Course Outline
Phase 1: Requirement Analysis – Establishing Specifications
Objective: Utilize large language models (LLMs) to derive structured requirements from ambiguous inputs.
Key Activities:
- Interpret vague product concepts or feature requests
-
Leverage AI capabilities to:
- Draft user stories and acceptance criteria
- Propose relevant personas and usage scenarios
-
Produce visual artifacts, such as diagrams generated via Mermaid or draw.io
Deliverable: A structured backlog of user stories accompanied by an initial domain model and visual representations
Phase 2: System Architecture – Design Validation
Objective: Employ AI to design and validate system architecture plans.
Key Activities:
-
Use AI to:
- Recommend architectural patterns (e.g., monolithic, microservices, serverless)
- Create high-level component and interaction diagrams
- Generate initial class or module structures
-
Conduct peer design reviews to challenge and refine architectural decisions
Deliverable: A validated architecture design and foundational code skeleton
Phase 3: Implementation – Code Development
Objective: Use AI coding assistants to implement features and enhance code quality.
Key Activities:
- Utilize GitHub Copilot or ChatGPT to develop functionality
-
Refactor AI-generated code to optimize:
- Performance
- Security
- Maintainability
-
Participate in peer clean-up challenges by identifying and resolving injected code defects
Deliverable: A functional, refactored codebase generated with AI support
Phase 4: Quality Assurance – Testing and Debugging
Objective: Generate and enhance test coverage using AI, then identify defects in peer code.
Key Activities:
-
Use AI to create:
- Unit tests
- Integration tests
- Simulations for edge cases
-
Exchange codebases with another team for AI-assisted debugging exercises
Deliverable: A comprehensive test suite, detailed bug reports, and corresponding fixes
Phase 5: Continuous Integration/Continuous Deployment – Pipeline Automation
Objective: Establish efficient CI/CD pipelines with AI assistance.
Key Activities:
-
Use AI to:
- Define workflow configurations (e.g., GitHub Actions)
- Automate build, test, and deployment procedures
-
Propose policies for anomaly detection and system rollback
Deliverable: A fully functional, AI-assisted CI/CD pipeline script or workflow configuration
Phase 6: Operations Monitoring – Log Analysis and Anomaly Detection
Objective: Analyze system logs using machine learning to detect anomalies and simulate recovery protocols.
Key Activities:
- Review pre-populated or synthetically generated log data
-
Use AI to:
- Identify anomalies and error patterns
- Recommend automated responses, such as self-healing scripts or alert notifications
-
Construct monitoring dashboards or visual summaries
Deliverable: A comprehensive monitoring plan or a simulated intelligent alerting mechanism
Final Phase: Integration – End-to-End AI-Supported SDLC Implementation
Objective: Teams integrate all learned concepts to construct a working software development life cycle (SDLC) loop for a mini-project.
Key Activities:
- Select a team mini-project (e.g., bug tracker, chatbot, microservice)
-
Apply AI tools at each SDLC stage:
- Requirements, Design, Code, Test, Deploy, Monitor
- Present project outcomes via a concise team demonstration
Evaluation through peer voting or judging to identify the most effective AI-powered pipeline
Deliverable: An end-to-end AI-enhanced SDLC implementation and a team showcase
Upon completion 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
- Utilize AI copilots to implement and refactor production-grade code
- Automate test generation and perform AI-assisted debugging
- Design intelligent CI/CD pipelines capable of detecting and reacting to anomalies
- Analyze logs with AI/ML tools to identify risks and simulate self-healing processes
- Demonstrate a fully AI-enhanced SDLC through a collaborative mini-team project
Requirements
Target Participants: Software development personnel, quality assurance specialists, system architects, DevOps practitioners, and product management leaders.
Required prerequisites for attendees include:
- Competency in the fundamental phases of the Software Development Lifecycle (SDLC).
- Demonstrated proficiency in at least one programming language, such as Python, Java, JavaScript, or C#.
-
Working knowledge of:
- Drafting and analyzing user stories and functional requirements.
- Foundational software architecture and design concepts.
- Version control systems, specifically Git.
- Developing and executing unit-level testing protocols.
- Operating or analyzing Continuous Integration/Continuous Deployment (CI/CD) workflows.
This intermediate-to-advanced curriculum is designed for technical staff currently engaged in software delivery operations, including developers, testers, DevOps engineers, architects, and product owners who require specialized training solutions for government sectors.
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
