Writing on production AI systems, control loops, and reliable execution.
May 11, 2026
Control Systems for Intelligent Software #6
There's a quiet assumption underneath most AI discussions: if capability keeps improving, coherence will eventually follow. Gödel's incompleteness theorems suggest otherwise. The supervision layer isn't a temporary workaround — it's part of the design.
April 27, 2026
Control Systems for Intelligent Software #5
Once you can see what the system is doing, the next problem is interacting with it. Chat interfaces for AI agents are like flying a drone through a text terminal. The industry needs purpose-built control surfaces.
April 20, 2026
Control Systems for Intelligent Software #4
AI systems fail in ways that look like success. You can't find these failures in a chat log. You need traces. AI agent systems need the same observability infrastructure that distributed systems built over the past decade.
April 13, 2026
Control Systems for Intelligent Software #3
We're building AI systems like they're chatbots. They're not. They're control systems. The architecture that robotics solved decades ago — machine, telemetry, interface, human — is the same architecture AI agents need.
April 6, 2026
Control Systems for Intelligent Software #2
Most AI pipelines have generation and verification backwards. Smart models should generate. Cheap models should verify. The industry is putting its best capability in the wrong place — and it's creating a quality ceiling, not just a cost problem.
March 17, 2026
Control Systems for Intelligent Software #1
The industry phrase 'bash is all you need' is technically correct. But it hides the real problems: context management, execution reliability, alignment with outcomes, and human supervision.