Wonder Lab
Wonder LabWonder Lab
  • Blog
  • Products
  • Podcast
  • Resources
  • About
Subscribe
BLOG

Knowledge Share

Technical articles, tutorials, and insights

Found 2 posts
Code AgentReActState Machine

Code Agent Anatomy (02): How Does an Agent Think and Act Round by Round?

A deep dive into MyCodeAgent's ReAct main loop: immutable state machine, dual-layer loop structure, three-verdict completion gate, and model error recovery. Understand why an agent isn't just 'call the model once and get a result' — it's a control system with feedback, guarantees, and well-defined termination conditions.

2026-08-13·10 min read
WorkflowAgentState Machine

Workflow Series (01): Foundations — Three Execution Models and Anthropic's Five Patterns

AI Workflows aren't upgraded flowcharts — they're a fundamentally different execution model. Starting from a comparison of DAG / state machine / event-driven models, this article covers Anthropic's five core patterns: Prompt Chaining, Routing, Parallelization, Orchestrator-Subagents, and Evaluator-Optimizer, and how they compose into real production workflows.

2026-06-24·7 min read
Wonder Lab
© 2026 Dongqi Chen · Wonder Lab
AboutRSSSitemap