Tasks / Challenge

1000x an idea

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

Measures the systemTask v1.0 · 2 casesDifficulty

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

From 14 graded outputs by 7 models. 36% were usable with at most a quick edit.

Reliably right

  1. Extreme, then back to buildable96% pass
    It pushes the worker dimension to an extreme portable earnings network, then works back to a concrete first step that tests the same mechanism.
    GPT-6 Astra · ChatGPT · From tip calculator to worker network
  2. Finds the mechanism the data hides93% pass
    It centers the mechanism on workers with second jobs pulling new restaurants onto Tally, using the 41% second-job share and the 57 faster, cheaper worker-led signups.
    GPT-6 Astra · ChatGPT · From tip calculator to worker network
  3. Addresses the actual decision91% pass
    It commits early to the worker-led distribution thesis over the AI operating system and states the result that would stop the bet.
    GPT-6 Astra · ChatGPT · From tip calculator to worker network

Where it slips

  1. Proposes tests that could fail39% pass
    Several gates lack explicit measurement windows or clear actions for every outcome, such as the 25% lift gate and the 10% monthly adoption gate.
    GPT-6.1 Sol · API · From tip calculator to worker network
  2. Avoids unsupported claims63% pass
    It presents several causal, competitive, and data-structure claims as established facts without support in the pack.
    Sonnet 5.5 · API · From tip calculator to worker network
  3. Respects explicit constraints66% pass
    It violates the length constraint and proposes a stop threshold whose arithmetic is internally inconsistent.
    Sonnet 5.5 · API · From tip calculator to worker network

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

You're a PM at Pantry. Aisha, one of our PMs, has proposed letting people share a shopping list with one partner. Before we commit next quarter to it, our CEO, Lena Brandt, wants to see the 1000x version: how big could this idea get? Write a memo for Lena and Aisha of no more than 700 words that takes the idea to its most ambitious version and then back to what we should build first, and how we'll know it's working. What we know is below.

What the model was given5 items: About Pantry, Aisha's proposal, What we already see, What hasn't worked, Constraint
About PantryA shopping-list app. 2.4 million monthly active users, free, with a $4.99-a-month Plus plan that 3% of users pay for. The team for this work: four engineers and a designer, for one quarter.
Aisha's proposal“Let a user invite one partner to a list. Both can add and tick off items.”
What we already seeSome users already share their login with a partner to get the same effect. Lists edited from two or more devices on different phone numbers: 11% of lists. Users whose list is edited from two or more devices keep using Pantry at month 3 at 71%, against 22% for everyone else. On those lists, 38% of items are added by the second device. The most common support request is 'we both bought the milk': 1,900 tickets last quarter about duplicate purchases.
What hasn't workedRecipes and meal plans launched a year ago; 4% of users have opened them in the last month. Lena's note: “Whatever we do, it probably needs AI in it.”
ConstraintLegal: we can't track anyone's location without an explicit opt-in from that person, and we can't show one person's location to another without the second person's opt-in too.
What a strong answer doesThe answer key the graders mark against

Finds the mechanism in the data: the value is several people coordinating one household's shopping (71% against 22% month-3 retention when a list is edited from two devices, 38% of items added by the second person, 1,900 duplicate-purchase tickets), not the list itself and not recipes (4% use them). Pushes that one dimension to the extreme, such as the list as the household's shared memory where everyone's needs flow in, nobody double-buys and each errand goes to whoever is best placed (with location only on opt-in from both people), rather than adding AI features for their own sake. Works back to a first step four engineers can ship in a quarter that tests the coordination mechanism: shared lists for the whole household (not just one partner) with a live 'I'm at the shop' claim so items aren't bought twice. Sets a threshold, such as the share of lists with a second active editor and duplicate-purchase tickets per shared list, and says what result would stop the bigger bet. Uses AI only where it serves coordination, if at all.

Critical failures (cap the score at 40)
  • Builds the ambitious version on recipes, meal plans or AI for one person, dropping household coordination
  • Proposes tracking or sharing a person's location without their explicit opt-in
Case

Mid-level · v1.1 · synthetic · B2C, consumer app, retention, ambition

The outputs

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

Needs more than a quick edit9 of 10 checks passed

The memo is strong and actionable, but the invented current-workflow sentence would need to be removed or grounded before use.

