Tasks / Design

Activation & onboarding review

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

Measures the modelTask v1.1 · 2 casesDifficulty

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

From 14 graded outputs by 7 models. 50% were usable with at most a quick edit.

Reliably right

  1. Activation defined by what predicts retention100% pass
    Defines activation as three workouts linked to day-60 retention, and evaluates fixes by effect on that event.
    GPT-6 Astra · ChatGPT · Fitness app first week
  2. Prioritises by impact98% pass
    Ranks changes by likely impact on achieving three workouts, aligned with the identified activation threshold.
    GPT-6 Astra · ChatGPT · Fitness app first week
  3. Produces the required deliverable93% pass
    Provides a complete, actionable memo that a growth PM could implement without major gaps.
    GPT-6 Astra · ChatGPT · Fitness app first week

Where it slips

  1. Avoids unsupported claims54% pass
    It presents causal or evaluative claims such as 'successful connection is the gateway' and 'a required technical connection is an especially poor first step' as established fact rather than hypothesis.
    GPT-6 Luna · API · Analytics tool losing users at setup
  2. Uses the supplied evidence correctly54% pass
    It includes an unsupported motivation claim and a miscomputed '4% of trial starters' figure, so not every current-situation statement is supported by the brief or arithmetic.
    Sonnet 5.5 · API · Fitness app first week
  3. Identifies material uncertainty59% pass
    Identifies the lack of step-level data but does not state what result would change the call or how it would affect the ranking.
    Opus 5.5 · Claude · Analytics tool losing users at setup

Case viewer

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

Review our onboarding flow and funnel below. Write a memo to the onboarding squad saying where we are losing people and what to fix, in the order you would fix it, with the reason for each. Keep it under 500 words.

What the model was given4 items: Scenario, Funnel (last 90 days, 12,400 signups), Onboarding flow, screen by screen, Support
ScenarioChartwise is a self-serve product-analytics tool. Most people who sign up are product managers or marketers, not data engineers. Pricing starts at $49 a month after a 14-day free trial.
Funnel (last 90 days, 12,400 signups)Signup 100% → Connect data source 41% → First chart 33% → Invite teammate 9%. Week-2 retention: 62% for users who reach a first chart, 11% otherwise.
Onboarding flow, screen by screen1. Sign up: email, password, company name. 2. Verify email: the flow pauses until the link is clicked. 3. “What's your role?” (seven options). 4. “How big is your team?” (five options). 5. Connect your data: choose Postgres, BigQuery, Snowflake or CSV upload. There is no sample data and no skip. 6. Connection form: host, port, database, username, password and SSL mode. The help link opens a 14-page setup guide. 7. Choose tables: a list of every table in the database. 8. Syncing: a progress bar that can take up to 20 minutes; leaving the page cancels the sync. 9. Pick a dashboard template (twelve options). 10. First chart: a chart builder with an empty canvas. 11. Invite teammates: email fields, with a “Skip for now” link.
SupportThe most common onboarding ticket (41% of them) is some version of “I don't have the database credentials.” The next is “my sync failed” (18%).
What a strong answer doesThe answer key the graders mark against

The data-source connection step (screens 5–8) is the activation bottleneck; prioritise a sample-data or CSV-first path to a first chart, then non-admin credential handoff and a sync that survives leaving the page, ahead of cosmetic fixes.

Case

Mid-level · v1.8 · anonymised real · B2B SaaS, data

The outputs

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

Needs more than a quick edit4 of 9 checks passed

The output misinterprets the support ticket data as a user proportion and presents unsupported causal claims, so a PM would need to re-check the evidence before using it.

Output

To: Onboarding Squad Subject: Fixing Our Activation Funnel: Priorities & Action Plan

Where We Are Losing People

Our biggest drop-off occurs at Step 5–8 (Connect Data): 59% of signups leave without connecting a data source.

We are asking PMs and marketers for database ports, SSL modes, and passwords they do not possess. 41% of our support tickets are “I don't have credentials,” followed by 18% for failed syncs. Furthermore, requiring a 20-minute, open-tab sync kills momentum.

Because Week-2 retention jumps from 11% to 62% once a user builds their first chart, our sole objective is getting non-technical users to that "aha!" moment in under two minutes.

