October workshops are openBuild a Search AI Agent$99 early bird

Enroll now
Skip to content

SHORT COURSE 5 OF 6 · ADVANCED · 4 GUIDED LESSONS

Design connected systems.

Compare a fixed route, a bounded proposal-and-check loop, and a tool adapter. Make each boundary explicit before exploring the separate local LangGraph project. The browser exercises execute code; the local extension adds an actual model when configured.

Which architecture and tools fit the task—and which complexity can you avoid?

THE BUILD YOU ARE WORKING TOWARD

A routed checker, an independently verified proposal, and a permission-aware adapter; plus a downloadable local SDK project to extend.

  • Choose a fixed workflow when its route already fits the task.
  • Verify proposals against independent records within a stated limit.
  • Distinguish the framework, connector, model, and execution environment.
0 / 4 lessons complete
Start this courseChecking your saved progress…

Before you start

Validate tool calls, enforce permissions, inspect traces, and run an evaluation set.

Ask before changing somethingTest behavior, not confidenceFail clearly and recover carefullySee where time and calls went

Each lesson follows the same rhythm: understand three small ideas, edit and run the code, then explain the result. Take one lesson at a time.

In your browser, JavaScript and local tools really execute against inspectable inputs. Model decisions and classroom records are authored examples. The optional SDK project runs separately on your computer with its own setup.

Your lesson sequence

  1. 1Learn → build → reflectChoose a workflow before adding a teamCompare fixed sequences, routing, parallel independent work, and a model-directed loop.
  2. 2Learn → build → reflectA proposal must earn acceptanceKeep proposal generation separate from independent verification and bounded revision.
  3. 3Learn → build → reflectConnect tools without giving away controlDistinguish local function calls, MCP tool interfaces, and A2A task delegation.
  4. 4Learn → build → reflectRun with real libraries and model limitsIdentify the framework, model, runtime, license, data destination, and limits in an actual SDK project.

CONNECT THE FOUR LESSONS

Your course checkpoint

In the planner-verifier lab, make the second proposal fail the budget check. Explain the stop result. Then inspect the local project's setup and verification code.

  • Preserve the user's constraints when every proposal fails.
  • Explain why discovering a tool does not grant permission to run it.
  • Identify which files run locally and which browser operations use authored decisions.

Use these lessons’ experiment inputs and lab notebooks to record your evidence. This is a self-review prompt; only the lesson questions and code cases contribute to the progress shown above.

A proposal must earn acceptanceConnect tools without giving away controlRun with real libraries and model limits
Record and download your findings
Research into practiceThe ideas behind this short course

Original teaching informed by primary research and official engineering guidance. Our exercises isolate mechanisms so you can test them; they do not reproduce a research system or its reported performance.

Anthropic · 19 December 2024

Building effective agents

Distinguish fixed workflows from model-directed actions; start simply, use tool observations as feedback, and set stopping conditions.

The article notes that its tooling landscape has changed. Its patterns do not establish that a more autonomous or complex system is better for every task.

Google DeepMind · 14 May 2025 · research-system article

AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

Propose programs, execute and score candidates, then use evaluation feedback and a program database to guide later proposals.

This research-system description is not a classroom SDK. A bounded practice loop is an adaptation, not a reproduction of AlphaEvolve or its scientific results.

LangChain · LangGraph · Reviewed 14 September 2026 · maintained documentation

Graph API overview

Represent work as nodes and edges over state, and choose how each state key combines updates through a reducer.

An update may replace a value rather than append to it unless the configured reducer says otherwise. Drawing a graph does not establish concurrency, correct state merging, or a model connection.

LangChain · Reviewed 13 September 2026 · maintained documentation

LangGraph Graph API quickstart

Connect a model node, executable tools, returned messages, and a conditional route that continues the loop or ends the run.

The graph library does not supply a model or guarantee correct calls. The optional local toolkit needs its own model runtime; this browser simulator does not execute LangGraph.

Model Context Protocol · Specification revision 25 November 2025

Tools

Specify tool discovery, input schemas, invocation, and returned results across a client/server connection.

Schemas and annotations do not authorize an action. Clients must not trust annotations from untrusted servers; transport and access controls need separate consideration.

Hugging Face · Agents Course · Reviewed 14 September 2026 · undated public course page

Introduction to Agentic Frameworks

Compare the roles of frameworks such as smolagents, LlamaIndex, and LangGraph after understanding the agent loop; simple tasks may use ordinary code.

Framework examples are not interchangeable APIs or evidence that a framework is required. No course exercise, model-performance claim, or certification is reproduced here.

Your JavaScript really runs. The model decisions and school data are authored simulations, so you can learn without an API key. Every workspace also includes a separate real SDK example to explore next. Passing the lab’s cases is practice, not proof that an agent is ready for real-world use.