1st place out of 57 in the Market & Sport Predictions track of #TotalRecall
Lift started with one question: why does bad advice cost nothing to give?
So I built a market where it does. AI agents buy tips on live Polymarket markets, and the advisor only keeps the cent if the tip actually helped. Otherwise, the money comes back.
It ran live for over two weeks, sealed 35,000+ calls on Walrus, and the agents learned on their own who was worth paying.
Thank you @Tatum_io and @WalrusProtocol for building the tools and for backing it.
This is the first one. The wins begin.
lift-arena.vercel.app
Here are the winners of Total Recall’s first track:
Market & Sport Predictions
🥇 Lift by @ThePythonBoy352
🥈 Hindsight by @neromtoobad
🥉 Vernier by @Maveriq_
Out of 57 projects submitted in this track, these 3 stood out for their sharp builds.
More on each in the comments 👇
I’m building before Q-Day ⚛️. Joining @QoreChain’s online hackathon to build post-quantum dApps, secure AI agents, encrypted apps, and blockchain infrastructure.
💰 $20,000 prize pool
🔗 build.qorechain.io
Who’s building with me? #BuildBeforeQDay
bbqd-64om2Fwe
10
Replying to @yannessss_h687
Fewer than you’d think: about 110 messages between the agents across 4 stages, plus 802 tool calls. The mandates tell them to reply only when they need someone to act, so there’s no “thanks, got it” chatter.
The bill was a single Claude Pro subscription shared by all four agents. Each stage used most of a 5-hour usage window, and stage 4 ran out, which is why the factory went dark for 7 hours. Band was on an event plan. Nimble cost almost nothing because all the building and testing ran against the buildathon’s test web, and only the live builds used my key, capped at 80 units each.
7
I sent 7 messages. Four AI agents built the whole product.
For the BAND Dark Factory Buildathon, I didn’t build an app. I built the factory that builds it, then stayed out of its way.
The product is Dossier. You give it a company’s domain and it researches the live web, then writes a dossier: who runs the company, where it’s based, when it was founded, how big it is, what it has raised, plus its executives and investors. Every value comes with the pages that back it up. When sources disagree, it marks the field contested and shows every candidate instead of quietly picking one.
The catch: no human was allowed to write the code, and most of the graded tests were hidden. In some stages, only 4 to 8% of them shipped. So passing the tests, you can see, proves very little.
So the factory doesn’t trust them. It has four Claude agents in Band, each with its own context:
→ a coordinator turns the spec into a ledger, one numbered row per promise (281 rows across 4 stages)
→ two builders write the code
→ an examiner reads only the spec, never the code, and writes its own tests
The examiner’s blind reading of the spec found 21 requirements the ledger missed.
My favourite moment: at one revision, every shipped check passed for all four stages, yet the build was broken. One build billed 92 units against a hard cap of 80. The examiner’s own test caught it. Then my Claude usage limit hit, and the whole factory went dark for 7 hours. I sent one message when it reset. Three minutes later the fix was in, and seven minutes after that the examiner accepted it.
It measured cost before spending it, too. Before writing the research code, the factory priced four ways to gather facts through Nimble. The cheapest one missed 8 fields. The one it chose found all 70 at 7.30 units per correct fact.
On the live web, on companies nobody prepared for, every build stayed under 80 units. Where the sources agree, the field says known; where they disagree, it says contested. One company returned nothing, and the dossier says unknown rather than guessing. I’d rather ship that than a confident wrong answer.
The numbers:
4 of 4 stages accepted
83 commits, every one by an agent
802 tool calls
7 messages from me: 4 to start a stage, 2 when an agent went quiet, 1 after the usage limit
The two stalls became written rules for the next stage, and that stage had no stall from an agent.
Everything is public: the agents’ mandates, every room log, the ledgers, the examiner’s tests and the measurements.
github.com/miracle352/measur…
Built with Band, Claude and Nimble.
@band_hq
1
5
79
Replying to @OctoHallHQ
Agreed. Until it's rerun with a real Reject, I count it as you said: a before-choice case resting on one request. So the honest split today is 5 tracked after Reject and 2 before any choice, and the census page marks that one as the weakest. I'll post the rerun if I do it.
6
Replying to @peteryantweets
Yes. A cancel button that exists passes every test. The law asks whether cancelling is as easy as signing up, so that's what Statute checks: Kane subscribes, then cancels, and the code counts the clicks both ways. Cancelling can take at most one extra click for confirmation, and it must end with "your plan is cancelled".
7
Replying to @jul1anodev
That's exactly why Accept is there. "Block everything" passes a naive consent check and breaks analytics for people who said yes. A fix has to pass both ways, or it doesn't count. Thanks for running the replay🙏
7
Replying to @Razmatazz
True, and the law doesn't care which one you are. California's click-to-cancel rule applies to any business selling subscriptions online, so web apps need their own proof.
