13 Topics

AI Agents

Learn how to build autonomous AI systems that can reason, plan, and take actions using tools and memory.

Help Make This Better

This guide is open source. Got an idea for a new topic? Found a bug? Want to improve an explanation? Every contribution helps.

Request a Topic Report a Bug Star on GitHub

Core Concepts

The Agent LoopThe observe-think-act cycle that powers autonomous agentsSep 13, 2026

B

Context AnatomyHow agents structure and manage their context windowSep 13, 2026

I

Chat CompactionHow to compress long agent chats without losing resumability, retrieval, or exact detailApr 21, 2026

Building Blocks

Tool DesignPrinciples for building tools that agents can use reliablySep 13, 2026

I

Programmatic Tool CallingLet agents write code that calls tools, reducing latency and tokensSep 13, 2026

I

Memory SystemsHow agents remember across conversations and sessionsSep 13, 2026

I

Agent SkillsReusable capabilities that extend what agents can doSep 13, 2026

I

MCP (Model Context Protocol)A standard protocol for connecting agents to external toolsSep 13, 2026

Patterns

OrchestrationCoordinating multiple agents and tools for complex tasksSep 13, 2026

Quality & Security

Agent ProblemsCommon failure modes: loops, hallucinations, and goal driftSep 13, 2026

I

Agent SecurityDefending agents against prompt injection and data exfiltrationSep 13, 2026

E

EvaluationMeasuring agent performance with benchmarks and metricsSep 13, 2026

E

Verifiable RewardsTraining LLMs and agents with objective outcome checks in realistic environmentsSep 13, 2026

Back to all topics