Research from production systems.
Notes on multiplayer AI, memory, browser automation, continual learning, and how agents earn their autonomy. Every finding comes from systems that are running.
I Built AI Agent Memory Wrong 3 Times. Here's What Finally Worked.
What seven research papers, one catastrophic bug, and 10,000+ memory objects taught me about building memory systems that actually earn user trust.
The Selector Ladder: Why Your Browser Automation Breaks Every Week
After running 27 browser automation skills across X and LinkedIn for months, we developed a reliability hierarchy that survives CSS obfuscation, DOM reshuffles, and React re-renders.
The Coordination Problem: Why Multi-Agent AI Systems Break at Scale
Single agents are getting powerful. Multi-agent systems are still a mess. The problem isn't intelligence — it's coordination. Here's what we learned building Grid.
Agents That Actually Learn: Beyond Session-by-Session Amnesia
Every session starting from scratch is not a feature — it's a ceiling. Here's how we think about continual learning for production AI agents.
How Do You Value an AI Agent? The Case for Agency Evaluation
Benchmarks measure outputs. Agency evaluation measures what an agent is actually allowed to do next — and why that's the more important number.
Agent Evals Are Not Benchmarks. They Are Trust Infrastructure.
The second post in our evals series: why the output of an eval should not be a score — it should be a decision about what the agent is allowed to do next.
Agent Evals Are Not About Answers. They Are About Work.
The first post in our evals series: why agentic evals must measure outcomes, process, side effects, and reliability instead of final answers alone.