Tasks / Strategy

1000x an idea

Can the model expand an idea's ambition while keeping it tethered to a real mechanism?

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 18 graded outputs by 9 models. 56% were usable with at most a quick edit.

Reliably right

  1. Extreme, then back to buildable100% pass
    Pushes from two-person sharing to the extreme household as the unit (any number of members, live pantry state, learning routines, delivery integration), then works back to the scoped two-person build that tests coordination.
    Haiku 5.5 · API · Sharing a shopping list, 1000x
  2. Finds the mechanism in the data100% pass
    Uses the retention, conversion, session frequency, notification triggers, note usage, and invitation context to identify shared money decisions as the core mechanism, not just budgeting.
    GPT-6.1 Sol · API · Budgets for two
  3. Respects explicit constraints97% pass
    Location tracking is not proposed this quarter and is explicitly kept behind dual opt-in; the memo stays well within 700 words and respects the team size and quarter.
    Haiku 5.5 · API · Sharing a shopping list, 1000x

Where it slips

  1. Proposes tests that could fail40% pass
    The proposed test does not name a numeric threshold for the primary outcome; it only says to set minimum detectable effects and thresholds before launch, which is a process, not a specific threshold.
    GPT-6.1 Sol · API · Budgets for two
  2. The big version gets stronger as it grows50% pass
    The memo names a demand network as a compounding mechanism but does not propose a test of whether that network effect would be large enough to matter, nor does it ask that question.
    GPT-6 Astra · ChatGPT · Sharing a shopping list, 1000x
  3. Uses the supplied evidence correctly58% pass
    The claim 'Solo budgeting runs on willpower, which fades' is a statement about the current situation not found in the supplied context and not derivable from it.
    Opus 5.5 · Claude · Budgets for two

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. The big version gets stronger as it grows

    Does the ambitious version name a mechanism that makes it more valuable or harder to copy as it grows (each new user adding value for others, or a barrier a competitor couldn't buy), and ask whether that effect would be large enough to matter?

    Passes when Names the mechanism, how it compounds with scale, and a test of whether the effect is big enough to matter.

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 · Extreme, then back to buildable · Proposes tests that could fail · and 1 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 a PM at Pocketbook. Ana has proposed shared budgets for couples; before we commit next quarter, our CEO wants the 1000x version (her note is below). Write the memo, in no more than 900 words: the most ambitious version of the idea, the mechanism that makes it work, and then what we build first and how we'll know it's working. The data is attached.

What the model was given5 items: About Pocketbook, ana_idea.md, ceo_note.md, usage_by_user_group.csv, what_shared_budgets_do.md
About PocketbookA personal budgeting app: connect your accounts, set budgets, track spending. Free, with Premium at $6 a month.
ana_idea.md3 lines · Download
# The idea (from Ana, PM)

"Let people share a budget with their partner. It's our most requested feature after bank sync for more banks."
ceo_note.md1 lines · Download
From Ruth (CEO): "Before we commit next quarter to Ana's idea, show me the 1000x version. How big could this get? Then bring it back to what we build first and how we'll know it's working. Keep it under 900 words."
usage_by_user_group.csv3 rows · Download
user_group,users,retained_at_6_months_pct,invited_someone_pct,invitee_joined_pct,premium_conversion_pct
Solo budgeters,182000,17,3,22,4
Couples sharing one budget,24600,58,100,100,19
Households (3+ people on one budget),3900,71,100,100,31
what_shared_budgets_do.md6 lines · Download
# What shared budgets do (from the data team)

- Couples who share a budget open the app on more days than solo users (11 a month against 4) and most sessions start from a notification about the other person's spending ("Alex spent $48 at the grocery store").
- 41% of couples add a "money talk" note to a transaction in their first month; the note feature was built as an afterthought.
- 16% of couples add a third person within a year (a teenager, a parent they support).
- Shared budgets started from an invite link in a shared-expenses moment (rent, a holiday) retain best.
What a strong answer doesThe answer key the graders mark against

