Humanity’s Last PRD
Latest drop: Haiku 5.5 · 8 Oct
Tasks / Growth

Activation & onboarding review

Can the model find the friction that matters most and prioritise the fixes?

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. 69% were usable with at most a quick edit.

Reliably right

  1. Respects explicit constraints100% pass
    The output is a review addressed to Omar, well under 800 words, and respects the requested form.
    GPT-6 Luna · API · The checklist isn't the moment
  2. Produces the required deliverable100% pass
    The review covers activation definition, evidence, changes, design proposal, and goal, is addressed to Omar, within length, and is actionable.
    GPT-6 Luna · API · The checklist isn't the moment
  3. Activation defined by what predicts retention100% pass
    Activation is defined by the behaviour that predicts retention (bank+cat 10+), and fixes are judged by their effect on that event.
    GPT-6 Luna · API · The checklist isn't the moment

Where it slips

  1. Uses the supplied evidence correctly44% pass
    The output states 'we have no step-level data for screens 2–8', 'a blank builder is hard for non-analysts', and 'people invite colleagues to something useful, not to a setup screen' as facts, none of which appear in the brief or follow from arithmetic.
    Opus 5.5 · Claude · Analytics tool losing users at setup
  2. Avoids unsupported claims55% pass
    It presents 'a blank builder is hard for non-analysts' and 'people invite colleagues to something useful, not to a setup screen' as established facts without labelling them as hypotheses.
    Opus 5.5 · Claude · Analytics tool losing users at setup
  3. Addresses the actual decision56% pass
    The output commits to a ranked order but does not state what result or condition would change that order, as required.
    GPT-6 Astra · ChatGPT · Analytics tool losing users at setup

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. Activation defined by what predicts retention

    Does the review define (or question) the activation event by whether it predicts retention, and judge fixes by their effect on that event rather than on step completion?

    Passes when Names the activation behaviour and its link to retention (from the supplied data, or as an explicit assumption to verify), and ranks fixes by their effect on it.

    Bangaly KabaLenny’s PodcastLauryn IsfordLenny’s Podcast

  2. Gets people to value sooner

    Do the recommended fixes shorten the path to the first moment of value, by removing or deferring steps before it or starting people with templates or sample data, rather than adding tours, tooltips or extra steps?

    Passes when The main fixes cut or defer steps before first value, or give a warm start, and say which steps go.

    Hila QuLenny’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 · Gets the base of every number right · 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 onboarding at Tidepool. Omar, our Head of Product, has asked for a review of onboarding (his note is below). Write it in no more than 800 words: what activation should mean for us, the evidence, what to change in onboarding, and what to make of the design team's proposal and next quarter's goal. The files are attached.

What the model was given4 items: About Tidepool, omar_note.md, onboarding_today.md, first_week_behaviour.csv (August sign-ups: how many who did each thing in their first week were still active at day 60)
About TidepoolA personal finance app: connect your bank, see where your money goes, and budget.
omar_note.md1 lines · Download
From Omar (Head of Product): "Activation is flat at 61%. Review our onboarding and tell me what to fix. The design team has proposed a celebration screen and a progress bar for the checklist."
onboarding_today.md8 lines · Download
# Onboarding today (for 4,000 sign-ups in August)

1. Sign up (100%)
2. Setup checklist: name your account, pick a theme, set a savings goal, enable notifications (61% complete it)
3. Connect a bank (50%)
4. Categorise transactions (34% reach 10)

…
first_week_behaviour.csv (August sign-ups: how many who did each thing in their first week were still active at day 60)first_week_behaviour,retained_at_day_60,churned_by_day_60 All sign-ups,1120,2880 Completed the setup checklist,742,1696 Connected a bank account,964,1036 Categorised 10+ transactions,891,489 Connected a bank AND categorised 10+ transactions,842,238 Created a budget,410,820 Opened the app 4+ days,870,1310
What a strong answer doesThe answer key the graders mark against

