AI agent development is one of the more demanding specializations in AI engineering, and it's growing fast. Engineers in this space build systems that perceive, reason, plan, and act across complex workflows with minimal human oversight. Udacity's AI agent development courses cover the full engineering stack for building agents in production. You'll work with LangGraph for stateful agent workflows, Google ADK and Vertex AI for cloud-native deployment, Model Context Protocol (MCP) for tool integration, and multi-agent coordination patterns for enterprise and life sciences applications. Courses include specialized tracks for financial services agents and building AI agents that connect with real-world APIs and data systems.
Build robust AI agents. Integrate tools via function calling, generate structured outputs with Pydantic, manage agent state, and utilize short-term and long-term memory. Create data-driven agents that interact with external APIs, search the web, query SQL databases, and perform agentic RAG for dynamic retrieval. Learn to evaluate agent performance for reliable, real-world applications.
This course guides learners through the essentials of implementing intelligent agents using LangGraph. Learners will explore external tools and APIs, and learn how to integrate them effectively within their agents. Key lessons include interacting with databases and implementing LangGraph Database Agents for efficient data retrieval. The course covers advanced topics like Retrieval Augmented Generation, incorporating human-in-the-loop strategies, and ensuring agent observability and reliability. Finally, learners will apply these concepts in a hands-on project, designing an Energy Advisor agent, which synthesizes their knowledge into a practical application.
This course equips learners with the essential skills and knowledge to design and implement sophisticated agent-based systems. The course covers long-term memory integration within agents, emphasizing the LangGraph framework. Participants explore multi-agent architectures and state management, focusing on effective orchestration and data routing. Through hands-on projects, learners will implement agentic systems, culminating in the development of an Autonomous Knowledge Agent.
Go beyond simple automation and learn to architect intelligent systems. In this course, you'll master the art of designing and building agentic workflows using Python. You'll explore core patterns like Prompt Chaining, Routing, and Parallelization to create teams of AI agents that can reason, plan, and act to solve complex problems. You will finish by building a complete, agentic project management system, proving your ability to translate high-level goals into powerful, adaptive AI solutions.
This course guides you through building intelligent agents using the Agent Development Kit (ADK) and Google Cloud technologies. You will start with tool definition and agent tool usage, then progress through structured outputs, state management, and memory systems (short and long-term). The course covers secure API integration, database interaction via MCP, web search with grounding, and Retrieval Augmented Generation (RAG). You'll explore multi-agent architectures and implement observability through distributed tracing. For the final project, you'll build Betty's Bird Boutique Customer Service Agent that answers bird- and store-related questions.
This course teaches the skills to design and implement effective multi-agent workflows using the Google ADK framework and Vertex AI Gemini. Starting with foundational architecture patterns, you'll progress through implementation, orchestration (sequential and parallel), custom routing logic, explicit state management, and distributed A2A communication. You'll learn to integrate external databases, implement multi-agent RAG with vector search, and build microservices-based architectures. The final project involves building a distributed banking system with multiple specialized agents communicating via A2A protocol.
This course equips you with the skills to design and implement AI agents tailored to the financial sector. Beginning with an introduction to AI agents, you will explore extending agents with tools, structured outputs, and state management. The course emphasizes practical programming in Python, covering agent memory, API integrations, and database interactions. Key concepts include short-term and long-term memory management, Agentic Retrieval Augmented Generation (RAG), and agent evaluation techniques. At the end of this course, you will apply your knowledge in a project, creating a comprehensive FinTool Analyst AI agent that synthesizes course principles.
In this course, you'll become an AI architect by learning the Model Context Protocol (MCP). You'll build sophisticated, agentic systems where multiple AI tools, databases, and servers work together as one. You will write your own Python-based MCP clients (the "brain") that use LLMs to plan and execute tasks, and your own MCP servers (the "tools") that perform specific jobs. Your final project is to build "PriceScout," an autonomous bot that can understand a request, scrape websites, query a database, and deliver a complete analysis. Master the skills to build the next generation of interconnected AI.
Agentic AI Engineer with LangChain and LangGraph is a program that teaches Python developers how to turn large‑language‑model applications into fully autonomous agents. You begin with LangChain fundamentals—prompt templates, chains, memory, and single‑tool agents—then progress to multi‑tool planning, self‑critique loops, and deployment practices. Finally, you integrate external knowledge through retrieval‑augmented generation, long‑term memory, and multi‑agent collaboration.
This course focuses on designing, implementing, and orchestrating multi-agent architectures. Starting with an introduction to the fundamentals, participants will learn the nuances of building multi-agent systems using Python. Key lessons cover agent orchestration, routing and data flow management, and state management within these systems. Practical implementations will guide students through developing sophisticated multi-agent orchestration and coordination strategies. The course also explores advanced topics such as Multi-Agent Retrieval Augmented Generation and culminates with a project on the Orphan Finder, a rare-disease variant-to-therapy matchmaker.
Building reliable agents draws on several adjacent skills. Explore Agentic AI, LLM Fine-Tuning & Training, and RAG & Vector Database courses to design agent workflows, tune the underlying models, and ground them in your own data.
Fine-tuning builds on core model knowledge. Pair this collection with Generative AI & Large Language Models, Deep Learning, and RAG & Vector Database courses to understand the models, train them well, and extend them with your own data.
Retrieval-augmented systems connect to the wider LLM toolkit. Explore AI Agent Development, Generative AI & Large Language Models, and LLM Fine-Tuning & Training to ground models in your data and improve how they respond.
Gain a solid background in AI basics to better understand Generative AI, or compliment your AI knowledge with product management skills to create AI-powered products. Explore the exciting field of Game Development and Monetization.
Explore all of Udacity’s Schools, consisting of hundreds of career-driven programs and courses that are designed to teach practical skills and help you learn to your full potential.