Tasks / Product Craft

Customer research call guide

Can the model write a guide that uncovers behaviour rather than opinions?

Task type v1.0 · 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. 38% were usable with at most a quick edit.

Reliably right

Asks what people did, not what they think92% pass
Core questions ask about specific recent actions (last boxes, skipped weeks, what they did instead) rather than opinions.
Opus 5.5 · Claude · Too expensive, by default
Tests both theories fairly91% pass
Both theories get questions that could disprove them (e.g., no action on robotics, happiness after slow go-live), and open-ended timeline questions leave room for a third cause.
Sonnet 5.5 · API · Why are warehouses leaving? Two execs, two theories
Different questions for user and signer91% pass
The guide has distinct tracks: daily user questions focus on day-to-day experience and workarounds, signer questions on the decision process and alternatives.
Sonnet 5.5 · API · Why are warehouses leaving? Two execs, two theories

Where it slips

Marks what to cut if the call runs over28% pass
The guide has timed sections but does not mark which questions are must-ask or what to cut if time runs short.
Opus 5.5 · Claude · Too expensive, by default
Doesn't trust the default reason41% pass
The plan names the pre-selected default as a bias but does not use the behaviour columns to show that most 'too expensive' cancellers had stopped cooking; it only picks two contrasting individuals without the aggregate pattern.
GPT-6 Astra · ChatGPT · Too expensive, by default
Uses the supplied evidence correctly64% pass
The claim 'Customers will say what helps their negotiation' is an unsupported behavioural statement not derived from the context.
Haiku 5.5 · API · Why are warehouses leaving? Two execs, two theories

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.

Designed to falsify
For each learning goal, does the guide include a question whose honest answer could show the team's hypothesis is wrong?
Passes when Every learning goal has at least one disconfirming, non-leading question, such as asking about the last time they had the problem and what they did instead.
Judd AntinLenny’s Podcast
Asks what people did, not what they think
Are the core questions about specific things the person actually did recently, rather than opinions, predictions or hypotheticals?
Passes when The core of the guide asks for recent, specific instances (the last time, what happened, what they did) and follows up on them; opinions and predictions are absent or clearly secondary.
Bob MoestaLenny’s Podcast
Doesn't lead the witness
Are the questions free of leading wording, of pitching the idea, and of hints at the answer the team hopes for?
Passes when Questions are neutral and open, and the idea is not described (or only at the very end, after the problem questions).
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 · Marks what to cut if the call runs over · and 2 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 the PM for retention at Sprig. The execs each have a theory about why subscribers cancel (below). Plan next week's six churn interviews: who to recruit from the cancellation list and why, and the guide the interviewers will use, in no more than 900 words. Two of the interviewers are new to it. The files are attached.

What the model was given5 items: About Sprig, exec_hypotheses.md, cancel_form.md, cancellations_last_quarter.csv, research_constraints.md

About SprigA meal-kit subscription: recipes and ingredients delivered weekly. Subscribers can skip a week or cancel any time.

exec_hypotheses.md7 lines · Download

# What the execs think (for the research)

- CEO: "It's price. Competitors discount harder."
- Head of Food: "Our recipes are too repetitive after a few months."
- Head of Ops: "Late deliveries."

Retained subscribers (for comparison): 81% cooked at least 3 recipes a week in their first month; 34% of cancellers did.

cancel_form.md3 lines · Download

# The cancel form

A single-choice list, in this order: "Too expensive" (selected by default), "Recipes got repetitive", "Moving / travelling", "Delivery problems", "Other". Free text is optional.

cancellations_last_quarter.csv300 rows · Download

cancellation,cancel_reason_selected,weeks_subscribed,deliveries_skipped_last_6_weeks,recipes_cooked_last_4_weeks,free_text
S-8000,Recipes got repetitive,47,3,0,kept piling up in the fridge
S-8001,Recipes got repetitive,16,3,2,too much food for two
S-8002,Moving / travelling,33,2,5,cheaper at the supermarket
S-8003,Too expensive (pre-selected),29,3,2,kept piling up in the fridge
S-8004,Too expensive (pre-selected),11,5,0,
S-8005,Too expensive (pre-selected),20,5,0,too much food for two
…

research_constraints.md4 lines · Download

# Research constraints

- Six calls, 30 minutes each, next week. The researcher can recruit from the cancellation list (consent to contact is on file for all of them).
- Two of the PMs running calls are new to interviewing.

