26 Weeks to Senior AI Agent Engineer
Framework-agnostic first: raw APIs → the agent loop → RAG → memory → multi-agent → MCP → production evals → a capstone coding agent. ~5 hrs/week. Every module ends with a quiz (pass ≥ 80%) and a hands-on lab.
Phase 1 — Foundations from raw APIs
Weeks 1–5No frameworks. Raw HTTP/SDK calls only. Everything an agent does reduces to these mechanics: the message array, tool calling, structured outputs, thinking & effort, streaming, multimodal input, tokens, and robust error handling.
An agent is an LLM calling tools in a loop, with the model deciding what to do next. This module is the heart of the curriculum: the loop itself, ReAct, Anthropic's workflows-vs-agents taxonomy, planning, termination, budgets, and failure recovery.
Phase 2 — Knowledge & state
Weeks 6–11RAG shows up in nearly half of agent take-home assignments — but building a pipeline is table stakes. The senior differentiator is *measuring* it: ingest → chunk → embed → index → retrieve → rerank → generate with citations, with an evaluation harness running from day one.
"How would you design agent memory?" is now a standard senior interview question. This module gives you a real implementation to talk about: context-window budgeting, compaction, a persistent memory store with disciplined write and read paths, contradiction resolution — and defenses against memory injection, where a prompt attack becomes a persistent compromise.
Phase 3 — Scale & interoperability
Weeks 12–17Frameworks enter — you've earned them by building everything by hand. LangGraph for stateful, checkpointed, resumable agent graphs; orchestrator-worker and handoff patterns; and the senior-level judgment call interviews probe hardest: when multi-agent is worth the coordination cost (usually it isn't).
The Model Context Protocol is the USB-C of agent tooling: one protocol connecting any agent host to any tool server. You'll learn the architecture and JSON-RPC flow, build a real server and client, master the tool-design principles that make agents actually use your tools well, and run agent-generated code safely in a sandbox.