Know what’s coming.
Know what to do.
Knowable Labs builds end-to-end forecasting and trading infrastructure. We produce best-in-class forecasts on news, politics, and finance, then execute them as positions on prediction and capital markets, with hard risk guardrails and a full audit trail.
Who we work with
Forecasts are useful anywhere a decision depends on what happens next. Today we work with traders and teams in three areas.
Active prediction market traders
You bring an idea, your own data, or nothing at all. The harness does the research, writes a strategy you can run, backtests it with fees included, and places the positions inside guardrails you set.
Hedge funds and market makers
Use calibrated forecasts to find event-driven and macro opportunities, sharpen conviction, and size positions with greater confidence. For systematic desks, Knowable brings an independent, forward-looking signal into fair value, pricing, and execution.
Insurance
Underwriting and reserving are bets on events that haven’t happened yet. Knowable delivers calibrated probabilities on catastrophes, policy changes, and litigation outcomes, giving pricing and exposure decisions a live, evidence-backed forward view.
A demonstrated edge across leading benchmarks and live markets
Knowable’s forecasts outperform leading models and human forecasters on ForecastBench, while its trading system generates consistent returns in live Kalshi markets.
Fully autonomous: the system picks the markets, sizes the positions, and executes. Every trade is logged.
ForecastBench standings
On ForecastBench’s contamination-free questions, Knowable Labs is among the top market scores on the board.
| Forecaster | Market score (higher is better) |
|---|---|
| Knowable Labs | |
| Gemini Google DeepMind | |
| Superforecaster median human gold standard | |
| Grok xAI |
Standings as of September 21, 2026. Verify on the public leaderboard: we run as “Anonymous 8” (tick “show anonymous teams”).
Knowable forecasts that held
Real calls our system made on live Kalshi markets. For each one: what we said, what the market said, and what actually happened.
Each number is the chance of “yes” at the moment we made the call.
The harness
One harness, four steps. Research pulls news, filings, market data, and your own data as of the decision time. Strategize turns the idea into entry rules, sizing, and exits a system can run. Backtest and execute places positions with guardrails in code and every position traced to its evidence. Learn retrains calibration and sizing on every resolved market.
Forecasting infrastructure
Calibrated probabilities on news, politics, and finance continuously updated as new evidence arrives and outcomes resolve. Built to cover thousands of questions at once at a fraction of a frontier-model’s cost.
Any resolvable question, from a market feed or your own list.
Live news and data pulled per question, cited in every forecast.
Forecasts scored against outcomes and corrected continuously.
Thousands of open questions tracked at once.
Execution infrastructure
Turns forecasts into positions on prediction and capital markets. Built for scrutiny, not just returns.
Position and exposure limits enforced in code.
Every position traces back to its forecast and evidence.
Every decision recorded end to end.
Realized outcomes feed back into the forecaster.
If it resolves, we forecast it
Questions arrive from a market feed or your own list. Thousands tracked at once, re-forecast on every new fact.
Meet the team
They spent decades building ML systems at Google. Now they’re putting that experience toward a harder problem: knowing what happens next.
Yew Jin Lim
Ex-Director of Engineering on Google Search, with 18 years building planet-scale ML and GenAI systems. PhD from the National University of Singapore.
LinkedIn →
Gautham Srinivas
Ex-PM leader on Google Search AI. Before Google, an early engineer at Flipkart and one of India’s top 10 competitive programmers through the IOI training camp.
LinkedIn →Work with us
If you trade markets, plan supply chains, or underwrite risk, get in touch. None of those but want our forecasts on tap? We’d like to hear from you too.
Got it, thanks.
Your message is on its way to the team. We’ll get back to you within a day.