Closed · April - September 2026

3rd Eyes is closed.
The full trade record stays public.

For five months we traded daily temperature contracts on Kalshi using a four-model forecast ensemble, and published every position in real time. In September 2026 we shut it down. The strategy needed a win rate in the high eighties just to break even, the markets proved too thin to scale into, and our most recent stretch fell below that line. Rather than keep selling something we no longer believed would pay for itself, we stopped.

Every trade we ever placed is still published - wins, losses and stop-outs alike, reconstructed from the exchange's own settlement records. We did not take the record down when the numbers turned against us.

See the full verified record →

Nothing here is investment advice. Past performance does not guarantee future results, and prediction-market trading carries real risk of loss.

How it works

Your first trade, in 3 simple steps.

📲
1 · Get the alert

A Telegram message lands - the city, the price, our win-probability, and the exact market link to open.

👆
2 · Open the market

Tap our link straight to the exact contract on Kalshi (or find it on Coinbase / Robinhood) - you're on it in seconds.

3 · Tap Buy

Place the trade, set it down, get on with your day. We tell you the result when it settles.

No charts. No forecasting. No trading experience. If you can read a message and tap a button, you can do this.

Every trade. Every city.
Nothing hidden.

Reconstructed directly from Kalshi's settlement and fill records - every win, loss, and stop-loss exit. The full per-trade ledger lives on a dedicated page.

- W - L -% win rate Scanning 40+ · - w/ fills

The bot continuously scans 40+ US cities every 5 minutes. The figures above are the exchange-verified record since Apr 23, 2026 (v1.0 methodology start); see the full per-trade ledger at /track.

Date City Threshold NO Fill P&L Result
Loading recent trades… see the full ledger at /track.
See the track record, scan activity & calibration

The /track page shows every trade, reconstructed from Kalshi settlement records - with every stop-loss exit counted at its real cash result.

Built by data engineers.
Not influencers.

3rd Eyes isn't a hype account - and it isn't a single AI prompt. It's an engineered pipeline: a four-model weather ensemble, per-station bias correction learned from history, an ensemble-spread filter, a +EV pricing gate, confidence grading, and a pre-set stop-loss on every trade. Built and run by two engineers, brothers, with a combined 17 years moving and protecting production data. That discipline is why the public ledger - reconstructed from Kalshi's own settlement records - shows a win rate of the rate published at /track you can verify trade by trade.

🛰️
Anil Sharma
Data & Models · Co-founder
Reynoldsburg, OH · 7+ yrs data engineering

Databricks Certified Data Engineer. Builds the forecast pipeline - multi-model weather ingestion, the scoring engine, and the signal logic that finds mispriced contracts. Day job: enterprise data engineering (Spark, Azure Synapse, SAP Datasphere).

🛡️
Sunil Sharma
Infrastructure & Reliability · Co-founder
Washington, DC · 10+ yrs data protection

Principal Backup Engineer & Solution Architect at a major financial institution - enterprise backup/restore, RTO/RPO, and cyber resilience & recovery. Owns reliability and data integrity: the systems that keep the engine running 24/7 and the public ledger trustworthy.

𝕏 @Sunilpokhrel007
🤝

We trade every signal ourselves. Every signal we publish runs through our own accounts on auto-execute - we don't send you a trade we haven't taken. Our money is on the same line as yours.

3rd Eyes has stopped
taking subscriptions.

We ran this as a live, publicly verified experiment from April to September 2026. It is now closed to new customers, and the trading engine has been switched off.

Why we stopped. The strategy needed a win rate in the high eighties just to break even, and the market for these contracts is too thin to size into. Our most recent stretch fell below that break-even line. Rather than keep selling something we no longer believed would pay for itself, we shut it down.

The record stays public. Every trade we ever placed, wins and losses alike, remains at /track exactly as it was reconstructed from the exchange's own settlement records. We did not take it down when the numbers turned against us, and we are not taking it down now.

Existing subscriptions have been cancelled and no further payments will be taken. Questions: support@3rdeyes.io.

See the full verified record →

Questions answered.

