Testing Jev as a confidence-scored router to offload small LLM calls in oncology agents
Ubunta · x · 2026-09-26
The author has been trying Jev this week, likening it to a Bloom filter that runs a cheap check before expensive work — except Jev outputs a confidence score rather than a hard guarantee.
Working with real-world oncology data, their AI agent plans and runs analyses on a data warehouse, and the big model wastes time on trivial calls like counts or survival analyses. They are testing Jev for three roles: routing, ask-or-act decisions, and plan checks.
The architecture keeps reasoning in the large model while data access rules stay deterministic. The open question is whether Jev's confidence holds up on clinical data.
More from coding & agent
- Exa launches Agent Ultra, an agent-swarm deep research tool claiming SOTA — yoimnotkesku · 2026-09-26
- YC Backs 'Spend More Compute on Validation': Greptile Launches Plus and Apex Review Tiers — ycombinator · 2026-09-26
- OpenAI Showcases Proaction Using GPT-6 Astra to Build Fleet-Management Agents Faster — OpenAIDevs · 2026-09-26
- Prompt-to-Promo Video: Deterministic Frame Rendering Is the Real Unlock — ezshine · 2026-09-26
- Open-source MCP server lets agents use secrets they can never see — JuanixVentures · 2026-09-26
- One Stripe Engineer Merged 600 AI-Written Changes in Six Months, One Rollback — victor_explore · 2026-09-26