Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Bounded Autonomy and Guardrails with Claude and Claude Code

via Udacity

Go to class Write review

Details

Go to class

Provider

Udacity
Pricing

Paid Course
Languages

English
Certificate

Certificate Available
Effort

8 hours
Sessions

Self-Paced
Level

Intermediate

Found in

Overview

Give AI agents room to act on their own while keeping them inside firm boundaries. You'll design multi-agent systems where an orchestrator coordinates specialized agents, then build a hub-and-spoke system with the Claude Python SDK. From there you'll add guardrails that hold: deterministic hooks that enforce agent compliance no matter what the model decides to do. You'll put it all to work building an enterprise code-review orchestrator that routes work across multiple agents and keeps each one accountable.

Syllabus

Introduction to Bounded Autonomy and Guardrails with Claude and Claude Code

Start here for a tour of the course: the prerequisites you'll need, the outcomes you'll reach, and the resources that support building safe, guardrailed agents.

Introduction to Multi-Agent Orchestration

Discover how to design multi-agent AI systems using orchestrators and subagents, apply sequential, parallel, and advanced orchestration patterns, and automate complex, multi-step tasks.

Orchestrate Multi-Agent Systems

Learn to design and implement multi-agent systems using Claude Agent SDK where an orchestrator coordinates specialized subagents to automate and scale complex, multi-step business processes.

Build a Hub-and-Spoke Multi-Agent System

Assemble a multi-agent system that triages electronics-defect reports across four
cumulative exercises: scoped subagent definitions, parallel spawn with scoped
context, Pydantic-validated structured handoff, and a bounded iterative refinement
loop. By the end you have a working CLI that runs against the real Anthropic API.

Enforce Agent Compliance with Deterministic Hooks

Wrap an Anthropic-SDK banking agent in a compliance enforcement layer across three cumulative exercises: a programmatic KYC prerequisite gate, a PostToolUse hook that normalizes heterogeneous tool output, and an interception hook that redirects over-threshold transfers with a structured handoff. A comparison harness proves deterministic hooks block 100% of violations where a strong prompt cannot.