Yes. Kalshi is a CFTC-designated contract market, the same regulator that oversees CME and the major US futures exchanges. Trading prediction contracts on Kalshi is 100% legal for US residents. 3rd Eyes provides signal research, the same way stock screeners or options analytics services do.
No. 3rd Eyes is a research and signal-publishing service - think stock screener or options-analytics tool, not a broker. We never hold your money, place trades for you, or give personalized investment advice. You trade in your own account, in your own name, and every decision is yours.
Kalshi is open to US residents who are 18 or older, and you'll complete Kalshi's own identity verification when you sign up (a few states restrict certain markets). You'll need your own funded account on Kalshi, Coinbase, or Robinhood. 3rd Eyes only delivers research - we don't onboard you to any exchange or handle your funds.
Prediction-market gains are generally reportable, and exchanges like Kalshi may issue year-end tax forms (e.g., a 1099). Tax treatment depends on your circumstances and we are not tax advisors - please consult a qualified professional. The exchange's settlement records are the source of truth, so keep your own copies.
You can lose your entire stake on any trade. These are small-edge NO positions: they win often, but a single rare-weather day can take a position toward zero, and the stop-loss exits at a real (worse) price - never a guaranteed one. Past performance does not guarantee future results. Only stake discretionary funds you can afford to lose entirely, and size conservatively.
There's no minimum from us - Kalshi only requires a $10 deposit to start. What matters far more than the dollar amount is how you size each trade: we suggest risking a small, fixed fraction of your bankroll on each signal (commonly 1-5%, scaled by the signal's confidence grade) and never staking money you can't afford to lose. Many subscribers start with a few hundred dollars and a ~2% per-trade size. There are no platform fees for placing orders.
Temperature extremes are rare. "City X will hit 95°F today" is usually false. A NO position wins if the temperature stays below a stated threshold, which our models can predict with high confidence when every ensemble member across all four forecast models clusters far from the threshold. We never trade YES because the upside is smaller and the prediction is harder.
We keep it simple: one bankroll, not a tangle of slots or compounding ladders. Decide the total you're comfortable risking (your bankroll), then stake a small fixed fraction of it on each signal - many traders use 1-5%, scaled by the signal's confidence grade. Hold no more than two positions in any one weather region, and let the pre-set stop-loss cap the downside on each trade. As your bankroll grows, the same percentage naturally puts a little more to work; if it shrinks, you automatically bet less. The sizing calculator does the math for you.
Losses are part of any probabilistic edge, and we publish them rather than hide them. One instructive example: an early LA position moved against us intraday when morning GFS models underestimated afternoon temperatures due to marine-layer burn-off, a known coastal bias. We responded by widening the LA/SF/SD minimum buffer and adding per-station bias correction, so that specific failure mode now triggers a filter. Our full win and loss record is verified directly from Kalshi settlement records - see /track.
Probably not. Our signals reference US-regulated Kalshi contracts (also carried by Coinbase and Robinhood), and all three require US residency and identity verification. If you are outside the US you most likely cannot trade these markets. The free channel, the methodology and the verified track record remain open to everyone for research and education.
It varies. Currently we average 5-8 qualifying signals per week across 40+ cities. The system only fires when buffer, multi-model agreement, and orderbook depth all clear thresholds; we'd rather miss a trade than take a bad one. Quiet weather periods may show 2-3/week; active high-pressure regimes can push it past 10.
Our current verified win rate, trade count and net P&L are published live at /track, covering every trade since our v1.0 methodology launch on Apr 23, 2026. Every figure is reconstructed line-by-line from Kalshi's own settlement and fill records, with stop-loss exits counted at the real price we got out - nothing hidden or rounded up. See the full per-trade ledger at /track. (Note: a high win rate on small-edge NO positions still carries real risk; past performance doesn't guarantee future results.)
Yes. The $499 is a one-time setup: a live 1-on-1 session where we configure your own auto-execution listener on your server with your Kalshi API keys. It includes your first month of Pro free; after that, signals keep flowing through a standard Pro subscription at $49/mo, cancel anytime. Without an active Pro subscription the pipeline has no signals to execute. Nothing here is a promise of profit or a timeline to "recoup" anything - returns depend on market conditions, your sizing, and variance; see the verified record and sizing guide for the honest numbers.
Not exactly. We're not competing against meteorology desks on raw forecast accuracy. The edge comes from retail behavioral inefficiency on Kalshi: slow repricing, "YES chasing" on extreme temperatures, low liquidity in long-dated markets, and inconsistent risk management by casual traders. Our multi-model stack lets us identify those mispriced markets quickly. The forecast is the gate. The edge is the gap.
April - September 2026

We published every trade,
including the ones that ended this.

3rd Eyes was a live experiment in trading weather prediction markets, run in public with an exchange-verified record. It is closed. The full ledger stays up, unedited, because a track record you only publish while it flatters you is not a track record.

Read the full record →
Closed project · verified record · Next scan in - See the record →