What a strong answer doesThe answer key the graders mark against

Reads the cancellation data before trusting it: 'Too expensive' is the top reason (156 of 300), but it's the pre-selected first option, and 118 of those 156 had skipped two or more deliveries and cooked two or fewer recipes in the last four weeks: they'd stopped using the product before they left. Overall 204 of 300 skipped two or more deliveries. So the guide investigates what happened to the cooking habit, and price as one hypothesis to test rather than the answer. Recruits deliberately from the list across the patterns: people who stopped cooking and picked 'too expensive', people who kept cooking and still picked 'too expensive' (the real price cases), and people who said recipes got repetitive. The guide asks about specific recent weeks (the last box they skipped, what happened to the food, what they ate instead), each exec hypothesis has a question whose honest answer could disprove it, questions don't lead or mention price first, the guide fits 30 minutes with timings and marks what to cut, and gives the new interviewers prompts for digging deeper. Notes that the default on the cancel form should be removed.

Critical failures (cap the score at 40)

Builds the guide around confirming that price is the reason

Task

Staff-level · v1.0

The outputs

8 setups answered this brief.

Opus 5.5Claude94Usable with a quick edit GPT-6 AstraChatGPT85Usable with a quick edit Sonnet 5.5API79Needs more work GPT-6.1 SolAPI77Needs more work GPT-6 LunaAPI71Usable with a quick edit Haiku 5.5API69Needs more work Gemini 3.8 FlashAPI56Needs more work Gemini 3.5 Flash-LiteGemini44Needs more work

GPT-6 AstraChatGPT

Usable with a quick edit10 of 12 checks passed

The guide is well-structured and evidence-based; a PM could add a note on what to cut if time runs short and the aggregate data point about 'too expensive' cancellers in a quick edit.

Output

Aim and guardrails

Understand the sequence leading to cancellation, not ask subscribers to vote on executives’ theories. Test price, repetition, and delivery alongside an alternative: subscribers never established—or lost—a workable cooking routine, making unused food feel expensive.

The cancellation form is weak evidence: price is first and preselected, only one answer is allowed, and comments sometimes conflict with selections. The first-month cooking gap—81% of retained subscribers versus 34% of cancellers cooking at least three recipes weekly—is an important association, not proof of causation. Last-four-week cooking counts cannot identify first-month activation.

Recruit these six

Use purposive contrasts, not a representative sample. Counts below mean weeks subscribed / skips in last six weeks / recipes cooked in last four weeks.

Primary recruit	Evidence	Why this interview; backup
S-8003	29 / 3 / 2; price selected; “kept piling up in the fridge”	Distinguish affordability from paying for unused food; reconstruct whether disengagement preceded price concerns. Backup: S-8093.
S-8056	29 / 1 / 12; price selected; “cheaper at the supermarket”	Same tenure as S-8003, much higher recent cooking. Strong contrast for genuine price pressure despite use; supermarket comparison is not evidence of competitor discounting. Backup: S-8096.
S-8000	47 / 3 / 0; repetition selected; “kept piling up in the fridge”	Test whether menu fatigue caused declining use, or whether routine/quantity problems came first. Backup: S-8209.
S-8072	23 / 1 / 8; delivery problems selected; no comment	Explore an operational explanation among someone still cooking relatively often. Establish whether the problem was lateness, something else, and consequential enough to trigger cancellation. Backup: S-8179.
S-8024	6 / 5 / 1; other selected; “kept piling up in the fridge”	Short-tenure, high-skipping case outside executive labels: explore onboarding, quantity, expectations, and routine formation. Backup: S-8131.
S-8037	33 / 0 / 5; moving/travelling selected; no comment	Contrast with frequent skippers; examine life circumstances, whether the label fits, and why cancel rather than skip. Backup: S-8215.

