CoachDiscoverMapCompareSavedAI LearningAI WeeklyAbout
Learning Resource · AI Agent Engineering

The AI Learning Library

A structured collection of guides for understanding how AI agents actually work — from the bare loop all the way to production infrastructure. Read, quiz yourself, and drill concepts with flashcards.

3
Learning Guides
45
Concepts Covered
26
Quiz Questions
45
Flashcards
Practice — test & drill what you've learned
?
Multiple Choice · All Guides

Full Quiz

All 26 questions in one sitting — live score tracks as you go, with a per-guide breakdown at the end.

26Questions
3Guides
LiveScore
Start Quiz →
🃏
Flip Cards · All Guides

All Flashcards

45 unique flip cards across all three guides — 5 are tagged across guides. Filter by topic, shuffle the deck, or flip everything at once.

45Cards
3Guides
Shuffle+ Filter
Browse Cards →
The curriculum — read in order, or dip in anywhere
Foundations Applied Advanced  ·  each guide stands alone, but they build on each other.
01
01 · Foundations

How an Agent Actually RunsLearning agents from scratch — the bottom-up route

Strip away the frameworks and see the loop: LLM decides → tool executes → result feeds back. A study path through three small open-source projects — mini-swe-agent, smolagents, and a full Mini-Agent — plus a 10-question quiz and 20 flashcards covering the entire glossary.

agent loopReActtoolsCodeAgent vs ToolCallingmemory vs contextMCP10 questions · 20 cards
Read guide
02
02 · Applied

The Claude Code WorkflowHow a real agentic coding tool works, end to end

Take the loop into production. The agentic harness, the workflow primitives (CLAUDE.md, permissions, Skills/MCP/Hooks/Subagents, context management), the Explore → Plan → Code → Commit pattern, and quantified enterprise case studies from Ramp, Rakuten, cubic and more.

agentic harnessgather→act→verifyCLAUDE.mdpermission modessubagentsenterprise cases8 questions · 16 cards
Read guide
03
03 · Advanced

Agent Infrastructure Deep DiveThe engineering layer that makes agents reliable

The 11 high-frequency areas of agent infrastructure — memory write-back, skill loading, sandboxes, the harness, loop controllability, inference & KV-cache, post-training, long-horizon execution, eval, and model-native orchestration (Kimi Swarm). Each topic explained from first principles with quiz and flashcards.

memoryskillssandboxharnessKV-cachelong-horizonevalKimi Swarm8 questions · 14 cards
Read guide
How to use this library

Suggested flow