Finds the mechanism in the data: shared money decisions, not budgeting. Couples sharing a budget retain at 58% against 17% for solo budgeters, convert to Premium at 19% against 4%, open the app on 11 days a month against 4 (mostly from notifications about the other person's spending), and use transaction notes as 'money talk'; households of 3+ retain at 71% and convert at 31%. Every shared budget brings in at least one new user by design, and 16% of couples add a third person. So the 1000x version is the place a household runs its money together (shared goals, who pays for what, conversations on transactions, extended family), growing through invitations at shared-expense moments (rent, holidays). Asks whether the effect is large enough to matter: each new member makes the budget more useful to the others, so it compounds. Works back to a first step that keeps the mechanism: shared budgets launched from an invite at a shared-expense moment, with spending notifications and transaction notes built in, measured on invites accepted, retention of invited users, and Premium conversion for couples, with thresholds.

Task

Staff-level · v1.1

The outputs

9 setups answered this brief.

Usable with a quick edit4 of 10 checks passed

The memo contains a clear vision, data-backed mechanism, and actionable first step with metrics. A PM could use it as is or after a quick edit to add contingency actions and uncertainty statements.

Output

To: Ruth, Ana From: Product Subject: The 1000x Version of Shared Budgets: Multiplayer Money

The Insight: Money Isn’t Solo, It’s Social

Right now, Pocketbook is built as a single-player calculator. And like most calculators, people stop using it: 83% of our 182,000 solo users churn within six months, and only 4% ever pay us.

When we look at the 28,500 users who have hacked Pocketbook to share a budget, the product transforms: * Retention: 6-month retention jumps from 17% (solo) to 58% (couples) and 71% (households of 3+). * Monetization: Premium conversion leaps from 4% to 19% for couples, and 31% for households. * Engagement: Couples open the app 11 days a month vs. 4 for solo users.

Why? Look at how they use it. Most sessions start from a push notification about a partner's spending ("Alex spent $48 at the grocery store"). Furthermore, 41% of couples use our buried transaction-note feature to have "money talks" in their first month.

Ana’s proposal—shared budgets for couples—captures this energy. The 1000x version recognizes that "couples" are just the entry point. Already, 16% of our couples add a third person within a year—a teenager, an aging parent, a roommate.

The 1000x Vision: The Financial Operating System for Life’s Networks

Personal finance apps assume money stops at the individual. Peer-to-peer payment apps (Venmo, Splitwise) assume shared money is a series of one-off IOUs. Neither reflects reality. In the real world, money flows through overlapping, ongoing networks of trust: couples, co-parents, roommates, siblings caring for aging parents, and friends planning a wedding.

The 1000x version of Pocketbook is Multiplayer Money: the default communication and coordination network for every shared dollar in a person’s life.

  1. From Static Ledger to Financial Messenger: The transaction feed becomes an ambient communication feed. Every swipe of a card is a message to the group, with threaded conversations, receipts, and reactions attached directly to the transaction. We replace the awkward "we need to talk about money" Sunday night spreadsheet with micro-alignments in real time.
  2. Modular Shared Spaces (Not Just One "Marriage" Budget): Users don’t merge their whole financial lives into one login. Instead, a single Pocketbook user can have a private personal budget, a "Household" space with their partner, a "Summer Trip" space with six friends, and a "Mom’s Care" space with their two siblings. Users route specific bank accounts, cards, or individual transactions into specific spaces.
  3. Moving the Money: Once we own the social layer of shared spending, we move down the stack into the payment rails. Pocketbook issues instant virtual cards for any shared space (a "Roommates Utilities" card, a "Teenager Allowance" card) and automates end-of-month settlement between connected bank accounts. We expand revenue from a flat $6 subscription to interchange fees and float.

The Mechanism That Makes It Work

This vision runs on two interlocking loops that solve our biggest weaknesses—acquisition and retention:

  • The Retention Loop (Ambient Accountability): Person A spends $\rightarrow$ Person B gets a real-time notification ("Alex spent $48 at Whole Foods") $\rightarrow$ Person B leaves a note or reaction $\rightarrow$ Person A opens the app to reply. Budgeting stops being solitary homework and becomes a daily two-way conversation.
  • The Viral Loop (Contextual Invites): Only 3% of solo users ever invite someone, and only 22% of those invitees join. Why? Nobody casually invites a friend to "try a budgeting app." But users need to invite people to split rent or track a vacation. In our data, shared budgets started from an invite link during a shared-expense moment retain best. Every shared life event becomes a high-intent acquisition wedge. And as households grow from 2 to 3+ people, each new member brings their own external networks (e.g., the teenager grows up and starts a "Roommates" space in college).

