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 18 graded outputs by 9 models. 67% were usable with at most a quick edit.

Reliably right

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
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
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

Avoids unsupported claims26% pass
States 'App-open frequency is an outcome, not a cause' as an established fact, but only correlation is shown in the data; this causal direction is an unsupported interpretation.
Haiku 5.5 · API · The checklist isn't the moment
Identifies material uncertainty61% pass
Does not name specific unknowns that could change the decision, only suggests tracking metrics before expanding.
GPT-6 Luna · API · Analytics tool losing users at setup
Uses the supplied evidence correctly64% 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

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.

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 Podcast Lauryn IsfordLenny’s Podcast
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 · v1.1

The outputs

9 setups answered this brief.

GPT-6 LunaAPI98Usable with a quick edit Haiku 5.5API92Usable with a quick edit GPT-6 AstraChatGPT90Usable with a quick edit GPT-6.1 SolAPI90Usable with a quick edit Sonnet 5.5API90Usable with a quick edit Opus 5.5Claude71Needs more work Gemini 4 ArgonAPI69Needs more work Gemini 3.8 FlashAPI63Needs more work Gemini 3.5 Flash-LiteGemini40Needs more work

Gemini 4 ArgonAPI

Needs more than a quick edit8 of 11 checks passed

The output lacks an explicit correlation-causation caveat and a proposed test, which a PM would need to add before it could be acted upon confidently.

Output

To: Omar (Head of Product) From: PM, Onboarding Subject: Onboarding Review: Redefining Activation and Q4 Strategy

Executive Summary

Our current activation metric—completing the setup checklist (61%)—is a vanity metric. Analysis of August’s 4,000 sign-ups shows that users who complete the checklist retain at Day 60 at roughly the same rate as the overall average (30.4% vs. 28.0%). Worse, the checklist sits before our core value proposition, causing 39% of users to drop off before we even ask them to connect a bank.

We need to redefine activation around real product value, scrap the current Q4 checklist goal, and redesign onboarding to get users straight to their financial data.

---

1. The Evidence: What Actually Drives Retention?

Activation should measure the moment a user experiences Tidepool’s core value ("see where your money goes") in a way that predicts long-term habit formation. Looking at Day 60 retention from August’s cohort (4,000 total sign-ups), the data is clear:

All sign-ups: 28.0% D60 retention (1,120 / 4,000)
Completed setup checklist (61% of users): 30.4% retention (742 / 2,438)
Created a budget (31% of users): 33.3% retention (410 / 1,230)
Opened the app 4+ days (55% of users): 39.9% retention (870 / 2,180)
Connected a bank account (50% of users): 48.2% retention (964 / 2,000)
Categorised 10+ transactions (34% of users): 64.6% retention (891 / 1,380)
Connected a bank AND categorised 10+ transactions (27% of users): 78.0% retention (842 / 1,080)

Key Takeaways from the Data: 1. The setup checklist does not predict retention. Doing administrative chores (naming an account, picking a color theme) does not deliver financial clarity. Users who skip or abandon the checklist aren't failing to activate; they are likely just bored. 2. Core value is delivered through bank connection and transaction categorisation. When a user connects their bank and categorises 10+ transactions in week one, their Day 60 retention jumps to 78.0%. Notably, this 27% of users accounts for 75% of all retained users at Day 60 (842 of 1,120). 3. Crucial caveat on Bank vs. Manual: Notice that 1,380 users categorised 10+ transactions, but only 1,080 did so and connected a bank. For the 300 users who categorised 10+ transactions without connecting a bank (presumably via manual entry or CSV), D60 retention was only 16.3% (49 / 300). Categorising alone isn’t enough; automated bank syncing is essential.

---

2. Redefining Activation & Next Quarter’s Goal

New Activation Definition: "Connected a bank account AND categorised 10+ transactions within 7 days of sign-up."
Verdict on Q4 Goal: We must cancel the goal of raising checklist completion from 61% to 75%. Even if we hit 75%, D60 retention wouldn't budge.
New Q4 Goal: Increase true activation (Bank + 10 Categorised Transactions) from 27.0% to 38.0%. Because this cohort retains at 78% (though we should monitor for slight dilution as we push less-motivated users through the funnel), moving this needle is the highest-leverage way to lift overall D60 retention above 28%.

---

3. Assessment of the Design Team's Proposal

The design team proposed adding a progress bar and a celebration screen to the setup checklist. We should not build this for the current checklist.