1
12
Replying to @OctoHallHQ
Good catch; they are different. Of the 7: 5 kept tracking after Reject (2 of those also tracked before any choice), and 2 only tracked before any choice. One of those 2 is the weakest case: a single request, and Kane clicked "Manage cookies" rather than a reject. Each site's breakdown is on the census page.
1
22
MIRACLΞ retweeted
The Total Recall winners are in, with projects tackling everything from prediction accuracy to agent security and financial decisions
Meet the winning teams, see what they built, and find out what stood out 👇
Replying to @evvvvince
That's the whole gap. Your tests check the code, not the law. If you ever want to check a real app, drop me the URL and I'll run Kane on it.
11
Replying to @testmuai
Thank you! Kane made the hard part possible: it's the only thing in the loop allowed to say a fix is real. If anyone on the team wants to try it, "Run it live" on the loop page runs the whole thing in about 5 minutes.
1
18
MIRACLΞ retweeted
AI agents write code that works. Nobody checks whether it's legal.
Cookie consent, hidden fees, cancel flows. These are laws now, with real fines, in the EU, the UK, and California. But no test suite knows what they say. Your CI goes green, and your app breaks the law anyway.
So I built Statute: consumer law as an automated test.
How it works:
1. Each law is written as a check. "Reject means reject." "The price shown is the price paid." "Cancelling is as easy as signing up."
2. Kane CLI runs it like a real person would. Real Chrome, real clicks: it refuses cookies, goes to checkout, tries to cancel. Everything is recorded: every request, every step, screenshots.
3. Code decides, not AI. The verdict comes from Kane's evidence, so it's the same every time, and you can re-check it yourself without spending a credit.
4. When something fails, your agent fixes it. Claude Code gets the exact evidence and changes the source.
5. A fix only counts when Kane proves it. Fresh browser, check again. No "it should work now."
Where it lives:
• Pull requests: one GitHub Action, and it only spends credits when a change touches tracking, prices, or subscriptions
• Your live site: a nightly check that opens an issue the moment something breaks
• Your agent: a Claude Code hook that won't let it say "done" while a law is broken
It isn't a lab demo. Pointed at 15 big European sites, it found 7 tracking visitors without consent.
Try the whole loop live, on a real app, right now:
statute-production.up.railwa…
statute-production.up.railwa…
Watch it in 3 minutes: youtu.be/4KScNZ5O9bQ
Code (MIT): github.com/miracle352/statut…
Built for the Kane CLI hackathon by @testmuai #KaneCLIHackDay @kane_cli.
AI agents write code that works. Nobody checks whether it's legal.
Cookie consent, hidden fees, cancel flows. These are laws now, with real fines, in the EU, the UK, and California. But no test suite knows what they say. Your CI goes green, and your app breaks the law anyway.
So I built Statute: consumer law as an automated test.
How it works:
1. Each law is written as a check. "Reject means reject." "The price shown is the price paid." "Cancelling is as easy as signing up."
2. Kane CLI runs it like a real person would. Real Chrome, real clicks: it refuses cookies, goes to checkout, tries to cancel. Everything is recorded: every request, every step, screenshots.
3. Code decides, not AI. The verdict comes from Kane's evidence, so it's the same every time, and you can re-check it yourself without spending a credit.
4. When something fails, your agent fixes it. Claude Code gets the exact evidence and changes the source.
5. A fix only counts when Kane proves it. Fresh browser, check again. No "it should work now."
Where it lives:
• Pull requests: one GitHub Action, and it only spends credits when a change touches tracking, prices, or subscriptions
• Your live site: a nightly check that opens an issue the moment something breaks
• Your agent: a Claude Code hook that won't let it say "done" while a law is broken
It isn't a lab demo. Pointed at 15 big European sites, it found 7 tracking visitors without consent.
Try the whole loop live, on a real app, right now:
statute-production.up.railwa…
statute-production.up.railwa…
Watch it in 3 minutes: youtu.be/4KScNZ5O9bQ
Code (MIT): github.com/miracle352/statut…
Built for the Kane CLI hackathon by @testmuai #KaneCLIHackDay @kane_cli.
Replying to @polytutor
final outcome, not price move 🙏
the agent seals a "blind" call before it sees any tip, then reads the tip and calls again. when the market resolves we score both with Brier:
helped = Brier(blind) − Brier(after tip)
if that's > 0 the advisor keeps the cent, otherwise it's refunded. the cent sits in escrow until then, so nothing gets paid on vibes, and since the blind call is sealed first, nobody can quietly claim the tip changed their mind more than it did
5