What We Build First (Next Quarter)

We shouldn't build multi-group permissions or virtual cards yet. Next quarter, we build Ana’s couples feature, architected as the wedge for Multiplayer Money. We focus on the three mechanics proven by our data:

  1. Frictionless "Shared-Moment" Onboarding: Instead of forcing two people to merge entire accounts from the settings menu, allow any user to tap a single transaction (e.g., rent, a flight, groceries) or a single budget category (e.g., "Dining Out", "Tahoe Trip") and hit "Share with Partner." This generates an SMS invite link that drops the partner directly into that transaction or category once they connect their bank.
  2. The Real-Time Spend Feed: Make partner spend notifications first-class citizens. When a partner spends in a shared category, send an instant, rich push notification with a quick-reply action so they can react or comment right from their lock screen.
  3. First-Class "Money Talks": Promote our accidental transaction-notes feature into a proper mini-chat thread on every transaction, allowing partners to tag each other, split/reassign the category, or mark it as "settled."

How We’ll Know It’s Working

within 90 days of launch, we will measure success across four gates:

  • The Viral Wedge: Solo-to-partner invite rate increases from 3% to >15%, and invitee conversion increases from 22% to >50% via contextual "Share this expense/budget" links.
  • The Engagement Engine: >50% of newly formed couples use the "Money Talk" transaction chat within their first 30 days (up from 41%), driving average active days per month to 11+.
  • Early Retention: Month-2 retention for newly formed couples tracks at >2.5x the solo user baseline (putting them on the curve toward 58%+ 6-month retention).
  • Monetization: Free-to-Premium conversion for new shared budgets hits >15% within 60 days (vs. 4% for solo users), validating that multiplayer is our primary revenue driver.

Grades and run details

Decision model 55 · LLM judge 64
Decision model checks
  • failUses the supplied evidence correctly46%
  • partialAddresses the actual decision77%
  • passRespects explicit constraints28%
  • failIdentifies material uncertainty59%
  • failAvoids unsupported claims43%
  • passProduces the required deliverable31%
  • passFinds the mechanism in the data100%
  • passExtreme, then back to buildable100%
  • partialProposes tests that could fail86%
  • partialThe big version gets stronger as it grows89%
Run
Run
#1
API response time
16 s
Submitted
13 Oct 2026

Usable with a quick edit8 of 10 checks passed

The memo is well-structured, data-driven, and actionable. The unsupported market claim can be removed with a quick edit without redoing any reasoning.

Output

Shared budgets: the 1000x version and what we build first

To: Ruth | From: PM, Pocketbook

Recommendation

Commit next quarter, but frame the work as a growth loop, not a feature. The loop is the product's invite funnel, and today it is nearly empty. The larger vision is a plausible direction, not a forecast.

The 1000x version

Pocketbook becomes where households make money decisions together, not a tool one person uses to watch their own spending.

Most financial decisions are made by more than one person: rent, holidays, supporting a parent, a teenager's first card. Today those decisions happen in texts, arguments, and spreadsheets. The ambitious version is the shared layer for that: shared budgets, shared goals, bills and "who's paying" coordination, and the conversation about money attached to the transactions themselves. Couples are the wedge. Households of three or more, such as families, adult children supporting parents, and roommates, are the expansion. Each household brings 2–4 people into the product, and every one of them is a potential Premium payer.

The mechanism

The mechanism is a two-sided engagement loop that doubles as an acquisition channel:

  1. A shared budget requires a second person, so every one is an invite.
  2. Once shared, each person's spending gives the other a reason to open the app. Most couple sessions start from a notification like "Alex spent $48 at the grocery store." Couples open the app 11 days a month versus 4 for solo users.
  3. That activity triggers conversation. 41% of couples add a "money talk" note in month one, even though we built that feature as an afterthought.
  4. Households grow. 16% of couples add a third person within a year.

