Course Outline
Level 1: The Discovery Dungeon – Unveiling Requirements
Objective: Leverage LLMs (ChatGPT) to distill structured requirements from ambiguous inputs.
Core Activities:
- Decode vague product concepts or feature requests
- Utilize AI to:
- Create user stories and acceptance criteria
- Propose personas and use-case scenarios
-
Produce visual assets (e.g., basic diagrams via Mermaid or draw.io)
Result: A structured user story backlog plus initial domain model/visuals
Level 2: The Design Forge – The Architect’s Blueprint
Objective: Employ AI to formulate and verify architectural strategies.
Core Activities:
- Use AI to:
- Recommend architectural patterns (monolith, microservices, serverless)
- Generate high-level component and interaction diagrams
- Establish class/module structures
-
Engage in peer design reviews to challenge and refine architectural choices
Result: A validated architecture and code skeleton
Level 3: The Code Arena – The Codex Challenge
Objective: Utilize AI copilots to develop features and enhance code quality.
Core Activities:
- Implement functionality using GitHub Copilot or ChatGPT
- Refine AI-generated code for:
- Performance
- Security
- Maintainability
-
Introduce “code smells” and engage in peer-driven cleanup exercises
Result: A functional, refactored, and AI-assisted codebase
Level 4: The Bug Swamp – Testing the Unknown
Objective: Create and optimize tests with AI, then identify defects in other teams’ code.
Core Activities:
- Leverage AI to generate:
- Unit tests
- Integration tests
- Edge case simulations
-
Swap buggy code with another team for AI-assisted debugging
Result: A test suite, bug report, and implemented fixes
Level 5: The Pipeline Portals – The Automation Gate
Objective: Configure intelligent CI/CD pipelines with AI support.
Core Activities:
- Use AI to:
- Define workflows (e.g., GitHub Actions)
- Automate build, test, and deployment processes
- Propose anomaly detection and rollback strategies
Result: A working, AI-assisted CI/CD pipeline script or flow
Level 6: The Monitoring Citadel – The Log Watchtower
Objective: Examine logs and apply ML to spot anomalies and simulate recovery.
Core Activities:
- Analyze pre-existing or generated log data
- Use AI to:
- Detect anomalies or error patterns
- Suggest automated responses (e.g., self-healing scripts, alerts)
- Build dashboards or visual summaries
Result: A monitoring plan or simulated intelligent alerting system
Final Level: The Hero’s Arena – Constructing the Premier AI-Driven SDLC
Objective: Teams integrate all learned skills to construct a functional SDLC loop for a mini-project.
Core Activities:
- Choose a team mini-project (e.g., bug tracker, chatbot, microservice)
- Apply AI at each SDLC stage:
- Requirements, Design, Code, Test, Deploy, Monitor
- Present results in a brief team demonstration
Peer voting or judging to select the most effective AI-powered pipeline
Result: An end-to-end AI-enhanced SDLC implementation and team showcase
Upon completing this workshop, participants will be equipped to:
- Utilize generative AI tools to extract and structure software requirements
- Create architectural diagrams and validate design decisions using AI
- Employ AI copilots to implement and refactor production-ready code
- Automate test creation and conduct AI-assisted debugging
- Design intelligent CI/CD pipelines capable of detecting and responding to anomalies
- Analyze logs using AI/ML tools to identify risks and simulate self-healing
- Demonstrate a fully AI-enhanced SDLC through a collaborative team project
Requirements
Target Audience: Software developers, testers, architects, DevOps engineers, and product owners
Participants are expected to have:
- A solid grasp of the Software Development Lifecycle (SDLC)
- Hands-on experience with at least one programming language (such as Python, Java, JavaScript, C#, etc.)
- Knowledge of the following areas:
- Interpreting and writing user stories or requirements
- Fundamental software design concepts
- Version control systems (e.g., Git)
- Creating and running unit tests
- Executing or interpreting CI/CD pipelines
This is an intermediate-to-advanced workshop, ideal for professionals already integrated into software delivery teams, including developers, testers, DevOps engineers, architects, and product owners.
Testimonials (1)
That i gained a knowledge regarding streamlit library from python and for sure i'll try to use it to improve applications in my team which are made in R shiny