AI-Native Software Engineering with Coding Agents
Published 10/2026
Created by Baalu Mukkara
MP4 | Video: h264, 1920×1080 | Audio: AAC, 44.1 KHz, 2 Ch
Level: Intermediate | Genre: eLearning | Language: English | Duration: 107 Lectures ( 13h 24m ) | Size: 9.3 GB
Specs, tests, code review, security and legacy Java: ship production software with Claude Code, Cursor and Copilot
What you’ll learn
Give a coding agent the context it needs with one AGENTS md file that Claude Code, Cursor and GitHub Copilot all read
Turn tickets into agent-ready specs and plans, and slice work into pull requests a human can review properly
Drive features test-first with an agent, and catch agents that weaken or edit tests to get a green build
Review agent-written pull requests risk-first and catch scope creep, invented APIs and performance traps CI misses
Lock down agent permissions, keep secrets out of context and add a CI security gate for agent-written code
Map, test and safely modernise legacy Java code with an agent using characterisation tests and the strangler pattern
Run coding agents unattended in CI with budgets, kill switches and a human merge gate
Measure the real impact of coding agents on your team and write a team agent policy and 90-day rollout plan
Requirements
At least one year of professional programming in any language
Comfortable with Git, the command line and basic automated tests
Able to read Python and Java code (you do not need to be fluent in both)
A computer that can run Python, Java and Docker; Windows users need WSL
No paid AI subscription is required: every lab can be completed with a free tier or by hand against the same tests
Description
Coding agents now write a large share of the first draft of software. Most teams adopting them hit the same problems: pull requests too big to review, tests that pass for the wrong reason, agents that ignore conventions, keys in context files, and managers asking whether any of it made delivery faster.
This course teaches the engineering discipline that makes coding agents work in a professional team. You will learn to give an agent the context and specification it needs, drive the work with tests it cannot argue with, review its output like a senior engineer, keep it inside safe limits, use it on legacy code, run it in your CI pipeline, and measure whether it improved delivery.
You work throughout on OrderHub Brownfield, a realistic codebase with history: a modern Python service and an older Java billing module with a nightly batch and undocumented rules. Every lab has a starting point and a solution, and acceptance tests decide when you are done, whichever tool you use.
You will learn to
Write one shared context file (AGENTS md) that Claude Code, Cursor and GitHub Copilot all read, and avoid the precedence traps
Turn tickets into agent-ready specs and plans, and slice work so it can be reviewed
Drive features test-first, and catch agents that weaken tests to get a green build
Review agent pull requests risk-first, including performance traps and invented APIs
Lock down agent permissions and add a CI security gate
Map, pin and strangle legacy Java code safely with an agent
Run unattended agents in CI with budgets, kill switches and a human merge gate
Measure pull-request size, review time, rework and cost, and run a fair pilot
Write a team agent policy and a 90-day rollout plan
About the tools: the course is tool-neutral at its core. Most live sessions use Claude Code, and the same workflows are shown in Cursor and GitHub Copilot. Tool-specific lectures are dated and updated as the tools change.
About the evidence: this course does not promise that you will code ten times faster. It shows you what the research found, including where AI tools slowed experienced developers down, and gives you a way to measure your own results.
Who this course is for
Professional developers and senior engineers whose teams use, or are about to use, coding agents
Tech leads who set how their team works with Claude Code, Cursor or GitHub Copilot
Engineering managers who have to show whether agent licences improved delivery
Not for first-time programmers, or anyone who wants to build an app without learning to code
CAINATIVEOFTWAREENGINEERINGWIT
you must be registered member to see linkes Register Now