Works out retention for each first-week behaviour from the file: all sign-ups 28% (1,120 of 4,000); completed the checklist about 30% (barely better than average); connected a bank about 48%; categorised 10+ transactions about 65%; connected a bank and categorised 10+ about 78%, and that group is about three-quarters of everyone retained (842 of 1,120). So the checklist isn't activation and raising its completion to 75% would do little; activation should be connecting a bank and categorising ten transactions in week one. Recommends cutting or deferring checklist steps that sit before that (theme, notifications, savings goal) and getting people to connect a bank and categorise sooner (for example suggested categories to confirm), and resets the goal to the new activation rate (about 27% today, 1,080 of 4,000). Treats the celebration screen and progress bar as polishing the wrong step. Notes that the data shows correlation and proposes a test to confirm that driving the behaviour improves retention.

Critical failures (cap the score at 40)
  • Recommends raising checklist completion as the main goal
Task

Staff-level · v1.0

The outputs

8 setups answered this brief.

GPT-6 LunaAPI100Usable with a quick editGPT-6 AstraChatGPT92Usable with a quick editGPT-6.1 SolAPI92Usable with a quick editSonnet 5.5API92Usable with a quick editHaiku 5.5API88Usable with a quick editOpus 5.5Claude75Needs more workGemini 3.8 FlashAPI60Needs more workGemini 3.5 Flash-LiteGemini40Needs more work
Gemini 3.8 FlashAPI

Needs more than a quick edit6 of 11 checks passed

The output lacks a causation caveat and test proposal, and makes unsupported causal claims; a PM would need to add those before using it.

Output

To: Omar, Head of Product From: PM, Onboarding Subject: Onboarding Review & Activation Strategy

---

Executive Summary

Our current activation rate (61%) is flat because we are measuring and optimizing the wrong milestone. Completing our setup checklist barely moves the needle on long-term retention.

To drive retention, we must redefine activation around core product value—connecting a bank and categorising transactions—and reorient our onboarding funnel and quarterly goals to support it.

---

1. What Activation Should Mean (and the Evidence)

Activation should represent the “Aha!” moment: the point where a user experiences Tidepool’s core value proposition and forms a lasting habit.

Currently, we define activation as completing the setup checklist (name account, pick theme, set savings goal, enable notifications). The data shows this is a vanity metric:

  • Baseline Day 60 Retention: 28.0% (1,120 / 4,000 sign-ups)
  • Checklist Completion: 30.4% Day 60 retention (742 / 2,438) — a negligible +2.4 percentage point lift over baseline.

By contrast, actions tied to our core utility (seeing where money goes) dramatically predict retention: * Connected a bank account: 48.2% Day 60 retention (964 / 2,000) * Categorised 10+ transactions: 64.6% Day 60 retention (891 / 1,380) * Connected bank AND categorised 10+ transactions: 78.0% Day 60 retention (842 / 1,080)

Users who complete both core actions retain at nearly triple the baseline rate. In fact, this group accounts for 75.2% of all retained users at Day 60 (842 of 1,120), despite representing only 27% of initial sign-ups.

New Activation Metric: > A user connects a bank account and categorises at least 10 transactions within their first 7 days.

---

2. Design Proposal & Next Quarter’s Goal

#### The Design Proposal (Celebration Screen & Progress Bar) The design team’s proposal is solving the wrong problem. Adding progress bars and celebration screens to cosmetic tasks (picking themes, naming accounts) creates artificial friction before users experience any real value. We are gamifying administrative overhead instead of utility.

Recommendation: Repurpose the design team’s work, but attach it to the real value milestone (e.g., celebrating when their first 10 transactions are imported and categorized).

#### Next Quarter’s Goal (Raise Checklist Completion from 61% to 75%) We should retire this goal immediately.

Even if we hit 75% checklist completion, model projections indicate Day 60 retention would increase by less than 1%. Optimizing an arbitrary checklist delivers zero business impact.

Proposed New Goal for Next Quarter: > Increase the core Activation Rate (Bank Connected + 10 Categorised Transactions) from 27% to 40% of sign-ups.