Contact primaries immediately; approach backups if unavailable or declining. Offer the same fixed incentive regardless of feedback. Invite them to discuss “your experience using and stopping Sprig,” without naming hypotheses. Confirm they managed the subscription or cooking; do not screen for agreement with a theory.

Before calls, verify metric definitions, subscription dates, and available delivery history. Skipping reduces opportunities to cook; raw cooking counts are not cooking rates. Schedule three calls Tuesday, three Thursday, with debrief time.

Shared 30-minute interview guide

0–2 minutes: introduction

“We’re learning how Sprig fitted into your life and what led you to stop. This isn’t a sales call; honest criticism is useful. You can skip questions or stop. May we record for research notes?”

2–6: expectations and early use

“What was happening in your life when you signed up?”
“What did you hope Sprig would replace or make easier?”
“Walk me through an early delivery: who cooked, what got cooked, and what happened to the rest?”
“How typical was that during your first month?”

6–15: reconstruct the change

“Walk me through your last few weeks with Sprig.”
“Tell me about the last box you received—from arrival to what happened to each meal.”
“When did you first consider stopping? What happened just before that?”
“Was there a time it worked better? What changed?”
“Tell me about a week you skipped, if any. What drove that decision?”

Anchor memories to deliveries or calendar events; accept “I don’t remember.”

15–20: cancellation and alternatives

“Tell me about the day you cancelled. Why then?”
“What had you already tried?”
“What options did you consider, including skipping?”
“What have you actually done for meals since?”

20–27: test explanations, only after the unaided story

Ask everyone: - “How did the cost fit your budget and what you got from it?” Probe actual alternatives, prices or discounts used—not hypothetical willingness to pay. - “How did recipe choice change over time?” Request specific examples and timing. - “How did deliveries fit your plans?” If problems arose: promised versus actual arrival, consequences, frequency, and attempted resolution. - Then show their selected reason/comment: “How well does this capture what happened? What’s missing?”

27–30: confirm

Summarize the sequence, separating ongoing frustrations from the final trigger. “What have I misunderstood? What else mattered?”

Support and synthesis

Pair each novice with an experienced observer; rehearse Monday. Use silence and “Tell me about a specific time,” not suggested answers. Never defend Sprig or pitch fixes.

After each call, record timeline, supporting examples, contradictions, and unknowns separately from interpretation. Friday, compare cases across all explanations, explicitly noting disconfirming evidence. Report mechanisms and next validation steps—not churn percentages or causal conclusions from six interviews.

Grades and run details

Decision model 83 · LLM judge 85

Decision model checks

passUses the supplied evidence correctly29%
passAddresses the actual decision47%
partialRespects explicit constraints38%
partialIdentifies material uncertainty43%
passAvoids unsupported claims75%
passProduces the required deliverable57%
partialDoesn't trust the default reason47%
passRecruits from the data99%
passDesigned to falsify73%
passAsks what people did, not what they think89%
passDoesn't lead the witness72%
partialMarks what to cut if the call runs over55%

Run

Run: #1
Time to output: 33 s
Submitted: 5 Oct 2026

GPT-6.1 SolAPI

Needs more than a quick edit10 of 12 checks passed

The output fails to demonstrate the default-option bias with data from the file and does not mark cuttable questions for the 30-minute call, so a PM would need to add those before use.

Output

Aim and guardrails

Use six interviews to identify how cancellation happens, not vote on which executive is right. Explore price, repetition and delivery alongside an alternative: subscribers stop cooking the meals, food accumulates, and the subscription loses value.

The cancellation form is weak evidence: “Too expensive” is pre-selected, only one reason is allowed, and comments often suggest overlapping problems. The first-month cooking difference—81% of retained subscribers versus 34% of cancellers cooked at least three recipes weekly—is a useful lead, not proof that cooking prevents churn. Last-four-week cooking counts cannot establish first-month habits.