A solo budgeter has to supply their own discipline every day. A shared budgeter gets reminded by someone they care about, and that is a much sturdier retention engine.

What the data says, and what it doesn't

GroupUsers6-mo retentionPremium conversion
Solo182,00017%4%
Couples24,60058%19%
Households3,90071%31%
  • Shared users are about 14% of users but roughly 45% of Premium payers (about 5,900 of 13,200 by my arithmetic).
  • The bottleneck is the invite funnel. Only 3% of solo users invite anyone, and only 22% of invitees join. That is about 0.7% of solo users becoming a shared pair. The "100%" invite and join figures for shared groups are true by definition, because those groups are defined by having shared. They are not evidence of a good funnel.
  • This is correlation. People who share a budget with a partner are probably already more motivated and more financially aligned. Some of the 58% vs 17% gap is selection, not effect. I don't know how much, and the first experiment is designed to find out.
  • Context matters. Invites started from a shared-expense moment (rent, a holiday) retain best. That suggests where to put the invite prompt.

Illustrative upside, not a forecast: if we lifted solo invite rate from 3% to 10% and join rate from 22% to 40%, we would create about 7,300 shared pairs from today's solo base, against roughly 1,200 on current rates. Even if the new pairs retain and convert at only half the gap shown above, that is material. The real rates will probably be lower because the early inviters are our most motivated users.

What we build first (next quarter)

Scope is deliberately narrow: make the existing behavior easy to start and worth returning to.

  1. Invite at the shared-expense moment. Detect rent, large recurring bills, and trip or holiday spending, and prompt "Split this budget with someone?" with a one-tap invite link.
  2. Make the invitee's first minute good. They land inside a populated budget, not an empty onboarding flow. This targets the 22% join rate.
  3. Partner activity notifications, with user controls. Keep what works and add mute and privacy settings, because "watching your partner's spending" can feel like surveillance.
  4. Promote "money talk" to threaded comments on transactions. Don't expand beyond that yet.
  5. A frictionless "add a third person" path to test the household expansion.

Not building yet: payments or transfers, kids' accounts, roommate bill-splitting, and advisor features. These are the 1000x roadmap and should be earned by the first results.

How we'll know it's working

Primary metric: share of solo users who form a shared budget where both people are active weekly at week 8. Baseline is about 0.7% formed, and I will need to establish the "both active" baseline.

The causal test: run the invite prompt as a randomized experiment, with a holdout of solo users who never see it. Compare 6-month retention and Premium conversion across the whole exposed group versus the holdout, not just those who accepted. This separates real lift from selection. Since 6-month retention is slow, use 8-week retention and Premium conversion as leading indicators and confirm at 6 months.

Supporting metrics: - Solo invite rate (3% baseline) and invitee join rate (22% baseline) - Retention and Premium conversion of newly formed pairs versus matched solo users - Third-person add rate (16% baseline over a year) - Notification mute and opt-out rate, as a guardrail on the surveillance risk

Decision rules at end of quarter: - Invite rate and join rate both move meaningfully, and the exposed group beats the holdout on 8-week retention: expand toward households and the broader vision. - Invites rise but newly formed pairs retain no better than matched solo users: the existing 58% was mostly selection, and we stop treating this as a growth engine. - Join rate stays near 22%: the problem is invitee experience or relevance, so we fix that before building more.

Open questions

  • The data shows people already sharing budgets. Before kickoff I need to confirm exactly what sharing exists today and how those 28,500 users do it, since the answer changes the scope.
  • Do shared budgets cannibalize Premium seats? Does one Premium subscription cover both people? Pricing needs a decision.
  • Sensitive cases (separated couples, financial control in abusive relationships) need design review before we push invites harder.

I'd like a go on the first-quarter scope and the holdout experiment design.

Claims the judge couldn’t find in the brief

  • Most financial decisions are made by more than one person: rent, holidays, supporting a parent, a teenager's first card.
  • Today those decisions happen in texts, arguments, and spreadsheets.