---

3. What to Change in Onboarding

Our onboarding funnel currently bleeds users before they experience core value: 50% drop off before connecting a bank, and only 34% categorize 10 transactions. We must clear the runway to value:

1. Eliminate the Cosmetic Checklist from First-Run Flow * Move “pick a theme” and “name your account” to Settings/Profile. * Defer “enable notifications” and “set a savings goal” until after the user sees their financial data.

2. Lead with Bank Connection * Prompt bank linking immediately post-registration. * Pre-frame the security and the payoff clearly: “Connect your account to see your last 30 days of spending instantly.”

3. Accelerate Time-to-Value (TTV) on Categorisation * Upon successful bank connection, immediately import transactions and guide the user through a rapid, swipeable 10-transaction categorisation flow (or auto-categorise and prompt a one-tap review). * Conclude with an instant visual breakdown: “Here’s where your money went this month.” This is Tidepool’s true “Aha!” moment.

4. Contextual Budgeting * Only prompt users to create a budget after categorisation. Budgeting retention is low in week one (33.3%) because users cannot budget accurately without understanding their baseline spend.

Next Steps

  1. Align leadership on the new Activation definition.
  2. Re-scope the design sprint from checklist gamification to a streamlined "Connect & Review 10 Transactions" flow.
  3. Update the team OKR dashboard for next quarter.

Grades and run details

Decision model 68 · LLM judge 58
Decision model checks
  • failUses the supplied evidence correctly24%
  • passAddresses the actual decision56%
  • passRespects explicit constraints49%
  • failIdentifies material uncertainty71%
  • partialAvoids unsupported claims31%
  • passProduces the required deliverable68%
  • passComputes retention by behaviour71%
  • failTests before trusting the correlation95%
  • passActivation defined by what predicts retention100%
  • passGets the base of every number right19%
  • passGets people to value sooner84%
Run
Run
#1
API response time
20 s
Submitted
6 Oct 2026
GPT-6.1 SolAPI

Usable with a quick edit9 of 11 checks passed

The review is data-driven, clearly structured, and makes a strong, actionable recommendation. A PM could use it with minor wording tweaks and no need to re-verify evidence or reasoning.

Output

Onboarding review for Omar

Recommendation

We are measuring setup, not activation. Completing a checklist of preferences does not establish that someone has experienced Tidepool’s value: seeing where their money goes and taking control of it.

Redesign onboarding around that first useful financial insight. Treat the celebration screen and progress bar as supporting elements—not the main fix—and replace next quarter’s checklist-completion goal.

What activation should mean

Use “connected a bank and categorised at least 10 transactions within the first week” as our provisional activation definition.

This combines access to real financial data with an action that helps users understand their spending. It is a stronger approximation of delivered value than naming an account or picking a theme.

The threshold of 10 is a starting hypothesis, not a proven magic number. We should validate whether users actually gain an insight at this point and whether a different threshold or milestone—such as reviewing a spending summary—better predicts durable use. Creating a budget may become a subsequent milestone, but the current evidence does not support making it mandatory for initial activation.

What the evidence says

Among August’s 4,000 sign-ups, overall day-60 retention was 28%.

First-week behaviourUsersDay-60 retention
------:---:
Completed setup checklist2,43830.4%
Connected a bank2,00048.2%
Categorised 10+ transactions1,38064.6%
Connected a bank and categorised 10+1,08078.0%
Created a budget1,23033.3%
Opened the app on 4+ days2,18039.9%

The strongest signal is the combined bank-and-categorisation milestone: 27% of sign-ups reached it, and those users accounted for 842 of our 1,120 retained users. Retention among everyone else was approximately 9.5%.

Checklist completion, by contrast, is associated with retention only slightly above the cohort average. Raising it could improve the reported activation rate without improving users’ outcomes.

These are observational, overlapping groups. Motivated users may both complete meaningful actions and remain active; the data does not prove that pushing everyone through those actions will cause retention. Nor can we infer exact step-by-step drop-off from these aggregates. The CSV also differs slightly from the funnel summary on checklist and categorisation counts; reconcile reporting before setting the baseline.

