DEMO / RECORDING
Overview & result
Replaces tedious manual drop-down configurations in developer tools. When a developer submits a prompt, Jev instantly chooses whether it requires a full rewrite, Claude Code, an iOS runner machine, or local scripts.
From the original post
thanks to @typesafeai jev I no longer have fill out all of those fields on prompt boxes. It picks the agent / model / computer / folder for me.
- For a major rewrite it uses Fable + Claude Code.
- Changes to an ios app run on one of my macs
How Jev fits in the loop
- Parse prompt keywords, complexity, and file references.
- Jev Choice selects agent, model tier, target computer, and directory.
- Dispatch the task directly into the appropriate execution environment.
How to reproduce
- Inspect the source implementation at https://x.com/sawyerhood/status/2100994779291259187.
- 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
Eliminates cognitive friction in multi-agent workspaces by routing automatically before execution starts.
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.