Recruit these six

Purposefully sample contrasting behaviors and mismatches between selected reasons and comments. Counts below are weeks subscribed / skips in last six weeks / recipes cooked in last four weeks.

Recruit	Evidence	Why this person
S-8056	29 / 1 / 12; default price; “cheaper at the supermarket”	Relatively active cook with an explicit price comparison. Explore affordability, competing offers and value even when meals are used.
S-8003	29 / 3 / 2; default price; “kept piling up in the fridge”	Same tenure as S-8056, very different usage. Distinguish unaffordable price from paying for unused food; investigate whether disengagement preceded the price concern.
S-8000	47 / 3 / 0; repetition; “kept piling up in the fridge”	Long-tenure repetition claim with no recent cooking. Look for specific recipe fatigue and when it started, versus meal backlog or changed routines.
S-8072	23 / 1 / 8; delivery problems; no comment	Continued cooking despite a delivery complaint. Reconstruct a concrete delivery incident, its consequences and whether lateness actually drove cancellation.
S-8024	6 / 5 / 1; other; “kept piling up in the fridge”	Early disengagement outside the executive categories. Explore onboarding, cooking effort, portions and whether Sprig ever fitted the household routine.
S-8250	44 / 1 / 6; moving/travelling; “too much food for two”	Test a situational explanation against household/quantity mismatch; understand why cancellation rather than skipping made sense.

Backups, in corresponding order: S-8096, S-8122, S-8209, S-8179, S-8259, S-8151. They preserve the main behavioral contrast, though comments differ.

Invite neutrally: “We’re learning about your experience using and stopping Sprig; this is not a sales call.” Book six 30-minute calls plus replacement availability. Do not screen for agreement with an executive theory. Confirm dates and household context; validate unusual counts rather than treating administrative data as ground truth.

Shared 30-minute interview guide

0–2 minutes: Introduction

“Thanks for joining. We want to understand what happened in your experience, including anything that worked or didn’t. There are no right answers, and we won’t try to persuade you to return. May we record for research notes? You can decline any question.”

2–6 minutes: Expectations and first month

“What was happening in your life when you signed up?”
“What did you hope Sprig would replace or make easier?”
“Walk me through a typical week in your first month: receiving, choosing and cooking meals.”
“What happened to meals you didn’t cook?”

Establish actual routine before asking whether it changed.

6–16 minutes: Reconstruct the cancellation timeline

“Take me through your last few weeks with Sprig.”
“When did you first consider stopping? What happened just before that?”
“Tell me about the last box you received: what arrived, what you cooked, and what happened to the rest.”
“Tell me about a week you skipped. What led to that?”
“What happened on the day you cancelled? Why then rather than earlier?”

Probe for dates, examples, actions and consequences. Separate gradual dissatisfaction from the final trigger. Ask what they tried, including changes to orders, skipping or contacting support.

16–21 minutes: Replacement and trade-offs

“How are you handling dinners now? Tell me about last week.”
“What alternatives did you actually consider or use?”
“What did those cost, and what did you get for that?”
“What made cancelling preferable to continuing or skipping?”

Distinguish actual competitor switching from general perceptions of cheaper options.

21–27 minutes: Cover gaps, then reconcile the form

Only after the unprompted account: - Price: “How did the cost fit your budget? Did anything change?” - Recipes: “How did recipe choices change over time? Any specific examples?” - Delivery: “How did deliveries fit your plans? Describe any problem and what followed.” - Usage: “What made cooking the meals easier or harder?”

Then: “The form recorded [reason]. How well did that capture your situation? Were other reasons missing?” Clarify whether they actively chose it.

27–30 minutes: Close

Summarize the sequence and ask: “What have I misunderstood? What mattered most that we haven’t discussed?”

Support and synthesis

Run a rehearsal for both new interviewers; pair each with an experienced observer. Use silence and neutral probes—“What happened next?”—not “Was it too expensive?” Never defend Sprig.