Output

To: Lena Brandt and Aisha Subject: From shared lists to the coordination layer for household shopping

The 1000× version

Aisha’s proposal is not just multiplayer checkboxes. It could be the first step toward Pantry becoming the place a household coordinates everything it needs to buy.

Today, each person remembers needs, sends messages, shops, and discovers what someone else already bought. At full ambition, Pantry turns that fragmented process into one shared system: what we need, what we already have, who is handling it, and what remains undone.

An item might begin as a voice note, a pasted message, or a recurring household need. Pantry organizes it, flags likely duplicates, and—with permission—learns when to suggest replenishment. Households could eventually include roommates, caregivers, and extended family. Later, Pantry could connect that shared intent to retailer carts, substitutions, and delivery, while leaving purchasing decisions with users.

The business could expand from a personal utility into household subscriptions and, eventually, commerce revenue. But those opportunities depend on earning trust in coordination first. This is a direction, not a forecast of 1,000× revenue.

Why this wedge—not another content feature

We already see people working around the product by sharing credentials. Eleven percent of lists are edited across devices with different phone numbers; second devices contribute 38% of items on those lists. This looks like substantive participation, not occasional viewing.

Multi-device users’ month-three retention is 71%, versus 22% for others. That is evidence of opportunity, not proof that sharing causes retention: more committed households may already be selecting into this behavior. Likewise, 11% of lists does not mean 11% of users.

The clearest unmet need is concrete: 1,900 duplicate-purchase tickets last quarter. Meanwhile, recipes and meal plans reach only 4% of users monthly. We should deepen Pantry’s existing shopping workflow rather than build another destination users must remember to visit.

What we should build next quarter

With four engineers and one designer, ship one list, two separate accounts, reliable coordination:

  • Invite one partner through a secure link; accept, leave, and revoke access.
  • Both people can add and check off items, with clear attribution.
  • Fast synchronization, offline recovery, and predictable handling of simultaneous edits.
  • A lightweight “I’m buying this” claim, visible to both people, with easy release. Checking an item off means purchased; claiming it means someone is handling it.
  • Help existing credential-sharing households move to separate accounts.

Make basic sharing free: charging before establishing the collaboration habit would constrain adoption. Defer larger groups, inventory, retailer integrations, and monetization experiments.

AI belongs in service of the job, not in the launch headline. Test a small, optional assistant that converts pasted household messages into proposed list items and flags likely duplicates. Users confirm every change. Ship it only if it saves effort without introducing meaningful mistakes; it must not delay the coordination core.

No location tracking is needed. “I’m buying this” is an explicit action, not an inferred whereabouts signal. Any future location feature must require the explicit opt-ins Legal specifies, including both people’s consent before sharing location.

How we’ll know it works

Instrument household participation, claims, purchases, synchronization failures, and reported duplicates. Do not treat invitation volume as success.

Run a randomized rollout, keeping collaborating accounts in the same experiment group. Analyze by assignment, not only among people who accept invitations.

Proposed decision gates, to validate against baseline and statistical power:

  • At least a 10% relative improvement in day-30 retention versus control.
  • At least half of activated pairs still have both people contributing in week four.
  • At least a 25% reduction in self-reported duplicate purchases among activated pairs.
  • No material deterioration in list reliability, privacy incidents, or support burden.

Report month-three retention when cohorts mature; a quarter-end readout cannot establish it for late adopters. Scale only if Pantry makes two people’s shopping measurably easier—not merely more shareable.

Claims the judge couldn’t find in the brief

  • Pantry has 2.4 million monthly active users, free, with a $4.99-a-month Plus plan that 3% of users pay for.
  • Today, each person remembers needs, sends messages, shops, and discovers what someone else already bought.

Grades and run details

Decision model 90 · LLM judge 9 of 11 checks
Decision model checks
  • passUses the supplied evidence correctly57%
  • passAddresses the actual decision88%
  • partialRespects explicit constraints25%
  • passIdentifies material uncertainty92%
  • passAvoids unsupported claims57%
  • passProduces the required deliverable26%
  • passFinds the mechanism in the data99%
  • passA first step that tests the big idea88%
  • passExtreme, then back to buildable97%
  • partialProposes tests that could fail69%
Run
Run
#1
API response time
45 s
Submitted
1 Oct 2026

Needs more than a quick edit0 of 10 checks passed

A PM would need to correct unsupported evidence, replace the one-partner first step with a household-coordination test, and add explicit stop/continue thresholds. The reasoning is not usable without substantive revision.

