Hermes Setup with 443 Unique Skills
The Hermes setup now features 443 unique skills, utilizing Jev for skill selection. Jev achieved 94.4% exploratory reused-data performance, ensuring confidence-aware decision-making.
added by @GodsBoy7777
View similar
Ranked from stored criteria vectors. No live classification on this page.
Jev: Fast Decision-Making for LLMs
Jev offers a new intelligent decision-making primitive that enhances model routing and classification tasks. It allows for quick and cost-effective decision-making, improving the efficiency of LLM calls in applications.
Implementing Jev in AI Agent Fleet
A decision layer named Jev was integrated into an AI agent fleet, achieving high accuracy and low latency for decision-making tasks. The rollout emphasized careful testing and risk management to avoid potential failures.
Improved Model Routing and Action Review with Jev
The integration of Jev from @typesafe_ai replaced three steps in Prio, achieving 100% accuracy in model routing and significantly reducing action review time from 5 seconds to 0.25 seconds for clear cases.
Jev Adapter for Prompt Classification
The Jev adapter classifies prompts before they reach the LLM, reducing token consumption and costs. It provides classification and confidence scores, marking prompts for review when confidence is near the threshold.
Benchmarking Jev for Automated Code Reviews
The Jev model was benchmarked against an ensemble of models for code reviews, achieving zero false positives, a review speed increase of ~50x, and a cost reduction of ~100x. It demonstrated a 75% bug recall rate, highlighting its efficiency compared to traditional multi-turn agent workflows.
AI Feedback System Test Results with Jev
Jev was tested in an AI customer feedback system using 1,040 GitHub issues, proving to be 98% cheaper and 84% faster than Claude Sonnet 4.6 while maintaining higher accuracy.