Course Outline
Level 1: The Discovery Dungeon – Unraveling Requirements
Objective: Employ LLMs (ChatGPT) to derive structured requirements from ambiguous inputs.
Primary Activities:
- Interpret unclear product concepts or feature requests
- Leverage AI to:
- Create user stories and acceptance criteria
- Propose personas and scenarios
-
Produce visual assets (e.g., basic diagrams using Mermaid or draw.io)
Result: A structured backlog of user stories alongside an initial domain model/visuals
Level 2: The Design Forge – The Architect’s Scroll
Objective: Utilize AI to formulate and verify architecture plans.
Primary Activities:
- Utilize AI to:
- Suggest architectural styles (monolith, microservices, serverless)
- Generate high-level component and interaction diagrams
- Create scaffolded class/module structures
-
Challenge peer choices through design reviews
Result: Validated architecture plus a code skeleton
Level 3: The Code Arena – The Codex Gauntlet
Objective: Leverage AI copilots to build features and refine code quality.
Primary Activities:
- Implement functionality using GitHub Copilot or ChatGPT
- Refactor AI-generated code for:
- Performance
- Security
- Maintainability
-
Introduce 'code smells' and engage in peer cleanup exercises
Result: A functional, refactored, AI-generated codebase
Level 4: The Bug Swamp – Testing the Darkness
Objective: Generate and enhance tests with AI, then identify defects in other teams’ code.
Primary Activities:
- Use AI to generate:
- Unit tests
- Integration tests
- Edge case simulations
-
Swap buggy code with another team for AI-assisted debugging
Result: Test suite plus bug report and fixes
Level 5: The Pipeline Portals – The Automaton Gate
Objective: Configure intelligent CI/CD pipelines with AI support.
Primary Activities:
- Use AI to:
- Define workflows (e.g., GitHub Actions)
- Automate build, test, and deployment steps
- Propose anomaly detection/rollback strategies
Result: An AI-assisted, operational CI/CD pipeline script or flow
Level 6: The Monitoring Citadel – The Watchtower of Logs
Objective: Analyze logs and employ ML to spot anomalies and simulate recovery.
Primary Activities:
- Examine pre-populated or generated logs
- Use AI to:
- Detect anomalies or error trends
- Suggest automated reactions (e.g., self-healing scripts, alerts)
- Create dashboards or visual summaries
Result: Monitoring plan or simulated intelligent alerting mechanism
Final Level: The Hero’s Arena – Constructing the Ultimate AI-Supported SDLC
Objective: Teams apply all acquired skills to build a working SDLC loop for a mini-project.
Primary Activities:
- Choose a team mini-project (e.g., bug tracker, chatbot, microservice)
- Apply AI at each SDLC phase:
- Requirements, Design, Code, Test, Deploy, Monitor
- Present results in a brief team demo
Peer voting or judging for the most effective AI-powered pipeline
Result: End-to-end AI-enhanced SDLC implementation plus team showcase
Upon completing this workshop, participants will be able to:
- Utilize generative AI tools to extract and structure software requirements
- Generate architectural diagrams and validate design decisions using AI
- Employ AI copilots to implement and refactor production-grade code
- Automate test creation and conduct AI-assisted debugging
- Design intelligent CI/CD pipelines that detect and respond 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, product owners
Participants are expected to possess:
- A solid grasp of the Software Development Lifecycle (SDLC)
- Hands-on experience with at least one programming language (e.g., Python, Java, JavaScript, C#, etc.)
- Comfort with the following areas:
- Reading and writing user stories or requirements
- Foundational software design principles
- Version control (e.g., Git)
- Writing and running unit tests
- Managing or interpreting CI/CD pipelines
This is an intermediate-to-advanced level workshop. It is particularly suitable for professionals already embedded in 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