Skip to main content

Level 2 — AI Agent Essentials

Most developers know about agents. Most developers' agents do not work. This level is the difference.

Twelve articles. The concepts where most people quit. Do not quit here.


Articles

#ArticleAgenthood Component
1What Are AI AgentsBaseAgent, ReActLoop
2Agentic FrameworksADR-008 — why Agenthood builds its own
3Build Your First AgentDeveloperAgent extending BaseAgent
4Agent WorkflowsWorkflowEngine (shipped), step types
5Agent MemoryShort/Long/Episodic/Project/Residual memory tiers + decision/provenance records (ADR-015)
6Agent EvaluationEvalRunner + BaselineComparator (shipped), EpisodeLearner (shipped), 4 metrics
7Multi-Step ReasoningReActLoop, ChainOfThought
8Multi-Agent SystemsWorkflowEngine (shipped), ParallelStep (planned), ADR-005
9Agentic RAGAgenticRAG, RetrievalClassifier
10Action PlanningPlanSkill (planned), ArchitectAgent
11Safety and GuardrailsRiskManager, ThinkingBudget, SafetyGuard
12M6 — IntelligenceMarkdownHierarchicalChunkStrategy, AgenticRAG, MemberOrchestrator, Governance docs

What Level 2 covers

The gap between "knowing about agents" and "building agents that work." These twelve concepts are where production systems diverge from demos. Every one maps to an Agenthood component that handles it correctly — or a gap in the ecosystem that Agenthood was built to fill.

Finish Level 2, then go to Level 3 — Advanced Agent Skills.