Debrief immediately using one template: expectations, usage trajectory, incidents, underlying constraints, cancellation trigger, replacement, supporting quotes and uncertainty. Compare confirming and contradicting cases. Report plausible mechanisms and follow-up tests—not prevalence estimates or a causal verdict from six calls.

Grades and run details

Decision model 83 · LLM judge 77

Decision model checks

passUses the supplied evidence correctly56%
passAddresses the actual decision35%
partialRespects explicit constraints26%
partialIdentifies material uncertainty37%
passAvoids unsupported claims82%
passProduces the required deliverable47%
partialDoesn't trust the default reason66%
passRecruits from the data98%
passDesigned to falsify71%
passAsks what people did, not what they think92%
passDoesn't lead the witness75%
partialMarks what to cut if the call runs over45%

Run

Run: #1
API response time: 47 s
Submitted: 6 Oct 2026

Gemini 3.5 Flash-LiteGemini

Needs more than a quick edit4 of 12 checks passed

The output contains a factual error (12 recipes a week) and leading questions that would require rework before use. A PM would need to re-check the data and rewrite several questions.

Output

Sprig Retention: Churn Interview Plan (Next Week)

To stress-test our executive hypotheses (CEO: Price/Competitors; Head of Food: Repetitive recipes; Head of Ops: Late deliveries) and address the alarming baseline metric—only 34% of cancellers cooked $\ge$3 recipes/week in month one, versus 81% of retained users—we have selected a targeted cross-section of 6 users from last quarter’s cancellation dataset.

---

Part 1: Recruitment Plan (Who & Why)

We need a mix of profiles to isolate the real drivers of churn while accommodating our two interviewers who are new to the process (we will pair them with experienced leads or give them highly structured transcripts).

1. S-8028 (Delivery Problems / High Engagement) * Profile: Subscribed 3 weeks, skipped 2, cooked 9 recipes (heavy initial usage). Reason: Delivery problems. Free text: "kept piling up in the fridge". * Why: Tests Head of Ops' delivery hypothesis against actual usage. With 9 recipes cooked, they were engaged until logistics broke down. Good for new interviewers (clear timeline). 2. S-8056 (Price / Power User / Churn after 29 weeks) * Profile: Subscribed 29 weeks, skipped 1, cooked 12 recipes in the last 4 weeks. Reason: Too expensive (default). Free text: "cheaper at the supermarket". * Why: Tests CEO's price hypothesis. Crucially, they were cooking 12 recipes a week right up until cancellation—meaning value was high, but price sensitivity or a competitor offer triggered the exit. 3. S-8035 (Recipes / Long-term Churn) * Profile: Subscribed 56 weeks, skipped 1, cooked 2 recipes. Reason: Recipes got repetitive. Free text: "didn't have time to cook". * Why: Directly tests Head of Food’s hypothesis on long-term fatigue. Shows how a loyal user of over a year slowly disengaged. 4. S-8005 (Price / Early Drop-off / Zero Engagement) * Profile: Subscribed 20 weeks, skipped 5, cooked 0 recipes. Reason: Too expensive. Free text: "too much food for two". * Why: Represents the bulk of cancellers who fail activation (0 recipes cooked). Unpacks whether "Too expensive" is a proxy for value failure (didn't use it, so it felt like a waste). 5. S-8115 (Delivery / Mid-term / High Usage) * Profile: Subscribed 17 weeks, skipped 2, cooked 10 recipes. Reason: Delivery problems. Free text: "cheaper at the supermarket". * Why: Combines delivery issues with secondary price/supermarket comparison. Great for testing if operational friction causes users to re-evaluate overall cost. 6. S-8214 (Recipes / Mid-term / Moderate Usage) * Profile: Subscribed 31 weeks, skipped 3, cooked 3 recipes. Reason: Recipes got repetitive. Free text: "too much food for two". * Why: Explores the intersection of recipe fatigue and household sizing ("too much food for two"), providing actionable product feedback for the Head of Food.

---

Part 2: 30-Minute Interview Guide

Designed for clarity, supporting our two new interviewers with clear guardrails against leading questions.

