devwithjevFilters Candidate Files Before Claude
Reid Fletcher reports that Aition uses Jev ahead of Claude to filter candidate files, reducing files sent to the model by 33%, tokens by 25%, and cost by 23%, with no loss in recall.
Reid Fletcher@LxKus𝕏
Using generative LLMs for routing is a mistake. We put @typesafeai Jev in front of Claude to filter candidate files in @aitionapp: • -33% files to model • -25% tokens | -23% cost • $0.037 to score 543 files (0.38s/file) • 0 loss in recall https://t.co/k8cYAslumh
The reported run scored 543 files for $0.037, at 0.38s/file.
Also filed under Triage & routing
- Python Library for Jev Judgments
gut is an open-source Python library that turns Jev’s typed questions into a readable line of code.
- Real-Time Feedback Alert Classification
The author reports using Jev in a feedback platform, where real-time alert classification is already live.
- Yueli DEX Decision Exchange
Yueli DEX routes bounded business decisions to TypeSafe Jev or compatible providers and maps validated results to non-authorizing action intents.
- Medical Exam Option Scoring and Gating
Open Medical Jev is a frozen open-model medical decision stack that scores each exam option, then uses confidence and conformal gates to auto-release or escalate answers.