Course Format and Delivery

Delivery Method: LiveOnline
Schedule: 3 sessions of 4.5 hour
Cost: $1,350 USD

All sessions are delivered live by an expert instructor in a fully interactive online environment.

*20% off for group bookings when booking 3 or more attendees from the same organization on the same course dates in the same transaction.

About this course

This immersive 2-day bootcamp equips engineering teams with practical, hands-on skills to integrate Generative AI across every phase of the Software Development Life Cycle (SDLC)— from requirements and design to development, testing, deployment, and operations.

Designed for organizations leveraging modern AI tools such as Claude and OpenAI Codex, this course takes a platform-agnostic, engineering-first approach that focuses on real-world application rather than tool-specific training.

Participants will learn how to effectively combine:

• Claude for reasoning, analysis, and system design
• Codex and coding agents for code generation, automation, and execution

The bootcamp emphasizes “engineer-to-engineer” learning, where participants work through real SDLC scenarios using AI to accelerate delivery, improve code quality, reduce manual effort, and enhance collaboration across teams. In addition, the course introduces repeatable AI patterns, prompt engineering techniques, and governance frameworks to ensure AI is used responsibly, securely, and effectively within enterprise environments.

By the end of the session, teams will be equipped to move beyond experimentation and begin operationalizing AI within their development workflows.

What you will learn

• Understand how large language models (LLMs) work and their strengths and limitations
• Identify when to use different models (e.g., Claude vs Codex) based on SDLC tasks
• Apply prompt engineering techniques to improve AI output quality
• Use AI to translate business requirements into user stories and acceptance criteria
• Generate architecture designs, APIs, and system components, accelerate coding and refactoring
• Create and automate test cases and validation strategies & enhance CI/CD pipelines and deployment workflows
• Reduce development cycle time using AI-assisted workflows & improve code quality through AI-driven reviews and best practice enforcement
• Apply "vibe coding" and multi-step AI collaboration techniques and use AI for reasoning, validation, and iterative refinement
• Implement agent-style workflows (plan, generate ‚ validate)
• Establish guardrails for safe and compliant AI usage and understand risks such as hallucinations, bias, and data leakage
• Implement governance practices including auditability and prompt safety
• Identify high-impact AI use cases within their organization, develop a roadmap to scale AI across engineering teams & define KPIs to measure productivity, quality, and ROI

Topics Covered

Module 1 : GenAI Fundamentals for Software Teams (Multi-Model)

• How LLMs work:
• Tokens, embeddings, context windows
• Prompt-response lifecycle:
• Strengths:
• Code generation, reasoning, summarization
• Limitations:
• Hallucinations, lack of determinism, context gaps
• Model comparison:
• Claude → reasoning, long context, architecture
• Codex → code generation, automation
• AI tool ecosystem:
• Coding agents (Codex, Cursor, Cody)
• Chat-based reasoning models (Claude)
• AI testing tools
• Key Takeaways:
• When to trust AI vs validate
• Selecting the right model for the task

Hands-on Lab: Map SDLC activities → choose appropriate AI tools (Claude vs Codex)

Module 2: AI for Requirements & Product Discovery

• Converting business needs into:
• Epics, features, user stories
• Acceptance criteria (BDD/Gherkin)
• AI-assisted backlog refinement:
• Story decomposition
• Dependency mapping
• Identifying:
• Edge cases
• Missing requirements
• Persona and journey generation

Hands-on Lab: Convert a business requirement into: User stories, Acceptance criteria & Edge cases

Module 3: AI for Architecture & Design

• AI-assisted system design:
• Monolith vs microservices
• API-first design
• Generating:
• Architecture diagrams
• Data models
• API contracts (OpenAPI)
• Design trade-offs:
• Scalability, latency, cost
• Event-driven architecture patterns

Hands-on Lab: Use Claude to: Design system architecture, Generate API specifications

Module 4: AI for Development (Multi-Model Coding)

• AI-assisted coding:
• Code generation using Codex
• Refactoring legacy code
• Debugging issues
• Multi-model workflow:
• Claude → design & reasoning
• Codex → implementation.
• Vibe coding techniques:
• Iterative prompting
• Driver/navigator pattern

Hands-on Lab: Build a backend service using: Claude (design) & Codex (implementation)

Module 5: AI for Testing & Quality Engineering

• AI-assisted testing:
• Unit tests
• Integration tests
• UI automation
• Identifying:
• Boundary conditions
• Negative scenarios
• Test coverage and regression automation
• AI-driven defect detection

Hands-on Lab: Generate: Test cases from code & Automated regression suite

Module 6: AI in CI/CD & DevOps

• AI in pipelines:
• Build validation
• Test automation
• Pipeline tools:
• GitHub Actions, Jenkins
• Infrastructure as Code:
• Terraform generation using AI
• Deployment strategies:
• Blue-green
• Canary

Hands-on Lab: Generate CI/CD pipeline using Codex & Optimize using Claude

Module 7: AI for Code Review, Security & Governance

• AI-assisted code reviews:
• Code quality checks
• Best practices
• Security:
• Vulnerability detection
• Secure coding
• Governance:
• Prompt safety
• Data privacy
• AI usage policies

Hands-on Lab: Review code using AI, Identify and fix vulnerabilities

Module 8: AI for Documentation & Knowledge Management

• Generating:
• Technical documentation
• API documentation
• Knowledge management:
• Internal knowledge bases
• RAG-based assistants
• Automating documentation updates

Hands-on Lab: Generate: API docs & Developer onboarding guide

Module 9: AI in Operations & Observability

• AI-driven observability:
• Log analysis
• Metrics correlation
• Incident management:
• Root cause analysis
• Incident summarization
• ChatOps:
• AI-powered ops assistants

Hands-on Lab: Simulate production issue & Use AI for debugging and resolution

Module 10: Measuring Impact & Adoption Strategy

• Metrics:
• Lead time
• Deployment frequency
• Defect density
• MTTR
• ROI of AI adoption
• Adoption models:
• Pilot → scale → enterprise
• Governance:
• AI CoE
• Engineering guilds

Workshop: Create a 90-day AI adoption roadmap: Use cases, Tool selection, Governance model, KPIs

Key Outcomes: Participants will be able to:

• Apply AI across every phase of the SDLC
• Use Claude + Codex effectively in real engineering workflows
• Improve delivery speed, quality, and efficiency
• Reduce manual effort in coding, testing, and documentation
• Establish safe and scalable AI adoption practices