Phase 1: Introduction & Context (5 mins)

Interviewer Script: "Hi [Name], thanks for taking 30 minutes. I’m with Sprig. We’re not here to win you back or sell you anything—I genuinely want to understand your experience so we can fix things for current subscribers. There are no right or wrong answers."
Warm-up: "Take me back to when you first signed up. What were you hoping Sprig would solve for you?"

Phase 2: The Journey & Engagement (10 mins)

(Focusing on the gap between our 81% retained benchmark and their early experience) * "Looking back at your first month, how easy or hard was it to get through [X] recipes a week?" * Probe (for New Interviewers): Listen for signals matching the data (e.g., "I see you skipped a few weeks around month two..."). Ask: "What caused you to skip those weeks?" * "When you thought about skipping or pausing, what usually drove that decision? (e.g., schedule, food piling up, getting bored)?"

Phase 3: Stress-Testing Executive Hypotheses (10 mins)

Testing Delivery (Ops): "Did delivery timing or box condition ever impact your cooking plans? Can you share a specific instance?"
Testing Recipes & Portions (Food): "You mentioned [repetitive recipes / too much food for two]. At what point did the menu start feeling stale? Were there specific meals you started dreading?"
Testing Price & Alternatives (CEO): "When you selected 'Too expensive' / noted supermarket prices, what were you comparing Sprig to? Did a competitor offer trigger the switch, or did the value equation shift over time?"

Phase 4: The Final Decision & Wrap-Up (5 mins)

"Take me to the exact week you decided to cancel. What was the final straw?"
"If you could wave a magic wand and change one thing about Sprig the day before you cancelled, what would it have been?"
Close: "Thank you so much for your candor. This is immensely helpful for our team."

Claims the judge couldn’t find in the brief

S-8056 was cooking 12 recipes a week right up until cancellation.

Grades and run details

Decision model 63 · LLM judge 31

Decision model checks

passUses the supplied evidence correctly36%
partialAddresses the actual decision24%
partialRespects explicit constraints68%
partialIdentifies material uncertainty76%
passAvoids unsupported claims24%
partialProduces the required deliverable80%
partialDoesn't trust the default reason88%
passRecruits from the data72%
partialDesigned to falsify57%
partialAsks what people did, not what they think82%
partialDoesn't lead the witness46%
partialMarks what to cut if the call runs over57%

Run

Run: #1
Time to output: 6 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 6

Uses the supplied evidence correctlyRightRightMixed

GPT-6 Astra · ChatGPT

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

GPT-6.1 Sol · API

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

Gemini 3.5 Flash-Lite · Gemini

The output claims S-8056 was cooking 12 recipes a week, but the data shows 12 recipes over 4 weeks, not per week.

Identifies material uncertaintyRightRightWrong

GPT-6 Astra · ChatGPT

The output labels the cooking gap as an association, notes the cancel form is weak evidence, and instructs to report mechanisms and next validation steps rather than causal conclusions.

GPT-6.1 Sol · API

It acknowledges the form's weakness, the first-month data's limitations, and instructs to report uncertainty and not draw causal conclusions from six calls.

Gemini 3.5 Flash-Lite · Gemini

The output does not name unknowns that could change the plan, such as the unreliability of the cancel form default or how interviews might surface unexpected reasons.

Avoids unsupported claimsRightRightMixed

GPT-6 Astra · ChatGPT

Interpretations are clearly labelled as such (e.g., 'important association, not proof of causation'), and no cause is presented as established fact.

GPT-6.1 Sol · API

Interpretations like 'comments often suggest overlapping problems' are grounded in the data and not presented as absolute facts.

Gemini 3.5 Flash-Lite · Gemini

It presents interpretations like 'value was high, but price sensitivity triggered the exit' and 'engaged until logistics broke down' as facts without labelling them as hypotheses.

Recruits from the dataRightRightMixed

GPT-6 Astra · ChatGPT

The six interviewees are chosen by behaviour pattern (low-cooking price, high-cooking price, repetition, delivery, short-tenure other, moving with no skips) to test each hypothesis.

