AI Agents Lessons

AI agents from first principles: how LLMs, tools, the agent loop, planning, and MCP fit together — build the full stack from memory and tell real capability from hype.

Explain to an interviewer how an agent runtime orchestrates an LLM loop, why context engineering often matters more than model choice, and how the three memory tiers map to production storage systems.

Explain step-by-step how Claude Code executes a real task, how Cursor retrieves context from a large repo, and how MCP turns any business function into a standardized tool an agent can call.

Decide when multi-agent is justified vs unnecessary; name five ways production agents fail and how to prevent them; design a business agent (billing, support, or SRE) with the right tools, oversight model, and cost controls.

How production AI agents actually execute work: planning, state, execution engines, loop control, failure recovery, orchestration, long-running tasks, cost, and observability — from first principles.