Awesome Jev: early projects and use cases
A community-curated list gathers early Jev projects and ideas for developers who already have API access.
Community practice: classifying RAG passages with Jev
Marlene shares hands-on experience using Jev to classify RAG passages: Jev returns multiple probabilities per passage (e.g., relevance and whether it contains the answer), which guide keep/drop decisions. She is also testing it for compaction in the copilot SDK.
I like this approach to RAG with Jev. For each passage, Jev returns 4 probabilities like: P(relevant) < 0.45 → drop P(has answer) > 0.55 → keep It keeps or drops based on probability! https://docs.typesafe.ai/cookbooks/classifying_rag_passages… I've been trying it out for compaction in copilot sdk...
· 5 likesOpen on X
More like this
Training an MLP on Qwen 4B to Replicate Jev Behavior
The author shares an open-source project openjev that trains an MLP on qwen 4b to work like Jev, with a Hugging Face link. Link
Swapping an agent's tool-calling reasoning with Jev
The author shares replacing an agent's tool-calling reasoning with Jev, using Fable, Astra, and Opus; early results show drastic savings with very close results, with a demo video promised.