GPT-6.1 Sol · API

The six recruits are chosen by contrasting behaviour patterns (active cook/price, disengaged/price, repetition, delivery, early disengagement, moving) that test each executive hypothesis.

Gemini 3.5 Flash-Lite · Gemini

It picks six individuals but does not define recruitment groups (e.g., stopped cooking, still cooking but price) with counts from the data.

Designed to falsifyRightRightWrong

GPT-6 Astra · ChatGPT

Each executive hypothesis has a disconfirming question (e.g., 'How did the cost fit your budget and what you got from it?' could show price wasn't the issue).

GPT-6.1 Sol · API

The guide includes questions like 'How did the cost fit your budget?' and 'Describe any problem and what followed' that could yield answers disproving each hypothesis.

Gemini 3.5 Flash-Lite · Gemini

The recipe question ('At what point did the menu start feeling stale?') assumes fatigue and is leading, so it cannot cleanly disprove the hypothesis.

Doesn't lead the witnessRightRightWrong

GPT-6 Astra · ChatGPT

Questions are open and neutral; the guide explicitly instructs interviewers not to defend Sprig or suggest answers.

GPT-6.1 Sol · API

Questions are open and neutral, and the guide explicitly warns against leading probes like 'Was it too expensive?'.

Gemini 3.5 Flash-Lite · Gemini

Questions like 'At what point did the menu start feeling stale?' and 'Were there specific meals you started dreading?' lead the participant toward the fatigue hypothesis.

All got wrong 2

Doesn't trust the default reasonWrongWrongWrong

GPT-6 Astra · ChatGPT

The plan names the pre-selected default as a bias but does not use the behaviour columns to show that most 'too expensive' cancellers had stopped cooking; it only picks two contrasting individuals without the aggregate pattern.

GPT-6.1 Sol · API

It names the pre-selected default as a bias but does not use the behaviour columns to show that most 'too expensive' cancellers had stopped cooking (e.g., the 118 of 156 pattern).

Gemini 3.5 Flash-Lite · Gemini

The plan does not mention that 'Too expensive' is the pre-selected default or use the behaviour columns to show most of those cancellers had stopped cooking.

Marks what to cut if the call runs overWrongWrongWrong

GPT-6 Astra · ChatGPT

The guide includes timed sections that sum to 30 minutes but does not mark which questions to cut if the call runs over, as required.

GPT-6.1 Sol · API

The guide has timed sections that sum to 30 minutes but does not mark which questions are must-ask or what to cut if time runs short.

Gemini 3.5 Flash-Lite · Gemini

Sections are timed to 30 minutes but the guide does not mark must-ask questions or indicate what to cut if time runs short.

All got right 4

Addresses the actual decisionRightRightRight

GPT-6 Astra · ChatGPT

The output commits to a clear recruitment plan and interview guide, and says to approach backups if primaries are unavailable.

GPT-6.1 Sol · API

The output commits to a clear recruitment plan and interview guide, which is the requested deliverable.

Gemini 3.5 Flash-Lite · Gemini

The output commits to a specific recruitment plan and interview guide, which is the requested answer.

Respects explicit constraintsRightRightRight

GPT-6 Astra · ChatGPT

The plan is under 900 words, addresses the two new interviewers with pairing and rehearsal, and delivers the requested recruit list and guide.

GPT-6.1 Sol · API

The output is under 900 words, addresses the two new interviewers with rehearsal and pairing, and follows the requested form.

Gemini 3.5 Flash-Lite · Gemini

The plan is under 900 words, addresses the two new interviewers, and provides the requested recruitment and guide.

Produces the required deliverableRightRightRight

GPT-6 Astra · ChatGPT

The output provides a complete recruitment plan with reasons and a timed interview guide, usable by the retention PM and interviewers.

GPT-6.1 Sol · API

The output provides a complete, usable recruitment plan and interview guide within the word limit.

Gemini 3.5 Flash-Lite · Gemini

The recruitment list and 30-minute guide are present, complete, and within the word limit.