---

What to Fix (In Priority Order)

#### 1. Add “Explore with Sample Data” & a Clear “Skip” Button (Step 5) * What: Let users bypass database connection entirely using a fully populated e-commerce or SaaS demo dataset. * Why: This is the highest-leverage fix. It immediately unblocks the 59% who drop off at Step 5 and the 41% who lack DB credentials, giving them an instant path to create a first chart and experience the product’s value on Day 1.

#### 2. Introduce “Invite a Data Teammate” at Connection (Step 6) * What: Add a 1-click option: “Don't have credentials? Send an invite link to your data lead to connect your warehouse.” * Why: Replaces a dead end with collaboration. The PM stays in the app using sample data while the engineer handles credentials asynchronously.

#### 3. Make Syncing Asynchronous (Step 8) * What: Run syncing in the background. Notify users via email/in-app alert when ready instead of forcing them to keep a 20-minute tab open. * Why: Directly addresses our second-biggest support issue (18% sync failures/cancellations) and eliminates the drop-off caused by tab abandonment.

#### 4. Pre-Populate the Dashboard; Kill the Blank Canvas (Steps 9 & 10) * What: When a user selects a template, generate it automatically with 3–4 standard charts instead of dropping them onto an empty canvas. Prompt them to tweak one existing chart. * Why: Bridges the 8% drop-off between connecting data (41%) and creating a first chart (33%). Editing an existing chart is far lower friction than building from scratch.

#### 5. Defer Email Verification and Profiling Questions (Steps 2, 3, & 4) * What: Move verification to a non-blocking banner at the top of the app, and cut or defer the role/team-size questions until after the user creates their first chart. * Why: Every barrier before core value reduces trial-to-paid conversion. Let users reach the product before demanding administrative tasks.

---

Next Step

Let’s implement Priority 1 (Sample Data) this sprint. It requires zero infrastructure changes to our warehouse sync logic and directly targets our biggest activation leak.

Claims the judge couldn’t find in the brief

  • Requiring a 20-minute, open-tab sync kills momentum.
  • The 41% who lack DB credentials (as a proportion of users).
  • The drop-off caused by tab abandonment.

Grades and run details

Decision model 72 · LLM judge 4 of 10 checks
Decision model checks
  • failUses the supplied evidence correctly22%
  • passAddresses the actual decision93%
  • passRespects explicit constraints40%
  • failIdentifies material uncertainty99%
  • partialAvoids unsupported claims39%
  • passProduces the required deliverable96%
  • passPrioritises by impact98%
  • passActivation defined by what predicts retention100%
  • passGets the base of every number right44%
Run
Run
#1
API response time
21 s
Submitted
1 Oct 2026

Usable with a quick edit6 of 9 checks passed

The evidence and priorities are usable, but it needs a sentence stating what would change the order and softer labelling of causal claims; no re-checking or redoing of the reasoning is needed.

Output

To: Onboarding Squad Subject: Where onboarding is leaking—and what to fix first

The biggest loss is before a data source is connected: only 41% of signups get that far. Another 8 percentage points drop before a first chart. Just 9% of signups invite a teammate. The strongest activation signal is the chart: week-2 retention is 62% for users who reach one, versus 11% for those who don’t. Prioritize getting people to a useful chart; treat invites as a later step.

Fixes, in priority order

  1. Offer a sample-data path that reaches a real first chart. Let users skip connecting their own data and explore a preloaded dataset, with a clear route to connect later. Many signups are PMs and marketers, and the most common onboarding ticket is missing database credentials (41%). A required technical connection is an especially poor first step for them. This also gives users value while they wait for access.
  1. Make connecting data simpler and recoverable. Replace or supplement the 14-page guide with short, connector-specific instructions and troubleshooting. Validate credentials early, explain the required access, and offer a clear retry path. Don’t cancel a sync when someone leaves the page; send progress and failure notices and let users resume. The credential and sync tickets point to concrete blockers, and successful connection is the gateway to the high-retention chart experience.
  1. Get users to a chart with fewer decisions. Replace the database-wide table list with suggested tables and plain-language descriptions; cut the 12 dashboard templates to a few recommended starting points. Provide a prebuilt chart or guided first-chart flow rather than an empty canvas. The 8-point drop between connection and first chart, plus the sync burden, suggests too much work remains after connection.
  1. Remove early friction that doesn’t create value. Test deferring email verification until after users enter the product, and move role/team questions until they can personalize something useful. These steps currently delay access before users see value.
  1. Make inviting a teammate contextual, not a hurdle. Keep it optional; prompt after a user has made or shared a chart, and explain the benefit. Only 9% of signups invite someone, but chart reach—not inviting—is the clearest retention signal.

