Anthropic's official "Code with Claude" workshop materials — nine hands-on courses on skills, MCP, evals and Claude Managed Agents.
- official
- workshops
- anthropic
- managed-agents
Building Effective Agents
Anthropic's canonical essay on agent design — workflows vs agents, and five composable patterns.
Anthropic's most-cited engineering essay on building agents: the workflow-versus-agents distinction, five composable patterns (prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizers), and the discipline of starting with the simplest thing that works. Required reading before adopting any agent framework — most "agent problems" are solved by the patterns here.
What it does
- Anthropic's canonical engineering post on when to use agents vs simpler workflows
- Defines the workflow/agent taxonomy: prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer, autonomous agents
- Core advice: start with the simplest thing that works; add agentic complexity only when it pays
When to use it
Required reading before architecting anything agentic — it gives you the vocabulary to describe patterns and the judgment to know when NOT to build an agent.
Getting started
No install — it's an engineering blog post on anthropic.com.
Things to know
A guidance document, not code — pair it with the cookbook or Agent SDK docs for implementation.
Charted
Related on the map
Anthropic's announcement of Fable 5.1 and Mythos 5.1 — one base model, two guardrail postures.
- official
- models
- announcement
- fable
12-Factor Agents
GuideHumanLayer's 12 design principles for production-grade LLM agents — the closest thing to a 'best practices' manifesto.
- agents
- best-practices
- production
- principles