Jev-Driven Agent Tool Calling

Pratim Bhosale experimented with Jev for tool calling, replacing the LLM’s decision-making step with Jev. He says this could let an agent act before the user finishes speaking.

View on X

Pratim Bhosale@BhosalePratim𝕏

Played around with @typesafeai Jev today, mostly to understand what it does for tool calling. Instead of an LLM deciding what to do, I substituted that part with Jev. My learning is that we will be able to make the agent act before the user finishes the sentence. So far, we've used different LLM combinations (non-thinking + thinking ) plus state machine setups to get the right experience for the e

Sep 18, 2026X postsView on X

Bhosale says previous approaches used combinations of non-thinking and thinking LLMs, plus state-machine setups, to achieve the desired experience.

Also filed under Agents & browsers

Evaluates Tool-Using Agents with Jev in CI
The project evaluates a real tool-using AI agent using code checks, a calibrated Jev judge, and an LLM judge. It is wired into CI.
Watchdog for AI Coding Agents
Jev Watch is a watchdog for AI coding agents that stops Codex or OpenCode when they loop, stall, or drift off task, then resumes the same session with a correction.
Fraud Investigation Agent
The author is building a fraud investigation agent using Jev and TigerGraph. Its flow goes from an alert through graph evidence, a Bayesian update, a pattern, Jev’s extra lookup, policy, a verdict, and human approval.
Coding-Agent Runtime Using Jev Decisions
Distill is a coding-agent runtime that uses Jev decisions for model routing, context retention, and tool selection.