Skip to main content

Agent

AI Agent system that uses LLMs as core reasoning engine, augmented with tools, memory, and instructions.

Fundamentals​

  • Principles - Agent components and first-principles thinking
  • Patterns - Agent-native design and context management patterns
  • Instructions - Writing effective agent system prompts
  • Tool - Tool calling, bash scripts, and codegen

Operations​

  • Context - Context engineering and memory systems
  • Workflow - Plan, debug, TDD, and compound engineering

Orchestration​

  • Multi-Agent - Multi-agent orchestration patterns
  • Guardrails - Safety guardrails for agent execution
  • Eval - Evaluation methods, trace analysis, and benchmarks

Resources​

  • Ecosystem - SDKs, frameworks, and agent tools