Overview & result
Clawby shows "Clawby re-scores four dimensions every ten minutes", built on Jev: Technical, liquidity, sentiment and risk, re-judged on a ten-minute loop.
From the original post
Clawby re-scores four dimensions every ten minutes by @clawby: Technical, liquidity, sentiment and risk, re-judged on a ten-minute loop.
How Jev fits in the loop
- The agent collects input state and extracts candidate actions.
- The decision boundary is sent to Jev System One for a fast evaluation.
- The matching action or tool call is triggered based on the confidence score.
How to reproduce
- Review the source documentation and repository at https://x.com/openclawby/status/2102199469970477555.
- Configure environment with TypeSafe Jev / System One API keys.
- Run test prompts against the decision endpoints.
Why this build matters
Shows Jev in practical use for trading and financial markets.
Limitations
- Performance and latency benchmarks are community author-reported.
- Production deployments require custom guardrail calibration.