[ Anthropic · Claude Developer Roadmap ]

The Complete Anthropic & Claude Developer Roadmap (Basics to Production)

A 15-part sequential masterclass from a Principal DevRel lens — from context-window physics, XML structural prompting, and type-safe tool use to MCP aggregation, durable agent runtimes, eval-driven engineering, and autonomous cron routines.

15 lessons15 published~135 min total
  1. 01
    Developer CorePublished

    Claude Architecture: Context Windows & Output Physics

    The model is a fixed-size attention budget. Understand context windows, output caps, and token physics before you write a single prompt.

    Read lesson →
  2. 02
    Developer CorePublished

    XML-Tag Structural Prompting

    Free-text prompts are non-deterministic. Wrap inputs in XML tags to give Claude a parseable shell and pin its attention where you want it.

    Read lesson →
  3. 03
    Developer CorePublished

    Structured JSON Outputs + Zod Contracts

    An LLM that returns prose can't drive a system. Force type-safe JSON and validate it at the boundary with Zod before it touches your code.

    Read lesson →
  4. 04
    Developer CorePublished

    Tool Use & Function Calling Mechanics

    Tool use is the model asking your runtime to act. Master the request/result loop, schema design, and parallel tool calls.

    Read lesson →
  5. 05
    Developer CorePublished

    Model Context Protocol: Server Foundations

    Stop hard-wiring integrations into prompts. Build an MCP server that exposes tools and resources Claude can discover and call.

    Read lesson →
  6. 06
    Developer CorePublished

    Adaptive Extended Thinking: Latency vs. Compute

    Reasoning isn't free. Tune adaptive extended thinking budgets to trade latency for accuracy on the problems that actually need it.

    Read lesson →
  7. 07
    Developer CorePublished

    Local-First Claude Code: CLAUDE.md & Secure CLI

    Your CLAUDE.md is the agent's standing system prompt. Engineer it — plus secure CLI boundaries — for a deterministic local workspace.

    Read lesson →
  8. 08
    Developer CorePublished

    Building Custom Claude Skills

    Turn a repeated workflow into a first-class Skill — a discoverable, versioned task script the agent invokes on demand.

    Read lesson →
  9. 09
    Developer CorePublished

    Prompt Caching Deep Dive

    Structure the static prefix so it caches, and take roughly 90% off those tokens plus a latency win on every reuse.

    Read lesson →
  10. 10
    Developer CorePublished

    Constitutional AI, Safety & Guardrails

    Safety is an architecture, not an afterthought. Layer constitutional principles, system prompts, and runtime guardrails.

    Read lesson →
  11. 11
    Enterprise ProductionPublished

    Multi-Agent Worktrees & Parallel Subagents

    One context can't hold a migration. Fan work out to isolated git worktrees and route parallel subagents that don't collide.

    Read lesson →
  12. 12
    Enterprise ProductionPublished

    Stateful Agent Runtime: Durable Objects + Redis

    Agents crash, sessions resume. Checkpoint handoffs to Durable Objects and Redis so a long-running agent survives restarts.

    Read lesson →
  13. 13
    Enterprise ProductionPublished

    Enterprise MCP Aggregation

    Production agents need many tools at once. Aggregate Postgres, Figma, and Playwright MCP servers behind one governed surface.

    Read lesson →
  14. 14
    Enterprise ProductionPublished

    Eval-Driven Prompt Engineering

    If you can't measure a prompt, you can't ship it. Build golden datasets and an eval harness that gates every prompt change.

    Read lesson →
  15. 15
    Enterprise ProductionPublished

    Autonomous Agent Routines: Cron Workflows

    The endgame is an agent that runs without you. Schedule cron-style autonomous routines with checkpoints, budgets, and kill-switches.

    Read lesson →

Shipping Claude into production?

This is the roadmap I build agents by — from token physics to autonomous routines. Let's architect yours.

Start a conversation →