What does agentic AI in software development mean in this course?

In this course, agentic AI means using autonomous AI agents as active parts of software work rather than as simple code suggestions or fixed scripts. The focus is on how those agents support testing, CI/CD, and DevOps workflows by using context, taking focused actions, and learning from results.

When would you use agentic AI in a software workflow?

You would use it when testing, build validation, or deployment work involves repeated decisions that fixed automation handles poorly. The course focuses on situations where AI agents can respond to code changes, pipeline events, and feedback instead of only running predefined steps.

How does agentic AI fit into a broader software delivery workflow?

It fits into the build-and-test phase and extends into CI/CD and DevOps as a connected layer of analysis, action, and follow-up. In this course, agentic AI is treated as part of a repeatable delivery process, not just a one-off assistant used while writing code.

How is agentic AI in software development different from traditional automation?

Traditional automation follows predefined rules, while agentic AI is taught here as a system that can use context, adapt its next step, and coordinate specialized roles. The course emphasizes that difference in testing and pipeline work, where fixed scripts often need more manual intervention when conditions change.

Do you need any prerequisites before learning agentic AI for software workflows?

A basic understanding of software development practices, CI/CD concepts, version control, and automated testing is helpful. This is an intermediate course, so it assumes you already recognize the workflow and want to learn how agentic AI fits into it.

What tools, platforms, or methods are used in this course?

The course uses agent frameworks such as LangChain and LangGraph, and it also looks at how AI agents work alongside GitHub Copilot in CI/CD pipelines. Method-wise, the emphasis is on multi-agent orchestration and event-driven workflow integration.

What specific tasks will you practice or complete in this course?

You will practice analyzing code changes, defining specialized agent roles, generating and prioritizing tests, and connecting agents to CI/CD events and build decisions. You also work on monitoring, feedback, and human handoff points so agentic AI can support software delivery in a controlled, repeatable way.

Agentic AI Content for Practitioners: Software

位教师：Hurix Digital

包含在中

了解更多

3个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

4 小时完成

灵活的计划

自行安排学习进度

3个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

4 小时完成

灵活的计划

自行安排学习进度

您将获得的技能

您将学习的工具

要了解的详细信息

可分享的证书

添加到您的领英档案

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

该课程共有3个模块

Optimize Software Development with Agentic AI is an intermediate-level course designed for software developers, DevOps engineers, and technical leaders who want to harness the power of autonomous AI agents in their development workflows. As Gartner predicts that 33% of enterprise software applications will include agentic AI by 2028, this course provides the strategic foundation and practical skills needed to implement AI agents successfully. You'll master frameworks like LangChain and LangGraph for test automation, learn to integrate AI agents with GitHub Copilot in CI/CD pipelines, and develop comprehensive deployment strategies that avoid the common pitfalls causing 40% of agentic AI projects to fail. Through real-world case studies from Microsoft, McKinsey, and leading tech companies, hands-on exercises, and interactive coaching, you'll build the expertise to transform your development processes with intelligent automation. Whether you're optimizing testing workflows, enhancing CI/CD pipelines, or building resilient DevOps operations, this course equips you with the knowledge and tools to lead the next generation of AI-enhanced software development.

单元详情

This foundational lesson introduces learners to agentic AI in software development, focusing on frameworks like LangChain and LangGraph for test automation. Learners will explore how autonomous AI agents can revolutionize testing processes, examine real-world implementations, and understand the strategic considerations for successful adoption in development teams.

涵盖的内容

4个视频2篇阅读材料1个作业

4个视频总计20分钟

Introduction and Welcome4分钟
What Makes AI "Agentic" in Software Development?5分钟
LangChain and LangGraph: The Foundation of Agentic AI6分钟
Real-World Success Stories: Agentic AI in Testing5分钟

2篇阅读材料总计14分钟

Welcome to the Course: Course Overview4分钟
Framework Implementation Strategies for Test Automation10分钟

1个作业总计20分钟

HOL: Design Your Agentic AI Testing Framework20分钟

This lesson focuses on the strategic integration of AI agents with GitHub Copilot in continuous integration and deployment pipelines. Learners will explore how to leverage Microsoft's latest agentic AI capabilities, understand the technical considerations for seamless integration, and design workflows that enhance code quality while maintaining deployment velocity.

涵盖的内容

3个视频1篇阅读材料1个作业

3个视频总计19分钟

GitHub Copilot's Evolution: From Assistant to Agent5分钟
Technical Deep Dive: AI Agent Integration Patterns8分钟
Case Study: Successful AI Agent Integration in Production6分钟

1篇阅读材料总计6分钟

Microsoft's Agentic AI Vision for Software Development6分钟

1个作业总计15分钟

HOL: Design a CI/CD Integration Strategy for AI Agents15分钟

This final lesson focuses on the strategic deployment and long-term management of AI agents in DevOps environments. Learners will explore deployment strategies, monitoring approaches, and team adoption methodologies. The lesson emphasizes building resilient, scalable AI-enhanced DevOps practices while avoiding common pitfalls that lead to project failure.