aiml
SearchMy learning
Menu

Learning path

AI Agent Engineer

Choose a bounded workflow or agent, connect tools and retrieval, evaluate its behavior, then build a developer knowledge assistant.

  1. Models, structured output and tool calls

    Define the task and what a successful answer or action looks like. Practice model calls, structured output and permission checks before adding a framework.

    AI Fundamentals

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

    Prerequisites: Basic Python, a terminal and JSON. Local labs use Ollama; the hosted comparison also needs a Gemini API key.about 2 hours of reading

  2. Choose the system and define acceptance

    Define the task, required source support and action rules before choosing a model or framework. Start with these focused lessons; the full course adds model adaptation and operational controls.

    Building AI Systems

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

    Prerequisites: Python, basic HTTP and JSON, and AI Fundamentals. The adaptation modules add introductory linear algebra and gradients.about 9 hours of reading

  3. Build agents with one framework

    Choose Google ADK or LangGraph. Compare a fixed workflow with a model-directed agent, then use state, context limits and human approval. Completing both frameworks is optional.

    Building Agents with Google ADK 2.0

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

    Prerequisites: Python and HTTP APIs.about 6 hours of reading

    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.

    Prerequisites: Python 3.12, async Python and pytest, and a Gemini API key (or Ollama with gemma4:e2b).about 4 hours of reading

  4. Connect tools through MCP

    Build the server and client behind a tool connection, then inspect discovery, requests and remote access.

    Model Context Protocol (MCP)

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

    Prerequisites: Python 3.12 and async Python, and basic HTTP and SQL.about 2 hours of reading

  5. Retrieve documents and answer with sources

    Build the document index, retrieve useful context and check the returned source links.

    Retrieval-Augmented Generation (RAG)

    Build developer-document search with LangChain and pgvector, then answer from retrieved text and charts with checked source references.

    Prerequisites: Python, JSON, basic SQL tables, embeddings and cosine similarity.about 2 hours of reading

  6. Evaluate application changes

    Check retrieval, answers and tool use, then compare versions and block regressions.

    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.

    Prerequisites: Python and pytest basics: test functions, assert and fixtures. Live runs use a Gemini API key or a local Ollama model; replaying the recorded runs needs neither.about 2 hours of reading

  7. Bound the agent loop and verify its work

    Use the tools, retrieval and evaluations already introduced. Compare a fixed workflow with a decision loop, bound its actions, and check the resulting files independently of its completion claim.

    Agent Design, Optimization and Harnesses

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

    Prerequisites: A prior ADK or LangGraph course, tool contracts, retrieval and LLM Evals. These modules use those components rather than teach their introductions again.about 4 hours of reading

  8. Complete the developer knowledge assistant

    Connect the pieces in the capstone: a browser UI and CLI, versioned documents, collection permissions, cited answers and a local release check. Use the selected lessons when you need to revisit a component.

    Building Agentic RAG Applications

    Build a document-retrieval application with ingestion, hybrid search, context budgets, bounded search/read policies, FastAPI and MCP interfaces, and local evaluation and release controls.

    Prerequisites: Basic Python functions and JSON. Model requests and embeddings are introduced in the first module; review development and held-out splits before Module 2. Module 3 uses local UTF-8 fixtures and needs no model server.about 14 hours of reading

Optional ADK extensions

Use these after the ADK base course when your application needs them. Choosing LangGraph does not require taking these ADK courses.

Run, observe and control an ADK application

Optional after the ADK base course: serve agents, manage context and files, inspect traces and apply tool guardrails. Managed sessions and Memory Bank use Google Cloud.

Running and Deploying Agents with Google ADK 2.0

Extend context and project tooling