Grades and run details

Decision model 85 · LLM judge 82
Decision model checks
  • failUses the supplied evidence correctly10%
  • passAddresses the actual decision92%
  • passRespects explicit constraints33%
  • passIdentifies material uncertainty100%
  • passAvoids unsupported claims25%
  • passProduces the required deliverable35%
  • passFinds the mechanism in the data100%
  • passExtreme, then back to buildable100%
  • partialProposes tests that could fail64%
  • passThe big version gets stronger as it grows27%
Run
Run
#1
API response time
32 s
Submitted
6 Oct 2026

Usable with a quick edit9 of 10 checks passed

The memo is well-structured, uses evidence correctly, and only needs a minor edit to add a numeric success threshold for the experiment.

Output

To: Ruth From: Product Subject: Shared budgets: from feature to household money layer

The 1000x version

Don’t just let two people see the same budget. Make Pocketbook the place a household coordinates money: what’s shared, who’s responsible, what changed, and what the group wants to do next.

The product could grow from couples splitting rent or groceries to families managing bills, parents helping teenagers, and adults supporting relatives. Each person would bring in only the accounts and spending they choose to share. The household could set shared budgets and goals, see relevant activity, and discuss a transaction in context—without giving up the ability to keep other finances private.

The bigger opportunity is a financial habit, not a shared spreadsheet. A change in spending prompts a timely heads-up; people can add context or a note; the household can agree on an adjustment and see whether it’s working. Over time, Pocketbook could help households plan around bills, goals, and cash flow. Premium could offer richer household planning and controls.

Why it could work

Shared budgets appear to be associated with much stronger engagement: six-month retention is 58% for couples sharing a budget and 71% for households of three or more, versus 17% for solo budgeters. Premium conversion is 19% and 31%, respectively, versus 4% for solo users. Couples open the app 11 days a month versus four for solo users; most of their sessions start with a notification about the other person’s spending. And 41% add a “money talk” note in their first month—even though notes were built as an afterthought.

That suggests a reinforcing loop: an expense creates a useful moment to coordinate; a notification brings the other person in; context and discussion make the budget more useful; shared progress gives the household a reason to return. An invite sent during a real shared-expense moment—such as rent or a holiday—is associated with the best retention. Some couples also add a third person later, pointing to expansion beyond two-person households.

These are promising signals, not proof that sharing causes better retention or conversion: people who choose to share may already be more engaged. And the 100% invite/join figures for shared-budget groups describe people already in those groups, not a general invite-funnel benchmark.

What we build first

Start with one use case: a couple coordinating a shared expense or budget. Let one person create a shared budget and invite their partner with a link. Each person explicitly chooses which accounts or spending to share. Both can see shared-budget activity, get configurable notifications, and add a note to a transaction. Keep personal spending private by default; make it clear who can see what and allow people to mute notifications or leave the shared budget.

We should make the invite flow work in the moment of need, rather than asking solo users to make a vague “invite your partner” decision. Don’t build full household roles, complex permissions, or automated financial advice yet. First learn whether shared visibility and lightweight conversation produce a lasting joint habit.

How we’ll know it’s working

Track the funnel from shared-budget creation to invite acceptance, both people viewing shared activity, and both taking a meaningful action (for example, reviewing a transaction, adding a note, or changing a budget). Our leading indicator should be jointly active shared budgets: both members take an action in the shared budget in at least three of the first four weeks.

Use a randomized offer or holdout among eligible solo users to test whether offering shared setup improves activation and subsequent retention—not just whether people who opt in retain well. Follow six-month retention and Premium conversion, comparing like-for-like users, while monitoring privacy complaints, notification mutes, and shared-budget exits as guardrails.

If the experiment lifts joint activity and retention without eroding trust, we’ve earned the next step: support more household members and more of the financial decisions they share.

