DEMO / RECORDING
Overview & Result
An open-source skill that routes coding prompts to the right model tier (fast utility vs deep reasoning), saving token cost and reducing latency inside Codex agent sessions.
How Jev fits in the loop
- Intercept coding task before agent turn.
- Jev scores prompt complexity against available model capabilities.
- Assign optimal model tier for the current turn.
How to reproduce
- Inspect the source implementation at https://github.com/instructa/switchloom.
- Configure local Jev API credentials and register required tool/model bindings.
- Execute test prompts and observe decision latency and routing outputs.
Why this build matters
Directly empowers Codex users to optimize agent costs without degrading code quality.
Limitations
- Metrics are author-reported from the initial release unless independently verified.
- Requires access to the respective agent framework or runtime environment.
- Generative model execution remains external to the Jev decision step.