This course gives Scrum practitioners a practical, repeatable framework for integrating AI tools into every aspect of the Scrum process — from backlog refinement and persona generation to Sprint ceremonies, code quality, and retrospective pattern analysis. Attendees leave with working AI prompts, a team adoption roadmap, and an optional certification credential recognized by AgileAIDev.com.
The course spans two days with four modules, each approximately three hours. Day 1 covers Scrum foundations and AI-enhanced product discovery; Day 2 focuses on ceremony integration, code quality, TDD/DoD workflows, and certification preparation. Every module includes live tool demos using Claude.ai and structured hands-on activities with real or sample backlog data.
Modules at a glance
Module 1 · Day 1 AM
Foundations: Scrum Meets AI
~3 hours · 2 hands-on activities
- Scrum roles, events, and artifacts refresh from the Scrum Guide 2020
- AI and LLM fundamentals for Scrum practitioners
- AI augmentation vs. replacement — the human-AI partnership model
- Responsible AI: hallucination, bias, privacy, and over-reliance risks
- Aligning AI use with the five Scrum values
Module 2 · Day 1 PM
AI-Enhanced Product Discovery and Backlog
~3 hours · 2 activities + prioritization challenge
- AI-accelerated product discovery and proto-persona generation
- Writing INVEST-compliant User Stories with AI assistance
- Backlog refinement with structured AI prompts
- Epic decomposition and story splitting patterns
- WSJF and MoSCoW prioritization with AI as advisor
Module 3 · Day 2 AM
AI in Sprint Ceremonies and Team Collaboration
~3 hours · 1 applied activity per section
- AI-drafted Sprint Goals with team review and commitment
- Dependency mapping and risk flagging before Sprint start
- Daily Scrum prep, follow-up, and impediment tracking
- Sprint Review summary generation in under 30 minutes
- Retrospective pattern analysis across multiple Sprints
Module 4 · Day 2 PM
AI for Quality, Delivery
~3 hours · workflow design + exam prep
- AI-assisted code review, refactoring, and design patterns
- TDD and ATDD integration with AI tools
- Definition of Done and CI/CD pipeline evaluation
- Designing a phased AI adoption roadmap for your team
-