Grades and run details

Decision model 85 · LLM judge 91
Decision model checks
  • passUses the supplied evidence correctly61%
  • partialAddresses the actual decision48%
  • passRespects explicit constraints76%
  • passIdentifies material uncertainty85%
  • passAvoids unsupported claims61%
  • passProduces the required deliverable77%
  • passFinds the mechanism in the data100%
  • passExtreme, then back to buildable100%
  • partialProposes tests that could fail77%
  • partialThe big version gets stronger as it grows92%
Run
Run
#1
API response time
16 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 6

Uses the supplied evidence correctlyMixedWrongRight
Gemini 4 Argon · API

All factual statements about the current situation come directly from the supplied data, with no invented numbers or facts.

Sonnet 5.5 · API

The output claims as fact that 'Most financial decisions are made by more than one person' and that 'Today those decisions happen in texts, arguments, and spreadsheets,' neither of which appears in the supplied context or follows from it.

GPT-6 Luna · API

All factual claims about the current situation are directly supported by the supplied data or context.

Addresses the actual decisionWrongRightRight
Gemini 4 Argon · API

The memo does not say what result or condition would change the commitment; it lists success gates but doesn't link them to a pivot or kill decision.

Sonnet 5.5 · API

The memo commits to 'Commit next quarter' early, frames it for Ruth, and provides decision rules that would change the call based on experiment results.

GPT-6 Luna · API

The memo commits to a clear first step and measurement plan, and states that a positive experiment result earns the next step.

Identifies material uncertaintyWrongRightRight
Gemini 4 Argon · API

The memo does not name any unknowns that could change the decision, nor how they would be resolved.

Sonnet 5.5 · API

It explicitly names selection vs. causation, the invite funnel bottleneck, unknown sharing mechanics, pricing cannibalization, and sensitive cases, and says the experiment will resolve the key uncertainty.

GPT-6 Luna · API

It explicitly notes that the data is correlational, not proof of causation, and proposes a randomized experiment to resolve the uncertainty.

Avoids unsupported claimsMixedMixedRight
Gemini 4 Argon · API

No claims are presented as established fact when the evidence only suggests them; causal interpretations are labelled or supported by the data.

Sonnet 5.5 · API

The statements about most financial decisions being made by more than one person and happening in texts/arguments/spreadsheets are presented as established fact without support from the supplied evidence.

GPT-6 Luna · API

Hypotheses and interpretations are clearly labeled with words like 'suggests' and 'may', avoiding presenting them as established fact.

Proposes tests that could failWrongRightWrong
Gemini 4 Argon · API

The success gates list thresholds and some time windows, but do not state what action (stop, pivot, invest) would follow if the thresholds are missed.

Sonnet 5.5 · API

The randomized holdout experiment has a numeric threshold (exposed beats holdout on 8-week retention), a measurement window (8 weeks, confirmed at 6 months), and clear actions for each outcome (expand, stop treating as growth engine, fix invitee experience).

GPT-6 Luna · API

The randomized experiment's success condition ('lifts joint activity and retention') lacks a numeric threshold, so it does not fully specify a test that could fail.

The big version gets stronger as it growsWrongRightRight
Gemini 4 Argon · API

The memo describes a compounding mechanism (new members bring their networks) but does not explicitly ask whether that effect would be large enough to matter, nor propose a test to quantify it.

Sonnet 5.5 · API

It names the mechanism (each shared budget requires an invite, activity triggers more engagement, each new user adds value) and asks whether the effect is large enough to matter via the experiment and illustrative upside.

GPT-6 Luna · API

It names the reinforcing loop mechanism, implies it compounds as more people join, and proposes an experiment to test if the effect is large enough to matter.

All got right 4

Respects explicit constraintsRightRightRight
Gemini 4 Argon · API

The output is a memo under 900 words, addressed to Ruth and Ana, and includes the asked-for sections.

Sonnet 5.5 · API

The output is a memo to Ruth, under 900 words, and addresses the requested elements (ambitious version, mechanism, first step, success metrics).

GPT-6 Luna · API

The memo is addressed to Ruth, under 900 words, and includes the 1000x version, mechanism, first build, and success metrics as requested.

Produces the required deliverableRightRightRight
Gemini 4 Argon · API

A complete memo with vision, mechanism, first step, and success metrics is provided, usable by the CEO and Ana.

