Memory and control
Context Engineering for AI Agents That Work Across Real Systems
A practical guide to designing durable context, retrieval boundaries, working packets, and policy-aware memory for AI agents.
Field notes from the control plane
Build AI systems that can explain what happened.
Practical guides for operators who need durable context, visible execution, and publication gates that stay closed until a human approves the work.
Evidence and operations
AI Agent Observability: From Activity Logs to Actionable Evidence
A field guide to tracing agent decisions, tool calls, policy gates, failures, and human approvals without confusing activity with reliability.