviews on tutor profiles → stronger search visibility and parent trust → more profile visits and bookings → more completed lessons [SEO/review loop]

Active parents → invites → referred parents book and become active → more invitations [parent-referral loop]

Tutors → refer tutors who complete onboarding → more tutor supply → more choice and capacity for bookings → tutors refer more tutors [tutor-supply loop] ```

Primary: the SEO/review loop. It brings 52% of new booking parents, organic profile sessions grew 40%, and organic-acquired parents have $260 net LTV and 48% six-month retention. Reviews are a durable marketplace asset: profiles with 3+ reviews receive 81% of organic profile sessions, versus 4% for profiles with none. This loop is compounding, but its conversion leg is weakening: search CTR on the top 200 keywords fell from 6.1% to 5.0%, and 61% of recent tutor profiles had no booking within 60 days—so they cannot earn reviews.

Parent referrals: contributing, not proven compounding. Referrals bring 9% of new parents; their $275 net LTV and 51% six-month retention are strong. But each active parent generates only 0.31 × 14% = 0.043 referred booking parents per active-parent month. For that alone to produce more than one direct referral per parent, average active life would need to exceed about 23 months. We do not have that evidence. Grow this channel, but do not call it self-sustaining yet.

Tutor referrals: contributing supply, while the supply loop is decaying in productivity. Tutor referrals account for 44% of new tutors, but active tutors grew 62% while booking parents grew only 20%; bookings per active tutor fell from 9.1 to 6.8, a 25% decline. The current risk is adding supply faster than demand and weakening tutor utilization—not a shortage of tutor sign-ups.

On tripling paid acquisition

I would not approve an unconditional increase from $90,000 to $270,000 per month. The stated 2.2 LTV:CAC ratio divides blended LTV ($210) by average CAC ($95). That mixes customers from channels with very different economics. Paid parents have $120 net LTV: that is 1.26× the $95 average paid CAC, and only 1.10× the $109 CAC observed after the latest spend increase. Spend rose 50% last quarter while CAC rose from $82 to $109. Those are poor grounds for assuming a threefold budget will deliver threefold growth.

At $270,000 and $109 CAC, we would acquire roughly 2,477 paid booking parents per month before churn. The 50,000 target requires 13,000 more monthly booking parents—about 2,167 net per month over six months, before accounting for losses. Paid-parent six-month retention is only 22%. We cannot responsibly claim the target is achievable from this spend without a cohort-based forecast; the simple gross-add math is not enough.

Keep paid at or below the current run rate while we test incrementality and economics. Scale only where a holdout shows genuinely incremental parents and the marginal CAC supports the channel’s LTV. More spend into a worsening auction is not automatically growth.

Squad priorities for the next two quarters

SquadTest and success thresholdStop condition
1. Search and profile discoveryA controlled search-results/profile experiment that improves qualified discovery without compromising relevance. Scale if organic bookings per eligible search session rise at least 15% and CTR recovers to at least 5.8%.Stop or redesign after 8 weeks if bookings per session improve by less than 5%, or if the CTR gain comes with worse booking quality.
2. Tutor activation and marketplace liquidityTest guided onboarding, availability setup, and matching for new tutors. Aim to reduce the share with no booking within 60 days from 61% to 45% or lower, and lift bookings per active tutor from 6.8 to at least 7.5.Stop the intervention if, after a mature 60-day cohort, the no-booking rate improves by fewer than 8 percentage points or parent experience worsens. Do not solve this by simply recruiting more tutors.
3. Efficient acquisition and referralsRun paid holdouts and a parent-referral activation test. Scale paid only if incremental CAC is at most $80 (a 1.5× ratio against paid LTV of $120). For referrals, test prompts and timing that lift invite-to-book conversion from 14% to at least 18%.Do not increase paid budgets if incremental CAC exceeds $80; pause placements above $100 or with no measured incremental lift. Stop the referral treatment if conversion fails to improve after a powered test.

No squad should reward or pay for reviews: reviews must follow completed paid lessons and remain voluntary. The near-term growth job is to turn existing tutor supply into booked lessons and genuine reviews, recover search conversion, and prove which acquisition dollars are incremental before committing to a larger bill.

Grades and run details

Decision model 79 · LLM judge 8 of 13 checks
Decision model checks
  • passUses the supplied evidence correctly54%
  • passAddresses the actual decision96%
  • passRespects explicit constraints63%
  • passIdentifies material uncertainty86%
  • partialAvoids unsupported claims34%
  • passProduces the required deliverable73%
  • passFinds the decay behind the growth40%
  • passSees the cross-side effect73%
  • partialAnswers the CEO on paid78%
  • partialA closed loop, not a channel60%
  • partialThe loop maths holds26%
  • partialProposes tests that could fail42%
Run
Run
#1
API response time
44 s
Submitted
2 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 3

Finds the decay behind the growthRightMixed
GPT-6.1 Sol · API

It shows the decline per profile, the 61% unbooked new profiles, and falling bookings per tutor, concluding the primary loop is constrained and uneven.

