Procedural Memory: The Missing Leap in AI Agents

Harness and loops are required in any agent system today. Almost no one argues otherwise. The model reasons, the harness governs it, the loop executes and verifies without you having to hover over it.

But for us as a lab there is a third pillar that matters just as much, if not more. Memory.

Today, when people talk about memory in agents, they talk about two things. Short-term memory, the context of the conversation. And long-term memory, the facts the system remembers across sessions. On top of that there is a third category we don't even call memory: the workflows a person builds for the AI to execute.

That space is crowded. Workflows that people design and agents run. Systems that extract routines from past trajectories and hand them to the agent as guidance. But they all share one thing. The LLM is still in the middle, thinking through every step, burning tokens on decisions it has already made hundreds of times.

What if we could replicate what the human brain does?

The brain doesn't think about walking

Cognitive science described this more than 40 years ago. It's called Knowledge Compilation, and it's part of John Anderson's ACT-R architecture, one of the most studied theories of how human cognition works.

The idea is simple. When your brain does something for the first time, it thinks through every step consciously and effortfully. That is declarative memory. In AI agents, that means calls to the LLM. And therefore, token consumption.

But there comes a point when the human no longer has to think. They do it using procedural memory. It's like walking. You don't think "I have to move my leg, put one foot in front of the other." Or blinking. Or chewing when you eat. Your brain compiled that sequence into an automatic routine that fires on its own, and freed your conscious mind for what truly needs it.

That process of compiling expensive reasoning into automatic execution is exactly what AI agents are missing.

Procedural Memory in production

That's what we have running in FusionAI today. We call it Procedural Memory. The muscle memory of your agents.

When a procedure is compiled, the engine runs it end to end without invoking the LLM. Zero tokens in the engine. The model is freed up for what actually requires reasoning, just like your mind when you walk.

And the best part: you don't have to build it yourself. FusionAI creates it based on your day-to-day work with it. It detects the repetitive patterns, runs several reviews, and determines whether that procedure can be compiled and run on its own. Just like your brain doesn't ask your permission to automate walking. It simply does it once you've learned.

The frontier

We're not the only ones looking this way. AWM from CMU and MIT, NeSyPr at NeurIPS, Microsoft's Conductor. The best labs in the world are converging on this direction, and that confirms the path is right.

The difference comes down to two things. We run it in production, not on a benchmark. And the system compiles the workflows on its own, by watching you work, without you having to design them.

A model working with harness, loop and procedural memory is a different class of system.

We're at the frontier of memory, harness and loops. And we're just getting started — the leap ahead is ours to take.