Definition
Plain language
A way of treating an AI agent's task like source code and compiling it into an optimized plan before running anything.
As stated in the literature
A just-in-time compilation framework for computer-use agents that statically verifies state-flow contracts on cached tool plans, ranks candidate programs by a cost model, and selects a Monte-Carlo-simulated execution strategy at runtime.
Also called: Agent JIT, JIT planner
Why it matters: Compiling the plan up front lets the system catch contract violations and pick a cheap execution path, which agents that improvise step-by-step can't do.
For example, instead of letting the agent improvise screen-by-screen, JIT-Planner compiles 'book a flight from BOS to SFO next Friday' into a verified sequence of UI actions before any clicking starts.
Heard on the show
“JIT-Planner gets more than ten times the speed of Browser-Use — that's the standard open-source baseline that represents the screenshot-and-decide style of agent.”Episode 063 — Why Web Agents Are Slow: A Compiler-Style Fix for Computer-Use Latency