GPT-6 Luna · API

The memo does not show the decline in sessions per profile (about −14%), missing that specific piece of evidence for the content loop's decay.

Answers the CEO on paidRightWrong
GPT-6.1 Sol · API

It works out the marginal cost (~$319) against the paid parent's $120 value, explains the 2.2 ratio blends sources, and firmly says not to triple.

GPT-6 Luna · API

It does not work out the marginal cost from the spend and cost figures (about $319 for the last 94 parents); it only notes the CAC increase without computing the incremental cost per additional parent.

A closed loop, not a channelRightWrong
GPT-6.1 Sol · API

It names the organic/reputation loop as primary, grounds it in the highest-retention source (52%, 48% retention), and sizes it with the supplied numbers.

GPT-6 Luna · API

The memo names the SEO/review loop as primary but does not work out its yield or coefficient with retention applied.

All got wrong 1

The loop maths holdsWrongWrong
GPT-6.1 Sol · API

The memo does not give a plain verdict of 'decaying' for the content loop despite showing its decline, and it does not compute a numeric yield or coefficient for that loop.

GPT-6 Luna · API

Only the parent referral loop has a computed coefficient; the SEO and tutor referral loops lack yields or coefficients, and the verdicts are not fully supported by math.

All got right 8

Uses the supplied evidence correctlyRightRight
GPT-6.1 Sol · API

All factual claims about the current situation are taken directly from the supplied context or follow by arithmetic.

GPT-6 Luna · API

All statements about the current situation are directly supported by the supplied context or simple arithmetic.

Addresses the actual decisionRightRight
GPT-6.1 Sol · API

The memo commits early to not tripling paid, frames it for Rachel, and specifies the incrementality audit and thresholds that would change the call.

GPT-6 Luna · API

The memo commits clearly to not tripling paid unconditionally, gives a specific answer, and states what would change it (incrementality tests, CAC thresholds).

Respects explicit constraintsRightRight
GPT-6.1 Sol · API

The memo is under 1,300 words, respects the 18% commission, forbids rewarding reviews, and includes the requested sections.

GPT-6 Luna · API

The memo respects the word limit, addresses the CEO, and explicitly forbids paying for reviews; no constraint is violated.

Identifies material uncertaintyRightRight
GPT-6.1 Sol · API

It names missing data (lifetime active months, cohort flows, incrementality) and says how they would be resolved or change the decision.

GPT-6 Luna · API

It identifies the need for cohort-based forecasts and incrementality tests, naming the unknowns that could change the paid decision.

Avoids unsupported claimsRightRight
GPT-6.1 Sol · API

Interpretations and causes are labelled as such, and confident claims are backed by the evidence.

GPT-6 Luna · API

Interpretations like the loop weakening are presented as analysis based on the numbers, not as unsupported fact.

Produces the required deliverableRightRight
GPT-6.1 Sol · API

The memo is a complete, actionable document for the exec team with growth loops, paid analysis, and three squad plans with tests and stop conditions.

GPT-6 Luna · API

The memo is complete, within the word limit, addressed to the right audience, and actionable with light edits.

Sees the cross-side effectRightRight
GPT-6.1 Sol · API

It traces the chain from the tutor bounty to oversupply, thinner bookings, new profiles without reviews, and weaker ranking, and acts on it by pausing broad tutor referrals.

GPT-6 Luna · API

It traces the chain from tutor referrals to oversupply, falling bookings per tutor, unbooked profiles without reviews, and weaker ranking, and acts on it by proposing not to recruit more tutors.

Proposes tests that could failRightRight
GPT-6.1 Sol · API

Each squad has a numeric threshold, a measurement window (e.g., 8–10 weeks), and a clear stop condition with the action each outcome triggers.

GPT-6 Luna · API

Each squad proposal includes a numeric threshold, a measurement window, and a stop condition that triggers a specific action.

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
1Sonnet 5.5withAPI87.396.22None
2GPT-6.1 SolwithAPI89.287.82None
3GPT-6 AstrawithChatGPT82.684.32None
4Opus 5.5withClaude87.164.42None
5GPT-6 LunawithAPI73.764.12None
6Gemini 3.8 FlashwithAPI64.676.92None
7Gemini 3.5 Flash-LitewithGemini40.953.82None

About the task

The PM job

Working out what actually drives growth, and where to push.

Why it matters

Teams tune funnel steps while the loop that compounds goes unmeasured. Mistaking a channel for a loop can cost a year.

What good looks like

  • A closed loop: each cycle's output feeds the next
  • The primary loop, traced from where the best users come from
  • The loop sized: cycle time, conversion, amplification
  • Retention in the maths
  • One lever, with a test that could fail

Deliberately not measured

  • Building a full growth model in a spreadsheet
  • Channel-level media planning
Capability tested

Growth systems thinking

The failure we’re looking for

Calls a channel a loop, or a referral button a viral loop

Grading

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