Practical AI agents, organized by problem.
Original operating notes and interactive tools for building useful agents with visible boundaries and evidence.
AI agent operations
Practical field notes, tools, and runbooks for orchestrating AI agents with evidence, handoffs, observability, and recovery.
/ai-agent-operationsAgent safety & governance
Practical guidance and interactive tools for AI agent permissions, approval gates, audit trails, containment, and rollback.
/agent-safety-governancePrivate & local-first AI
Architecture, model routing, permissions, and operating patterns for private and local-first AI assistants.
/private-ai-assistantBuild logs & case studies
First-hand AI agent build logs covering failures, infrastructure, workflows, and lessons that can be reused.
/case-studies