aiml

AI Agent Engineering

Build AI agents and RAG applications with diagrams, runnable Python code and tests.

17 free courses · 224 lessons

Isometric illustration: an Agent hub wired to an LLM chip, Documents, Tools, a Database and Evals, returning an Answer.

Start here

AI Agent Engineer path

8 steps · about 42 hours of reading, or about 40 hours with LangGraph

View path
  1. 01

    Models, structured output and tool calls

    AI Fundamentals

  2. 02

    Choose the system and define acceptance

    Building AI Systems

  3. 03
  4. 04

    Connect tools through MCP

    Model Context Protocol (MCP)

  5. 05

    Retrieve documents and answer with sources

    Retrieval-Augmented Generation (RAG)

  6. 06

    Evaluate application changes

    LLM Evals

  7. 07

    Bound the agent loop and verify its work

    Agent Design, Optimization and Harnesses

  8. 08

    Complete the developer knowledge assistant

    Building Agentic RAG Applications

Foundations and systems

AI Fundamentals

Build the parts of a docs assistant: model requests, context, structured output, document ranking, validated tool calls and evaluations.

about 2 hours of reading

Building AI Systems

Choose, measure and improve an AI system against explicit quality, latency, cost and failure requirements.

about 9 hours of reading

Build a Small Language Model From Scratch

Build a small one-block transformer, then train it and generate text locally.

about 5 hours of reading

LLM Inference Engineering

Implement and inspect inference request handling, cache ownership, scheduling, measurement and capacity decisions using real local runs and clearly bounded experiments.

about 8 hours of reading

Building MLOps

Take one user-return prediction application from a manual baseline through reproducible training, local release controls and outcome monitoring.

about 10 hours of reading

Agents and frameworks

Building Agents with Google ADK 2.0

Build agents, tools and multi-step workflows with Google ADK 2.0, then evaluate them.

about 6 hours of readingGoogle ADK 2.0

Connecting Agents to Tools and Services with Google ADK 2.0

Connect agents to BigQuery, databases through MCP Toolbox, Agent Search, Google Search and code execution, then add Skills and A2A.

about 2 hours of readingGoogle ADK 2.0

Running and Deploying Agents with Google ADK 2.0

Serve, observe, evaluate and deploy ADK agents with runtime controls, context caching, traces, simulated users, Cloud Run and Agent Runtime.

about 8 hours of readingGoogle ADK 2.0

Building Live and Voice Agents with Google ADK 2.0

Stream audio and screen frames with ADK live agents, handle tools and sessions, test voice callbacks, and build a custom WebSocket bridge.

about 3 hours of readingGoogle ADK 2.0

Building Agents with LangGraph

Build and compare self-contained code-review agents and workflows with LangGraph: tools, stop conditions, context and token budgets, timeouts, checkpoints, idempotent retries, verified outcomes, human approval and memory.

about 4 hours of readingLangGraph 1.2

Retrieval and context

Retrieval-Augmented Generation (RAG)

Search developer docs with LangChain and pgvector, then answer with checked source links.

about 2 hours of reading

Context and Memory Engineering for AI Agents

Assemble bounded model requests, compare context policies and maintain scoped memory with explicit provenance, retention and deletion rules.

about 5 hours of reading

Building Agentic RAG Applications

Build a documentation assistant that answers from permitted, versioned sources. Learn retrieval, bounded agent decisions, service integration and evaluation through runnable examples.

about 15 hours of reading

Tools and evaluation

Model Context Protocol (MCP)

Implement, test and secure MCP servers and clients, from stdio to a remote OAuth-protected service with scoped database access.

about 2 hours of readingMCP SDK 2.3

LLM Evals

Test LLM features with pytest and DeepEval, measure RAG and tool-call quality per stage, and gate prompt, model and dataset changes on regressions in CI.

about 2 hours of readingDeepEval 4.3

Agent Design, Optimization and Harnesses

Choose a control policy, improve it on separated task data and independently verify bounded local actions.

about 4 hours of reading