Optimising a step that adds friction without adding value is wasted effort. However, we should repurpose the design team’s UI patterns for the Categorisation step. A progress bar ("4 of 10 transactions categorised to unlock your spending breakdown") and a celebration screen that immediately reveals their visualised spending insights will directly drive our new activation metric.

---

4. What to Change in Onboarding

Right now, our funnel is backwards: we ask for customization before showing value. We should restructure the flow as follows:

Kill the upfront setup checklist: Remove "name your account" and "pick a theme" from onboarding entirely (default these and move them to Settings). Delay "set a savings goal" and "enable notifications" until after the user has seen their spending data, when those prompts actually have context.
Make "Connect a Bank" Step 1: Immediately after sign-up, prompt bank connection. Currently, we lose 50% of users here (many because they dropped off at the checklist first). Moving this to Step 1—and adding trust signals around security and read-only access—will immediately increase the top of our true value funnel.
Guided "First 10" Categorisation Flow: Once the bank syncs, drop users into a focused, swipe/tap experience (using Design's progress bar) to categorise their 10 most recent transactions, culminating in an immediate "Aha!" dashboard showing where their money went this month.

Grades and run details

Decision model 77 · LLM judge 67

Decision model checks

passUses the supplied evidence correctly25%
passAddresses the actual decision49%
passRespects explicit constraints55%
partialIdentifies material uncertainty80%
failAvoids unsupported claims82%
passProduces the required deliverable77%
passComputes retention by behaviour72%
failTests before trusting the correlation82%
passActivation defined by what predicts retention100%
passGets the base of every number right20%
passGets people to value sooner91%

Run

Run: #1
API response time: 12 s
Submitted: 13 Oct 2026

Gemini 3.8 FlashAPI

Needs more than a quick edit7 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

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

Grades and run details

Decision model 73 · LLM judge 58

Decision model checks

passUses the supplied evidence correctly27%
passAddresses the actual decision31%
passRespects explicit constraints56%
failIdentifies material uncertainty69%
failAvoids unsupported claims85%
passProduces the required deliverable76%
passComputes retention by behaviour74%
failTests before trusting the correlation95%
passActivation defined by what predicts retention100%
passGets the base of every number right34%
passGets people to value sooner86%

Run

Run: #1
API response time: 20 s
Submitted: 6 Oct 2026

Gemini 3.5 Flash-LiteGemini

Needs more than a quick edit4 of 11 checks passed

The output misstates the baseline activation rate (34% instead of 27%) and lacks a causation test, so a PM would need to re-check the numbers and add a test plan.

Output

To: Omar, Head of Product From: PM, Onboarding Date: September 2024 Subject: Onboarding Review & Activation Strategy

---

1. What Activation Should Mean for Us

Currently, our definition of activation—completing a checklist of cosmetic preferences (name, theme, savings goal, notifications)—is flawed. It measures vanity completion rather than value realization.

As a personal finance app, Tidepool delivers core value when users connect their financial reality and engage with it. Looking at our August cohort (4,000 sign-ups), the data tells a clear story about Day 60 retention:

Checklist completers retain at 30.4% (742/2,438).
Bank connectors retain at 48.2% (964/2,000).
Users who categorise 10+ transactions retain at 64.5% (891/1,380).
Users who do BOTH (Connect + Categorise) retain at 78.0% (842/1,080).

Recommendation: We must redefine "Activation" from “completed the setup checklist” to “Connected a bank AND categorised at least 10 transactions within their first week.” This anchors our success metric to actual product utility, shifting our focus from cosmetic setup to establishing long-term financial habits.

---

2. The Evidence: Where We Are Losing Users

Our current funnel drops off steeply: 1. Sign up: 4,000 (100%) 2. Setup checklist: 2,440 (61%) 3. Connect a bank: 2,000 (50%) 4. Categorise 10 transactions: 1,360 (34%)

The biggest leak is bank connection (dropping 11 percentage points right after the checklist) and transaction categorisation (dropping another 16 points).

Interestingly, the checklist itself acts as a barrier. Users are spending cognitive load on naming accounts and picking themes before experiencing the core product. Meanwhile, power features like "Created a budget" (33% retention) and opening the app 4+ days are strong secondary indicators, but bank linking and categorisation are the undisputed gateways to retention.

