Udacity has just launched a four-month Nanodegree Program that prepares developers to build and ship production-grade AI agent systems with Anthropic’s Claude. It is just in time for prospective participants to take advantage of its Summer Sale. Enrol today, before 15:59 PT using code “JULY4TH50” for 50% off.
Disclosure: When you make a purchase having followed a link to from this article, we may earn an affiliate commission which makes a valuable contribution to maintaining this site now and in the future.
Claude regularly comes top as the most popular LLM for agentic AI and Udacity’s latest Nanodegree Program, AI Engineering With Claude provides four project-based courses in which you build agentic AI systems with Claude across financial services, retail, manufacturing, and insurance. With expert mentor reviews you can produce a portfolio that proves you can ship.
This is a 4-month program, claimed to require 38 hours, at Intermediate level and its prereqisites are:
Agentic AI
Generative AI Fluency
Basic Python
Basic typescript
You will also need to be able to communicate fluently and professionally in written and spoken English.
The curriculum relies heavily on Claude, the Claude Agent SDK, Model Context Protocol (MCP), and Claude Code. It is also designed to help align your skills with Anthropic’s independent Claude Certified Architect Foundations exam.
AI Engineering With Claude comprises four courses, each culminating in a hands-on project:
Harness Engineering with Claude and Claude Code – 12 hours (15 lessons)
Build the engineering skills to put Claude and Claude Code to work on real systems. You’ll choose the right Claude model for a job by weighing intelligence, speed, and cost, then design agent architectures that perceive, reason, and act. Using the Claude Agent SDK, you’ll build production agents driven by stop-reason loops and engineer context strategies that keep long conversations affordable.
Project: Stand up, run, and verify four reference systems from the course, then defend each one’s design in a reflection brief grounded in your own run output.
MCP in Action – 11 hours
(11 lessons)
Connect AI applications to the tools, data, and systems they need using the Model Context Protocol (MCP). You’ll start with the architecture: how hosts, clients, and servers talk to each other. From there you’ll work through the core server features (tools, resources, and prompts) and client features like roots and sampling. You’ll build your own MCP servers, integrate them with Claude Agent SDK agents, and add custom tools of your own.
Project: Build the “PriceScout” AI agent. Write a client that uses an LLM to command custom scraper and database servers to analyze competitor pricing automatically.
Agent Evaluation and Observability with Claude – 7 hours
(8 lessons)
Make AI agents you can trust by measuring what they do and watching how they behave in production. You’ll enforce structured outputs with schemas so an agent’s responses stay predictable and machine-readable. Then you’ll build automated evaluation frameworks that score an agent’s task completion, quality, and reliability. You’ll apply these skills to real document-extraction systems: a validated, routed insurance policy pipeline and a resilient mortgage extraction system that holds up under messy input.
Project: Operate three document and risk systems you built: run them, break them on purpose, and defend their design with your own evidence.
Bounded Autonomy and Guardrails with Claude and Claude Code – 8 hours
(5 lessons)
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.
Project: Build an enterprise-ready Code Review tool using the Claude Agent SDK that uses different tools to check the quality of code in PRs.
The 50% offer, which is valid for new customers until July 7, 2026 at 15:59 PT, by using code “JULY4TH50” applies to any monthly subscription, multi-month bundle, or one-time Nanodegree purchase and even extends to the Master of Science in AI (MSAI) degree, outlined in previous news.
More Information
Related Articles
Udacity Nanodegree in Responsible AI
Masters Degree in AI from Udacity
Udacity Launches Gen AI Nanodegree
More Machine Learning From Udacity
To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Facebook or Linkedin.
Comments
Make a Comment or View Existing Comments Using Disqus
or email your comment to: comments@i-programmer.info