This is the repository for the LinkedIn Learning course Hands-On Codex: Agentic Coding Workflows. The full course is available from LinkedIn Learning.
AI coding agents can inspect repositories, modify code, run tests, and complete multistep tasks with minimal prompting. But effective delegation requires more than handing an agent a goal and hoping it all works out. In this course, Dr. Isil Berkun shows you how to use OpenAI Codex to build a habit-tracking application while learning a practical workflow for supervising AI agents.
Learn how to define acceptance criteria, provide repository guidance, review implementation plans, establish permission boundaries, verify outcomes, and recover from scope drift. Discover why engineering judgment remains essential, even as agents take on more execution. Interactive CoderPad challenges let you practice writing acceptance criteria and reviewing AI-generated code changes. By the end of this course, you'll have a repeatable framework for delegating coding tasks to AI agents while maintaining control over quality, risk, and scope.
This course includes Code Challenges powered by CoderPad. Code Challenges are interactive coding exercises with real-time feedback, so you can get hands-on coding practice alongside the course content to advance your programming skills.
Learning objectives
- Define acceptance criteria for AI-assisted development tasks.
- Delegate implementation work to an AI coding agent.
- Apply approval and permission controls to agent workflows.
- Verify AI-generated solutions against requirements.
- Recognize and recover from scope drift while maintaining project goals.
- Use a define, delegate, gate, verify, and recover workflow in agentic coding projects.
Dr. Isil Berkun
Dr. Isil Berkun is an AI educator, strategist, and the founder of DigiFab.AI.
At DigiFab.AI, Dr. Berkun focuses on AI education, helping organizations bring AI into manufacturing, robotics, aerospace, and other complex industries. She spent nearly a decade at Intel, where she led applied machine learning and deep learning projects at scale. Her LinkedIn Learning courses have reached 380,000+ learners, covering topics such as predictive analytics with Python, deep learning with Keras and TensorFlow, responsible AI, cloud-based prototyping, and agentic development with Claude Code.
Check out my other courses on LinkedIn Learning.