Writing
Notes on agents and memory.
Longer pieces on the problems behind Kazn: why AI agents need one memory, and why people should approve what changes.
Your AI agents need one memory
AI tools keep getting more capable and more scattered. The missing piece isn’t another integration. It’s a memory you own that every agent reads.
Agents propose. People approve.
Why no AI agent in Kazn can change what you know on its own, and why that makes agents more useful, not less.