Agentic Systems

Unfurl

A research-to-execution loop that gates every step

Role
Systems architecture, safety engineering, strategy research
Year
2026
Status
Running in production with real capital
1,324
commits
290
test suites
3 / 981
configs past the DSR gate
10
money-path bugs found and fixed

The problem

Autonomous trading systems fail quietly. A strategy overfits to a thin backtest, the operator sees a good-looking equity curve, and capital goes to work behind a number that was never real. The system had to make that failure mode loud.

What we built

Decisions That Mattered

1.

Separate research from execution

A Python vectorbt research layer proposes and a TypeScript engine disposes. The two share a parity harness so a strategy behaves identically in backtest and live, and the harness fails the build when they diverge.

2.

Gate on statistical significance

Every candidate configuration passes through a Deflated Sharpe Ratio gate that accounts for how many configurations were tried. In the first full sweep, 3 of 981 survived. The other 978 were selection noise wearing a good chart.

3.

Race strategies before arming them

A per-market strategy arena runs candidates as zero-capital telemetry, promotes survivors to shadow trading on live prices, and only then presents them for arming. Promotion is automatic. Arming never is.

4.

Make the money path adversarial

A self-run audit of the execution path produced six critical and four high-severity findings on order sizing, idempotency, and position ownership. All ten were fixed and shipped as reviewed pull requests before that code touched capital again.

5.

Keep the human in the loop by design

Live execution sits behind a kill switch, per-session execution modes, and typed confirmation phrases. The default state of every strategy is off, and nothing in the automation can change that.

What this demonstrates

Autonomous systems that hold real risk, with promotion pipelines, evidence gates, and an off switch the automation cannot reach.

TypeScriptNext.jsPythonvectorbtElectronSolanaHyperliquidsystemd

Get in touch

Start a Project

Tell us what you are trying to build and what is in the way. We will tell you early if we are not the right fit.

starrybodies@gmail.com