Overview

Google, IBM & Meta Certificates – 40% Off

One Coursera Plus subscription covers most Professional Certificates on Coursera.

Strong agentic AI engineering starts with judgment: knowing when an agent beats a simple prompt, and how the runtime beneath it works. This course builds that foundation with the GitHub Copilot SDK. You'll evaluate real tasks for agentic automation, stand up an SDK development environment, build a working single-task agent, and trace the SDK's internal runtime to debug with confidence. By the end, you'll be able to: - Evaluate tasks for agentic automation vs. prompt-response approaches - Configure and initialize a Copilot SDK development environment - Build single-task agents using the SDK's agentic loop - Analyze the SDK's JSON-RPC runtime to diagnose issues You'll work hands-on with the GitHub Copilot SDK (Python and Node.js/TypeScript), the GitHub Copilot CLI, VS Code, and Git/GitHub. This course is intended for learners with at least 2 years of programming experience in Python or Node.js/TypeScript, with familiarity with Git workflows, REST APIs, and command-line tools. No prior experience with AI agents or the Copilot SDK is required. This course is designed for: - Software developers and ML engineers who want to build agentic AI applications. - Technical professionals with at least 2 years of programming experience in Python or Node.js/TypeScript. - Developers who are comfortable working with REST APIs, Git workflows, and command-line tools. - Professionals who want to understand when to use agentic AI and begin building agents with the GitHub Copilot SDK. No prior experience with AI agents or the GitHub Copilot SDK is required.

Syllabus

Designing Session Lifecycles
- Design and implement complete session lifecycles for conversational agent applications using the Copilot Software Development Kit (SDK). Learn to create, configure, persist, and gracefully tear down sessions, the foundational state management pattern that every multi-turn agent depends on.
Implementing Multi-Turn Context Management
- Implement context management strategies that keep agents coherent across long, multi-turn sessions. This course addresses two distinct challenges: managing conversation history within the model's context window as sessions grow long, and maintaining structured application state that persists meaningful information beyond what conversation history alone can capture. You'll learn the boundary between what the Software Development Kit (SDK) handles automatically (message history within a session) and what your application must manage (summarization, structured state, and cross-session persistence).
Streaming Responses & Event Handling
- Implement real-time streaming to progressively render agent responses and tool execution events in a user interface. Agent responses that arrive as a single block after a multi-second wait feel unresponsive; the same response streamed token by token, with tool execution status surfaced as it happens, feels immediate and trustworthy. Learn to subscribe to Software Development Kit (SDK) event streams and handle different event types: text chunks, tool invocations, execution status, and errors. Build rendering logic that keeps users informed during long agent operations, including graceful handling of mid-stream failures and user cancellation.
Building Custom Agents & System Prompts
- Define custom agents with specialized system prompts, restricted tool access, and behavioral constraints that the Copilot runtime can delegate to during task execution. Learn to design agents as modular, reusable components, each with a scoped identity and capability set.
Project Module: Multi-Turn Conversational Agent
- Build a multi-turn conversational agent that combines session lifecycle management, context persistence, streaming responses, and custom agent delegation into a cohesive application. This project integrates the session, context, streaming, and custom-agent skills developed across this long course into a portfolio-ready deliverable.