Wiki

Agentic AI

How AI agents actually work: tool use, planning and reasoning loops, memory, subagents, evaluation — and the guardrails (permissions, sandboxing, human confirmation) that make acting autonomously trustworthy. Same house style: intuition first, a visualization you can play with, then the math.

Foundations

What an agent actually is: the loop, tools, the context budget — and when not to build one.

Planning & reasoning

Decomposing a goal, deliberating in the loop, reflecting on mistakes, and searching over candidate plans.

Memory & context

Working memory, retrieval, long-term memory, and the engineering of what stays in the context window.

Multi-agent & orchestration

Splitting work across agents: supervisors, routing and decision layers, handoffs, and the coordination tax.

Evaluation & observability

Testing trajectories, the benchmark landscape, judges and verifiers, and tracing agents in production.

Safety & deployment

Permissions, sandboxing, injection and tool abuse, human confirmation, and shipping an agent you can trust.