---

3. What to Change in Onboarding

To drive our new definition of activation, we need to restructure the first-time user experience (FTUX):

Kill the upfront setup checklist: Strip out non-essential steps (naming accounts, picking themes, notifications) from the critical path. Move them to profile settings or prompt for them after value has been proven.
Accelerate time-to-bank: Move bank connection immediately following sign-up. Users downloaded Tidepool to see their money; let them see it instantly via Plaid/Aggregator integration.
Gamify the "aha" moment: Guide users smoothly from bank connection directly into categorising their first 10 transactions. Use smart auto-categorisation with a clear, frictionless bulk-approval or swipe UI to make reaching the 10-transaction milestone effortless.

---

4. Verdict on the Design Proposal and Next Quarter's Goal

The Design Team’s Proposal (Celebration screen + Progress bar): * Verdict: Reject in its current form. Adding a progress bar and celebration screen for the existing checklist optimizes the wrong metric. It puts lipstick on a superficial activation loop. * Pivot: If we redesign onboarding to focus on connecting a bank and categorising transactions, then we can use a celebration screen and progress bar—not to celebrate picking a theme, but to celebrate linking an account and hitting that crucial 10-transaction milestone.

Next Quarter's Goal (Raise checklist completion from 61% to 75%): * Verdict: Abandon this goal. Optimizing checklist completion is a local maximum that misaligns product and user success. Chasing 75% checklist completion will likely result in higher drop-offs further down the funnel and flat-to-declining Day 60 retention. * New Goal: We should replace this with a target to raise our true activation rate (Bank Connected + 10 Transactions Categorised) from the current baseline (~34%) to 50% next quarter. This directly correlates with our actual business health and user retention.

Claims the judge couldn’t find in the brief

The checklist itself acts as a barrier.
Users are spending cognitive load on naming accounts and picking themes before experiencing the core product.
Bank linking and categorisation are the undisputed gateways to retention.

Grades and run details

Decision model 50 · LLM judge 33

Decision model checks

failUses the supplied evidence correctly37%
passAddresses the actual decision28%
passRespects explicit constraints25%
failIdentifies material uncertainty91%
failAvoids unsupported claims85%
passProduces the required deliverable41%
partialComputes retention by behaviour33%
failTests before trusting the correlation98%
passActivation defined by what predicts retention98%
failGets the base of every number right64%
passGets people to value sooner92%

Run

Run: #1
Time to output: 5 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 4

Uses the supplied evidence correctlyRightRightWrong

Gemini 4 Argon · API

All factual claims about current numbers and performance are taken correctly from the supplied context or follow from arithmetic.

Gemini 3.8 Flash · API

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

Gemini 3.5 Flash-Lite · Gemini

The output states 'the checklist itself acts as a barrier' and similar causal claims as facts, which are not in the supplied context and do not follow by arithmetic.

Addresses the actual decisionRightMixedMixed

Gemini 4 Argon · API

Output commits early and unambiguously to redefining activation as bank + 10 categorised and abandoning the checklist goal.

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.

Gemini 3.5 Flash-Lite · Gemini

The output does not state what result or condition would change its recommendation, so it fails to commit with a clear change condition.

Computes retention by behaviourRightRightWrong

Gemini 4 Argon · API

Correctly computed Day-60 retention for each behaviour, including 28% overall, 30.4% checklist, 48.2% bank, 64.6% categorise, 78.0% both.

Gemini 3.8 Flash · API

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

Gemini 3.5 Flash-Lite · Gemini

The output does not compute the overall average retention (28%) and does not compare the subgroup rates to it.

Gets the base of every number rightRightRightWrong

Gemini 4 Argon · API

All percentages and rates are correctly derived from the supplied data, and denominators are clear (e.g., retention rates use the behaviour cohort as base).

Gemini 3.8 Flash · API

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

Gemini 3.5 Flash-Lite · Gemini

The baseline for the new activation rate is given as ~34%, but the correct rate for 'connected bank AND categorised 10+' is 1,080/4,000 = 27%.

All got wrong 3

Identifies material uncertaintyWrongWrongWrong

Gemini 4 Argon · API

Does not name the key uncertainty (correlation vs causation) or say how it would be resolved; only mentions dilution risk without a resolution plan.

Gemini 3.8 Flash · API

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

Gemini 3.5 Flash-Lite · Gemini

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

Avoids unsupported claimsWrongWrongWrong

Gemini 4 Argon · API

Presents cause-effect interpretations ('causing 39% to drop off', 'users are likely just bored') as fact, without labelling them as hypotheses.