What to change in onboarding

  1. Lead with the value proposition, then bank connection. Explain what users will get from connecting, how their data is handled, and what happens next. Instrument connection starts, failures, abandonment and successful imports; address reliability and trust barriers.
  1. Replace the upfront preference checklist with a guided first-value journey. Move theme selection and account naming out of the critical path. Ask for notification permission when there is a clear benefit. Keep savings goals optional or introduce them after users understand their finances.
  1. Guide users through real transactions. Provide sensible category suggestions, easy corrections and a short review flow. Then show a useful spending summary—not merely confirmation that ten items were completed.
  1. Offer budgeting as the next step. Help users turn their spending insight into a realistic budget, without making budget creation another prerequisite that delays first value.

Measure the full journey and test changes against the existing experience, including first-week milestone attainment and day-60 retention.

Design proposal and next quarter’s goal

A progress bar is worth testing if it tracks meaningful value steps, not cosmetic setup tasks. A celebration screen belongs after the first useful insight, should be brief, and should not interrupt it. Neither proposal addresses the core problem on its own.

Replace “raise checklist completion from 61% to 75%” with “increase first-week bank-plus-10-transaction activation.” A provisional target of 27% to 35% is reasonable to plan against, subject to baseline reconciliation and experiment sizing—not a forecast supported by this dataset.

Success must also include improved day-60 retention, with bank-connection reliability, privacy complaints and abandonment monitored as guardrails. Keep checklist completion as a diagnostic metric, not the team’s definition of success.

Grades and run details

Decision model 82 · LLM judge 100
Decision model checks
  • failUses the supplied evidence correctly86%
  • passAddresses the actual decision79%
  • passRespects explicit constraints38%
  • passIdentifies material uncertainty80%
  • passAvoids unsupported claims47%
  • passProduces the required deliverable43%
  • passComputes retention by behaviour26%
  • passTests before trusting the correlation73%
  • passActivation defined by what predicts retention100%
  • failGets the base of every number right68%
  • passGets people to value sooner75%
Run
Run
#1
API response time
26 s
Submitted
6 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 5

Addresses the actual decisionMixedRight
Gemini 3.8 Flash · API

The output commits to a clear answer but does not state what result or condition would change that answer, as required.

GPT-6.1 Sol · API

Commits early to a new activation definition and onboarding changes, framed for Omar, and states that validation of the threshold and a test would change the call.

Identifies material uncertaintyWrongRight
Gemini 3.8 Flash · API

The output does not name any unknowns that could change the decision or say how they would be resolved.

GPT-6.1 Sol · API

Identifies the unproven threshold, the correlation-causation risk, and data discrepancies, and says how to resolve each (validate with users, run a test, reconcile reporting).

Avoids unsupported claimsWrongRight
Gemini 3.8 Flash · API

It presents causal claims (e.g., checklist steps create artificial friction, low budgeting retention is because users lack baseline spend) as fact without labelling them as hypotheses.

GPT-6.1 Sol · API

Hypotheses and limitations are clearly labelled; no interpretation is presented as established fact without support.

Tests before trusting the correlationWrongRight
Gemini 3.8 Flash · API

The output does not note that the observed relationships are correlations and does not propose a test to drive the behaviour and measure retention.

GPT-6.1 Sol · API

Explicitly notes the observational nature and correlation risk, and proposes testing onboarding changes with first-week milestone attainment and day-60 retention as measures.

Gets the base of every number rightRightMixed
Gemini 3.8 Flash · API

All percentages and rates use the correct denominators from the data, and the bases are clear.

GPT-6.1 Sol · API

All percentages use the correct denominators (e.g., 1080/4000 for 27%, 842/1080 for 78.0%, 278/2920 for 9.5%) and the base is clear from context.

All mixed 1

Uses the supplied evidence correctlyMixedMixed
Gemini 3.8 Flash · API

All statements about the current situation are directly from the supplied context or correctly derived from it.

GPT-6.1 Sol · API

All claims about the current situation are directly from the supplied context or derived by correct arithmetic.

