DEMO / RECORDING
Overview & result
Inside busy Slack channels, agents often delay responses while deciding which tool to call. This build uses Jev as a lightning-fast front router that chooses the skill and fills parameters before the LLM generates prose.
From the original post
Jev made our Slack agent 2x faster ⚡️
Our agent can be quite slow because it needs to read skills and figure out which tools to call.
We used @typesafeai's new model to speed this up by first passing it the prompt and classifying the best skill, tool and params to use before handing it to the agent
How Jev fits in the loop
- Listen to Slack message event.
- Jev evaluates user request against registered company skills in under 50ms.
- Pass pre-selected tool bindings to agent for immediate response generation.
How to reproduce
- Inspect the source implementation at https://x.com/johnyeo_/status/2100987661926252737.
- 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
Demonstrates substantial latency improvements in enterprise chat interfaces.
Reported performance
Reported by authorLatency: 2× speed-up
Author reported 2× faster Slack response times by pre-selecting tool skills before LLM generation.
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.