Output

MEMORANDUM

To: Lena Brandt (CEO), Aisha (PM) From: Product Management Date: March 30, 2026 Subject: The 1000x Vision & Q3 Execution Plan: Household Graph

Lena asked for the 1000x version of Aisha’s "share with one partner" proposal. Here is how we take a simple list-sharing feature and turn it into the gravitational core of household commerce, followed by what we actually build in Q3 with our 4 engineers and 1 designer.

---

Part 1: The 1000x Vision (The Household OS)

If we zoom out to the ultimate limit, a shopping list isn’t a list of items—it’s the intent layer for the physical household.

At 1000x, Pantry is no longer an app you open when you run out of milk. It is an ambient, AI-driven household operating system. * Zero-Input Inventory: Using explicit-opt-in location data, smart home integrations, and receipt-scanning AI, Pantry automatically knows when you’re low on detergent, that you visited Costco yesterday, and that your partner is currently walking past the local bodega where organic eggs are in stock. * Predictive Autonomous Commerce: The AI doesn't just prevent duplicate milk purchases (our #1 support ticket); it predicts consumption velocity across the household, negotiates micro-subscriptions with local merchants, and routes optimized fulfillment paths without either partner lifting a finger.

We aren't building a shared document. We are building the decentralized brain of the home economy.

---

Part 2: What We Build in Q3 (The 1x Reality)

We have one quarter, four engineers, and a designer. We aren't building the 1000x sci-fi version yet, but the data screams that Aisha’s core premise is our highest-leverage bet.

Look at what’s already happening organically: * 11% of lists are already hacked together via password sharing across multiple devices. * Retention is staggering: Multi-device users have a 71% Month 3 retention rate, compared to just 22% for solo users. * True collaboration: 38% of items on those lists are added by the second device. * Pain is acute: 1,900 support tickets last quarter alone for "we both bought the milk."

We don't need a massive pivot (recipes failed because users don't want to plan meals; they want to survive the grocery run). We just need to formalize the behavior our best users have already invented.

#### The Q3 Scope: "Pantry Duo + AI Sync" 1. Frictionless Pairing: Allow a user to invite one partner via a secure link to co-own a list. Both can add and check off items in real time. 2. AI Duplicate Guard: Per Lena’s mandate, we embed lightweight AI into the sync layer. If Partner A checks off "milk" or adds an item already added by Partner B within a threshold window, the UI flags it instantly with a smart nudge ("Looks like Sam just added this!"), targeting our 1,900 duplicate-purchase tickets. 3. Privacy Compliance: Built strictly within our legal constraints—no background location tracking without explicit, dual-opt-in consent.

---

Part 3: How We Know It’s Working

We will measure success in Q3 against three core metrics:

  1. Adoption: 20% of active users invite a partner within 30 days of launch.
  2. The Retention Lift: Multiplying our multi-device magic. If the 71% M3 retention holds for formal Duo pairs, this feature alone will dramatically alter Pantry's baseline unit economics.
  3. Support Deflection: A 50% drop in "duplicate purchase" support tickets.
  4. Plus Conversion: Do shared households convert to our $4.99/mo Plus plan at a higher rate than solo users? (We suspect shared utility drives higher willingness to pay).

Aisha’s proposal is the exact right wedge. Let’s build it in Q3 and lay the groundwork for the household graph.

Claims the judge couldn’t find in the brief

  • 11% of lists are already hacked together via password sharing across multiple devices.
  • Multi-device users have 71% Month 3 retention, compared to 22% for solo users.
  • Recipes failed because users don’t want to plan meals; they want to survive the grocery run.

Grades and run details

Decision model 50 · LLM judge 1 of 11 checks
Decision model checks
  • passUses the supplied evidence correctly15%
  • partialAddresses the actual decision58%
  • partialRespects explicit constraints31%
  • partialIdentifies material uncertainty33%
  • failAvoids unsupported claims40%
  • failProduces the required deliverable36%
  • partialFinds the mechanism in the data60%
  • partialA first step that tests the big idea73%
  • passExtreme, then back to buildable55%
  • partialProposes tests that could fail58%
Run
Run
#1
Time to output
5 s
Submitted
1 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 9

Addresses the actual decisionRightWrong
GPT-6.1 Sol · API

It commits to a clear first build (one list, two separate accounts, reliable coordination) and states the decision gates that would change the answer.