Track step conversion and time-to-first-chart by path, especially sample-data versus live connection, before expanding the changes.

Grades and run details

Decision model 89 · LLM judge 7 of 10 checks
Decision model checks
  • passUses the supplied evidence correctly33%
  • passAddresses the actual decision98%
  • passRespects explicit constraints71%
  • partialIdentifies material uncertainty65%
  • partialAvoids unsupported claims48%
  • passProduces the required deliverable97%
  • passPrioritises by impact99%
  • passActivation defined by what predicts retention100%
  • passGets the base of every number right79%
Run
Run
#1
API response time
12 s
Submitted
29 Sept 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 2

Uses the supplied evidence correctlyWrongRight
Gemini 3.8 Flash · API

The output presents 'the 41% who lack DB credentials' as a user proportion, which is not supported by the ticket share data, and states 'kills momentum' and 'drop-off caused by tab abandonment' as facts without evidence.

GPT-6 Luna · API

All factual statements about the current situation are taken correctly from the brief and supplied context, with no invented facts.

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

The output misstates the 41% support-ticket share as a proportion of users lacking credentials, getting the base wrong.

GPT-6 Luna · API

All percentages use the correct denominators, and the 41% ticket figure is understood as a share of onboarding tickets rather than users.

All got wrong 2

Identifies material uncertaintyWrongWrong
Gemini 3.8 Flash · API

No unknowns are named, and the output does not discuss what could change the decision or how to resolve uncertainty.

GPT-6 Luna · API

It does not name specific unknowns that could change the priorities or say how resolving them would alter the call.

Avoids unsupported claimsWrongWrong
Gemini 3.8 Flash · API

Interpretations like 'kills momentum', 'the 41% who lack DB credentials' as a user share, and 'drop-off caused by tab abandonment' are presented as established facts without labelling them as hypotheses.

GPT-6 Luna · API

It presents causal or evaluative claims such as 'successful connection is the gateway' and 'a required technical connection is an especially poor first step' as established fact rather than hypothesis.

All mixed 1

Addresses the actual decisionMixedMixed
Gemini 3.8 Flash · API

The output does not state what result or condition would change the prioritised order, failing the requirement to say what would change the answer.

GPT-6 Luna · API

The memo commits to a clear ranked order but never states what result or condition would change that order; the closing sentence is only about expanding changes.

All got right 4

Respects explicit constraintsRightRight
Gemini 3.8 Flash · API

The memo is under 500 words, addressed to the onboarding squad, and provides a ranked list with reasons.

GPT-6 Luna · API

It is a memo to the onboarding squad, well under 500 words, and respects the requested form and reader.

Produces the required deliverableRightRight
Gemini 3.8 Flash · API

The output is a complete memo with the requested structure, reader, and length, and a PM could act on it with light edits.

GPT-6 Luna · API

The required memo is complete, actionable, and usable by the onboarding squad as written or with light edits.

Prioritises by impactRightRight
Gemini 3.8 Flash · API

Fixes are ranked by likely impact on activation, starting with the biggest drop-off and linking to the retention-driving first chart.

GPT-6 Luna · API

Fixes are ranked by likely impact on reaching a first chart, tied to the retention signal.

Activation defined by what predicts retentionRightRight
Gemini 3.8 Flash · API

The output defines activation as building a first chart, cites the retention difference (11% vs 62%), and ranks fixes by their effect on reaching that event.

GPT-6 Luna · API

It names first chart as the activation behaviour based on 62% vs 11% retention and ranks fixes by their effect on it.

Results

Every setup we’ve tested on this task, across all cases and repeats, graded on the current checklist. Calibrated: the graders match our PM on 82% of checks.

#Model · HarnessTask scoreDecision modelLLM judgeRunsCritical failures
1GPT-6.1 SolwithAPI100.0100.02None
2GPT-6 AstrawithChatGPT94.4100.02None
3GPT-6 LunawithAPI94.485.02None
4Opus 5.5withClaude80.665.02None
5Gemini 3.5 Flash-LitewithGemini69.455.02None
6Sonnet 5.5withAPI77.845.02None
7Gemini 3.8 FlashwithAPI69.450.02None

About the task

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