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.

Gemini 3.5 Flash-Lite · Gemini

Interpretations like 'the checklist itself acts as a barrier' and 'undisputed gateways' are presented as established fact without being labelled as hypotheses.

Tests before trusting the correlationWrongWrongWrong

Gemini 4 Argon · API

Does not note that the retention links are correlations, nor propose a test to drive the activation behaviour and check retention.

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.

Gemini 3.5 Flash-Lite · Gemini

The output does not note that the retention differences are correlations and does not propose a test to confirm causation.

All got right 4

Respects explicit constraintsRightRightRight

Gemini 4 Argon · API

Output is a memo to Omar, under 800 words, covers the requested components, and respects the form and reader.

Gemini 3.8 Flash · API

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

Gemini 3.5 Flash-Lite · Gemini

The output is a memo to Omar, under 800 words, and addresses the requested topics.

Produces the required deliverableRightRightRight

Gemini 4 Argon · API

Produced a complete, usable memo within the length limit, addressed to Omar as a review.

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.

Gemini 3.5 Flash-Lite · Gemini

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

Activation defined by what predicts retentionRightRightRight

Gemini 4 Argon · API

Defines activation by retention prediction (bank + 10 categorised) and ranks fixes by their effect on that event.

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.

Gemini 3.5 Flash-Lite · Gemini

Activation is redefined based on retention prediction (bank + categorise), and fixes are judged by their effect on that event.

Gets people to value soonerRightRightRight

Gemini 4 Argon · API

Recommends removing upfront checklist steps and making bank connection step 1, directly shortening the path to first value.

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.

Gemini 3.5 Flash-Lite · Gemini

The main fixes cut or defer checklist steps before value and move bank connection and categorisation earlier.

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 72% of 53 checks.

#	Model · Harness	Decision model	LLM judge	Runs	Critical failures
1	Sonnet 5.5withAPI	83.6	100.0	2	None
2	GPT-6 AstrawithChatGPT	86.1	95.5	2	None
3	GPT-6.1 SolwithAPI	83.6	90.9	2	None
4	Haiku 5.5withAPI	88.0	86.7	2	None
5	GPT-6 LunawithAPI	92.7	81.8	2	None
6	Opus 5.5withClaude	81.4	78.4	2	None
7	Gemini 4 ArgonwithAPI	73.6	65.2	2	None
8	Gemini 3.8 FlashwithAPI	71.4	51.9	2	None
9	Gemini 3.5 Flash-LitewithGemini	60.0	39.4	2	None

What you get for the cost

GPT-6 Luna · API scores within 5 points of Sonnet 5.5 · API at about a thirtieth of the cost.

Best valueNobody beats these on both score and costCost partly estimated (app runs with no usage meter)

Task score and relative cost by setup
Setup	Task score	Relative cost (cheapest = 1)
GPT-6 Luna · API	88	1.0×
Haiku 5.5 · API	88	1.8×
Gemini 3.5 Flash-Lite · Gemini	47	3.4× (partly estimated)
Gemini 3.8 Flash · API	59	13×
GPT-6.1 Sol · API	88	15×
Gemini 4 Argon · API	68	15×
Sonnet 5.5 · API	93	32×
Opus 5.5 · Claude	79	101× (partly estimated)
GPT-6 Astra · ChatGPT	91	122× (partly estimated)

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

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

Reliably right

Where it slips

How it’s graded

Activation defined by what predicts retention

Gets people to value sooner

Plus our standard checks

The tasks

The outputs

Output

Executive Summary

1. The Evidence: What Actually Drives Retention?

2. Redefining Activation & Next Quarter’s Goal

3. Assessment of the Design Team's Proposal

4. What to Change in Onboarding

Grades and run details

Decision model checks

Run

Output

Executive Summary

1. What Activation Should Mean (and the Evidence)

2. Design Proposal & Next Quarter’s Goal

3. What to Change in Onboarding

Next Steps

Grades and run details

Decision model checks

Run

Output

1. What Activation Should Mean for Us

2. The Evidence: Where We Are Losing Users

3. What to Change in Onboarding

4. Verdict on the Design Proposal and Next Quarter's Goal

Claims the judge couldn’t find in the brief

Grades and run details

Decision model checks

Run

Check by check

Where they differ 4

All got wrong 3

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