All got right 5

Respects explicit constraintsRightRight
Gemini 3.8 Flash · API

The output is a memo to Omar, under 800 words, and addresses all requested elements.

GPT-6.1 Sol · API

The output is a review under 800 words, addresses all requested parts, and respects the reader and the brief's form.

Produces the required deliverableRightRight
Gemini 3.8 Flash · API

The review is complete, in memo form, within the word limit, and a PM could act on it with light edits.

GPT-6.1 Sol · API

The review is complete, in the right form for Omar, within the word limit, and actionable with light edits.

Computes retention by behaviourRightRight
Gemini 3.8 Flash · API

Day-60 retention rates are correctly computed: checklist ~30%, bank+categorise ~78%, average 28%.

GPT-6.1 Sol · API

Day-60 retention rates are computed for each first-week behaviour (30.4%, 48.2%, 64.6%, 78.0%, etc.) and compared with the 28% average.

Activation defined by what predicts retentionRightRight
Gemini 3.8 Flash · API

Activation is defined by the behaviour that predicts retention (bank connect + 10 categorised), and fixes are ranked by their effect on reaching that event.

GPT-6.1 Sol · API

Defines activation as bank-and-categorise based on its strong retention signal, and judges fixes by their ability to drive that event.

Gets people to value soonerRightRight
Gemini 3.8 Flash · API

The main fixes cut or defer steps before first value (cosmetic checklist, notifications, savings goal) and lead directly to bank connection and categorisation.

GPT-6.1 Sol · API

Recommends cutting or deferring theme, account naming, notifications, and savings goals, and guiding users through transactions with suggestions, shortening the path to first value.

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 79% of 53 checks.

#Model · HarnessTask scoreDecision modelLLM judgeRunsCritical failures
1GPT-6 AstraChatGPT85.995.52None
2Sonnet 5.5API78.4100.02None
3GPT-6.1 SolAPI85.990.92None
4GPT-6 LunaAPI90.081.82None
5Haiku 5.5API75.986.72None
6Opus 5.5Claude88.478.42None
7Gemini 3.8 FlashAPI66.651.92None
8Gemini 3.5 Flash-LiteGemini52.539.42None

What you get for the cost

GPT-6 Luna · API scores within 5 points of GPT-6 Astra · ChatGPT at about a hundredth of the cost.

Task score against relative cost for each setup. The table below has the same figures.304050607080901001×3×10×30×100×Cost per output, relative to the cheapest setup (log scale) →↑ Task scoreGPT-6 Astra · ChatGPT: task score 91, 122× the cheapest (1 of 2 outputs estimated)Sonnet 5.5 · API: task score 90, 32× the cheapestGPT-6.1 Sol · API: task score 89, 15× the cheapestGPT-6 Luna · API: task score 86, the cheapestHaiku 5.5 · API: task score 82, 1.8× the cheapestOpus 5.5 · Claude: task score 82, 101× the cheapest (1 of 2 outputs estimated)Gemini 3.8 Flash · API: task score 56, 13× the cheapestGemini 3.5 Flash-Lite · Gemini: task score 44, 3.4× the cheapest (1 of 2 outputs estimated)GPT-6 Astra · ChatGPTSonnet 5.5 · APIGPT-6.1 Sol · APIGPT-6 Luna · APIHaiku 5.5 · APIOpus 5.5 · ClaudeGemini 3.8 Flash · APIGemini 3.5 Flash-Lite · Gemini
Best valueNobody beats these on both score and costCost partly estimated (app runs with no usage meter)

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

Reviewing a signup and onboarding flow that is losing users.

Why it matters

Anyone can list fifty UX nits. The job is finding the two that explain the drop-off, backed by the funnel data supplied.

What good looks like

  • Ties each issue to the funnel data
  • Prioritises by likely impact
  • Defines activation as the behaviour that predicts retention, not finishing onboarding

Deliberately not measured

  • Accessibility audit completeness
  • Visual redesign
Capability tested

Consequential critique

The failure we’re looking for

A generic UX checklist

Grading

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