We test the gate on our own work.
Instrumented file, shell, and Git operations from our founder's coding-agent workflow pass through Warm Winter in shadow mode. The record below shows what the gate observed, how much outcome evidence each action class has accumulated, and where stronger CI or deployment verification is still required. Shadow mode records; it does not block.
Production snapshot · updated 2026-07-19 · Founder coding agents · shadow mode · weak labels (tool-exit)
0 of 5 verified, and that's the point.
Warm Winter won't claim trust it hasn't earned. Provisional means there's signal but not enough verified depth to let the agent act unsupervised. Ungrounded means it doesn't have the evidence yet, and says so instead of pretending. Autonomy is earned from real outcomes, not granted on day one.
The honest caveat: these are weak tool-exit labels. They show that the observation and outcome loop works; they do not prove that an edit was correct, a command was safe, or a push was valuable. Strong CI and deployment-health outcomes are what can turn those action classes into verified competence.
Read how evidence earns trustSee your own agent's frontier.
Guided setup, shadow mode, nothing to break. It installs, observes, and starts building your record from request #1.
Connect Codex, Claude Code, Hermes Agent, Gemini CLI, OpenCode, Goose, OpenClaw, Cursor Agent, Grok agents, or another local or remote agent through the same evidence contract. Observation is universal; governed execution is certified runtime by runtime.