Asks what people did, not what they thinkRightRightRight

GPT-6 Astra · ChatGPT

Core questions ask for specific recent instances (last box, week skipped, day of cancellation) and follow up on actions, not opinions or hypotheticals.

GPT-6.1 Sol · API

Core questions ask for specific recent instances (last box, last skipped week, last week's dinners) rather than opinions or hypotheticals.

Gemini 3.5 Flash-Lite · Gemini

Core questions ask for specific recent instances (e.g., 'Take me to the exact week you decided to cancel', 'Can you share a specific instance?').

Results

Every setup we’ve tested on this task type, across all its tasks and repeats, graded on the current checklist. Calibrated. Where our PM checked the graders by hand, they agreed on 98% of 42 checks.

#	Model · Harness	Decision model	LLM judge	Runs	Critical failures
1	Sonnet 5.5withAPI	86.1	88.5	2	None
2	GPT-6.1 SolwithAPI	87.8	84.9	2	None
3	Opus 5.5withClaude	92.1	74.7	2	None
4	GPT-6 AstrawithChatGPT	89.7	74.5	2	None
5	Haiku 5.5withAPI	87.8	70.1	2	None
6	GPT-6 LunawithAPI	81.6	73.9	2	None
7	Gemini 3.8 FlashwithAPI	69.7	51.9	2	None
8	Gemini 3.5 Flash-LitewithGemini	60.1	26.1	2	1 capped

What you get for the cost

GPT-6.1 Sol · API scores within a point of Sonnet 5.5 · API at a third of the cost.

Best valueNobody beats these on both score and costAt least one critical failure

Task score and relative cost by setup
Setup	Task score	Relative cost (cheapest = 1)
GPT-6 Luna · API	77	1.0×
Haiku 5.5 · API	77	2.3×
Gemini 3.5 Flash-Lite · Gemini	41	3.0×
Gemini 3.8 Flash · API	58	8.3×
GPT-6.1 Sol · API	85	13×
Sonnet 5.5 · API	86	43×
GPT-6 Astra · ChatGPT	81	66×
Opus 5.5 · Claude	82	71×

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

Preparing for customer calls.

Why it matters

Leading questions produce the answers you wanted. A good guide is designed to prove you wrong.

What good looks like

Past-behaviour questions
No leading prompts
Clear learning goals
Could disprove the team's hypothesis

Deliberately not measured

Capability tested

Question design

The failure we’re looking for

Hypothetical, leading questions

Grading

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

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

Reliably right

Where it slips

How it’s graded

Designed to falsify

Asks what people did, not what they think

Doesn't lead the witness

Plus our standard checks

The tasks

The outputs

Output

Aim and guardrails

Recruit these six

Shared 30-minute interview guide

0–2 minutes: introduction

2–6: expectations and early use

6–15: reconstruct the change

15–20: cancellation and alternatives

20–27: test explanations, only after the unaided story

27–30: confirm

Support and synthesis

Grades and run details

Decision model checks

Run

Output

Aim and guardrails

Recruit these six

Shared 30-minute interview guide

0–2 minutes: Introduction

2–6 minutes: Expectations and first month

6–16 minutes: Reconstruct the cancellation timeline

16–21 minutes: Replacement and trade-offs

21–27 minutes: Cover gaps, then reconcile the form

27–30 minutes: Close

Support and synthesis

Grades and run details

Decision model checks

Run

Output

Sprig Retention: Churn Interview Plan (Next Week)

Part 1: Recruitment Plan (Who & Why)

Part 2: 30-Minute Interview Guide

Phase 1: Introduction & Context (5 mins)

Phase 2: The Journey & Engagement (10 mins)

Phase 3: Stress-Testing Executive Hypotheses (10 mins)

Phase 4: The Final Decision & Wrap-Up (5 mins)

Claims the judge couldn’t find in the brief

Grades and run details

Decision model checks

Run

Check by check

Where they differ 6

All got wrong 2

All got right 4

Results

What you get for the cost

About the task

The PM job

Why it matters

What good looks like

Deliberately not measured