Topic
AI Agents
5 engineering lessons and 2 supporting resources about AI Agents.
About this topic
This track collects 5 lessons on AI Agents, written to be read in order and revisited as reference.
It opens with “AI Agents Explained: LLMs, Tools, Loops & MCP.” 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.
You’ll learn
- AI Agents Explained: LLMs, Tools, Loops & MCP
- Agent Runtime, Context Engineering & Memory
- How Coding Agents Work: Claude Code, Cursor, MCP
- Multi-Agent Systems & Production AI Agents
- Agent Systems Engineering — How Production AI Executes Work
Recommended starting lessons
View all lessons- 01AI Agents Explained: LLMs, Tools, Loops & MCP
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.
18 min - 02Agent Runtime, Context Engineering & Memory
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.
9 min - 03How Coding Agents Work: Claude Code, Cursor, MCP
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.
15 min
What this topic connects to
Related topics to explore next.
Resources in this track
Curated references, cheat sheets, and checklists.
- AI Agent Architecture-Review Checklist
AI agent architecture-review checklist: seven review lenses, trust boundaries, production-readiness checks, common failure modes, and red flags for the design-review chair.
- AI Agents Cheat Sheet
One-page AI agents cheat sheet: the agent stack, core definitions, mental models, archetypes, buzzword-to-engineering translations, and ten memory rules to recite.