Course Outline
Level 1: The Discovery Dungeon – The Art of Requirements
Mission: Leverage LLMs (ChatGPT) to extract structured requirements from ambiguous input.
Key Activities:
- Interpret vague product ideas or feature requests
- Utilize AI to:
- Generate user stories and acceptance criteria
- Suggest personas and usage scenarios
-
Generate visual artifacts (e.g., simple diagrams using Mermaid or draw.io)
Outcome: A structured backlog of user stories along with an initial domain model/visuals
Level 2: The Design Forge – The Architect’s Blueprint
Mission: Use AI to create and validate architectural plans.
Key Activities:
- Employ AI to:
- Propose architectural styles (monolith, microservices, serverless)
- Generate high-level component and interaction diagrams
- Scaffold class/module structures
-
Challenge each other's choices through peer design reviews
Outcome: Validated architecture and a code skeleton
Level 3: The Code Arena – The Codex Gauntlet
Mission: Utilize AI copilots to implement features and enhance code quality.
Key Activities:
- Use GitHub Copilot or ChatGPT to implement functionality
- Refactor AI-generated code for:
- Performance
- Security
- Maintainability
-
Inject “code smells” and run peer clean-up challenges
Outcome: A functional, refactored, AI-generated codebase
Level 4: The Bug Swamp – Testing the Depths
Mission: Generate and improve tests with AI, then identify bugs in peers’ code.
Key Activities:
- Use AI to generate:
- Unit tests
- Integration tests
- Edge case simulations
-
Exchange buggy code with another team for AI-assisted debugging
Outcome: A test suite, bug report, and bug fixes
Level 5: The Pipeline Portals – The Automation Gate
Mission: Configure smart CI/CD pipelines with AI assistance.
Key Activities:
- Use AI to:
- Define workflows (e.g., GitHub Actions)
- Automate build, test, and deploy steps
- Suggest anomaly detection/rollback policies
Outcome: An AI-assisted, functional CI/CD pipeline script or flow
Level 6: The Monitoring Citadel – The Log Watchtower
Mission: Analyze logs and use ML to detect anomalies and simulate recovery.
Key Activities:
- Analyze pre-populated or generated logs
- Use AI to:
- Identify anomalies or error trends
- Suggest automated responses (e.g., self-healing scripts, alerts)
- Create dashboards or visual summaries
Outcome: A monitoring plan or simulated intelligent alerting mechanism
Final Level: The Hero’s Arena – Building the Ultimate AI-Supported SDLC
Mission: Teams apply all learned concepts to build a working SDLC loop for a mini-project.
Key Activities:
- Select a team mini-project (e.g., bug tracker, chatbot, microservice)
- Apply AI at each SDLC phase:
- Requirements, Design, Code, Test, Deploy, Monitor
- Present outcomes in a short team demo
Peer voting or judging to identify the most effective AI-powered pipeline
Outcome: An end-to-end AI-enhanced SDLC implementation plus a team showcase
By the end of this workshop, participants will be able to:
- Apply generative AI tools to extract and structure software requirements
- Generate architectural diagrams and validate design choices using AI
- Use AI copilots to implement and refactor production-grade code
- Automate test generation and perform AI-assisted debugging
- Design intelligent CI/CD pipelines that detect and react to anomalies
- Analyze logs with AI/ML tools to identify risks and simulate self-healing
- Demonstrate a fully AI-enhanced SDLC through a mini team project
Requirements
Audience: Software developers, testers, architects, DevOps engineers, and product owners
Participants should possess:
- A solid grasp of the Software Development Lifecycle (SDLC)
- Practical proficiency in at least one programming language (such as Python, Java, JavaScript, C#, etc.)
- Knowledge of:
- Drafting and interpreting user stories or requirements
- Fundamental software design principles
- Version control systems (e.g., Git)
- Writing and running unit tests
- Executing or interpreting CI/CD pipelines
This is an intermediate-to-advanced level workshop. It is best suited 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