Gemini 3.5 Flash-Lite · Gemini

It commits to building Duo + AI Sync but does not state what result would change the decision or stop the bigger bet.

Respects explicit constraintsRightWrong
GPT-6.1 Sol · API

It respects the legal location constraint, the team/quarter constraint, and the memo form/length.

Gemini 3.5 Flash-Lite · Gemini

It respects the word limit and team constraint, but its proposed location-based vision does not clearly enforce the dual opt-in requirement for showing one person’s location to another.

Identifies material uncertaintyRightWrong
GPT-6.1 Sol · API

It names selection bias, the lists-vs-users denominator, and the need for randomized rollout and mature cohorts, with gates to resolve them.

Gemini 3.5 Flash-Lite · Gemini

It names metrics but not the material unknowns that could falsify the household-coordination bet, nor how those unknowns would change the call.

Avoids unsupported claimsRightWrong
GPT-6.1 Sol · API

It labels causal uncertainty and future possibilities as hypotheses or directions rather than established facts.

Gemini 3.5 Flash-Lite · Gemini

It presents unsupported causal and comparative claims as facts, including recipe failure motivation and solo-user retention.

Produces the required deliverableRightMixed
GPT-6.1 Sol · API

It is a memo for Lena and Aisha, under 700 words, and actionable as written.

Gemini 3.5 Flash-Lite · Gemini

It is a memo to Lena and Aisha, under 700 words, with a 1000x vision, first step, and metrics, though with gaps.

Finds the mechanism in the dataRightWrong
GPT-6.1 Sol · API

It centers household coordination and uses the supplied retention, second-device item share, and duplicate-ticket evidence.

Gemini 3.5 Flash-Lite · Gemini

It uses the coordination figures but centers the first step on one-partner sharing and an AI duplicate guard rather than household-wide coordination as the mechanism.

A first step that tests the big ideaRightWrong
GPT-6.1 Sol · API

The first step is scoped to four engineers and a designer in a quarter and directly tests the coordination mechanism.

Gemini 3.5 Flash-Lite · Gemini

The first step is buildable but tests one-partner list sharing and duplicate nudges, not the broader household-coordination mechanism needed to validate the 1000x bet.

Extreme, then back to buildableRightMixed
GPT-6.1 Sol · API

It pushes the idea to a household coordination layer, then works back to a buildable first step with the same mechanism.

Gemini 3.5 Flash-Lite · Gemini

It pushes to an extreme household OS but then returns to a narrower one-partner feature that does not preserve the same household-coordination mechanism.

Proposes tests that could failRightWrong
GPT-6.1 Sol · API

Each gate has a numeric threshold, a measurement window, and a clear continue/stop implication.

Gemini 3.5 Flash-Lite · Gemini

It gives numeric thresholds for adoption, retention, support deflection, and conversion, but no measurement windows for all, no kill criteria, and no actions for failing thresholds.

All mixed 1

Uses the supplied evidence correctlyMixedMixed
GPT-6.1 Sol · API

The memo invents a current-situation workflow ('Today, each person remembers needs, sends messages, shops, and discovers...') that is not in the supplied context.

Gemini 3.5 Flash-Lite · Gemini

The memo misstates the 11% figure as password-sharing hacks, calls the 22% comparison group solo users, and asserts an unsupported cause for recipe failure.

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 89% of checks.

#Model · HarnessTask scoreDecision modelLLM judgeRunsCritical failures
1GPT-6 AstrawithChatGPT95.295.52None
2GPT-6.1 SolwithAPI92.786.72None
3GPT-6 LunawithAPI88.278.82None
4Opus 5.5withClaude90.774.62None
5Sonnet 5.5withAPI90.265.92None
6Gemini 3.8 FlashwithAPI71.134.521 capped
7Gemini 3.5 Flash-LitewithGemini61.417.02None

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

    This task measures the whole setup. Tools, instructions and skills in the harness do real work here, so read the harness as carefully as the model name.