Sonnet 5.5 · API

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

GPT-6 Luna · API

The memo is complete, in the correct form for the CEO, within the word limit, and actionable as written.

Finds the mechanism in the dataRightRightRight
Gemini 4 Argon · API

The memo uses the data on notifications, transaction notes, and shared-expense invites to define the mechanism, showing it is about shared money decisions, not just budgeting.

Sonnet 5.5 · API

It cites the retention, conversion, notification, note, and shared-expense data to identify the mechanism as a two-sided engagement loop around shared money decisions, not just budgeting.

GPT-6 Luna · API

It cites the retention, conversion, notification, and note data to identify a reinforcing loop around shared money decisions, not just budgeting.

Extreme, then back to buildableRightRightRight
Gemini 4 Argon · API

The memo pushes to an extreme 'multiplayer money' vision and then works back to a buildable first step (couples feature with shared-moment onboarding, notifications, notes) that tests the same mechanism.

Sonnet 5.5 · API

It pushes to 'where households make money decisions together' and then works back to a concrete first step (invite at shared-expense moment, notifications, money talk, add third person) that tests the same mechanism.

GPT-6 Luna · API

It pushes to a household money layer and then works back to a concrete first step (couple coordinating a shared expense) that tests the same mechanism.

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 91% of 118 checks.

#Model · HarnessTask scoreDecision modelLLM judgeRunsCritical failures
1Haiku 5.5withAPI83.0100.02None
2GPT-6 AstrawithChatGPT90.591.32None
3GPT-6.1 SolwithAPI90.587.12None
4Opus 5.5withClaude93.078.42None
5GPT-6 LunawithAPI85.783.02None
6Sonnet 5.5withAPI88.074.22None
7Gemini 4 ArgonwithAPI54.856.82None
8Gemini 3.8 FlashwithAPI54.339.02None
9Gemini 3.5 Flash-LitewithGemini54.834.82None

What you get for the cost

No setup scores within 5 points of the leader at half its cost or less here, so the leader is also the best value.

Task score against relative cost for each setup. The table below has the same figures.304050607080901001×3×10×30×Cost per output, relative to the cheapest setup (log scale) →↑ Task scoreHaiku 5.5 · API: task score 92, 2.1× the cheapestGPT-6 Astra · ChatGPT: task score 91, 74× the cheapestGPT-6.1 Sol · API: task score 89, 15× the cheapestOpus 5.5 · Claude: task score 84, 59× the cheapestGPT-6 Luna · API: task score 83, the cheapestSonnet 5.5 · API: task score 80, 31× the cheapestGemini 4 Argon · API: task score 56, 14× the cheapestGemini 3.8 Flash · API: task score 44, 9.1× the cheapestGemini 3.5 Flash-Lite · Gemini: task score 42, 2.9× the cheapestHaiku 5.5 · APIGPT-6 Astra · ChatGPTGPT-6.1 Sol · APIOpus 5.5 · ClaudeGPT-6 Luna · APISonnet 5.5 · APIGemini 4 Argon · APIGemini 3.8 Flash · APIGemini 3.5 Flash-Lite · Gemini
Nobody beats these on both score and cost
Task score and relative cost by setup
SetupTask scoreRelative cost (cheapest = 1)
GPT-6 Luna · API831.0×
Haiku 5.5 · API922.1×
Gemini 3.5 Flash-Lite · Gemini422.9×
Gemini 3.8 Flash · API449.1×
Gemini 4 Argon · API5614×
GPT-6.1 Sol · API8915×
Sonnet 5.5 · API8031×
Opus 5.5 · Claude8459×
GPT-6 Astra · ChatGPT9174×

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

About the task

The PM job

Finding the bigger version of a good idea.

Why it matters

Ambition without mechanism is fan fiction. The useful version pushes to the extreme, then works back to something buildable.

What good looks like

  • Names the mechanism that scales
  • Keeps the core insight
  • Works back to a first step you could build

Deliberately not measured

    Capability tested

    Ambitious expansion

    The failure we’re looking for

    Bigger adjectives, same idea

    Grading

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