AI in the SDLC learning roadmaps
Whether you are new to AI or rolling it out across an engineering organisation, start at the stage that fits you and keep building.
Stage 1 · Getting started
Understand AI well enough to use it safely every day
New to AI and large language models
0 of 6 complete
- What Is AI? Machine Learning, Deep Learning and Generative AI Explained from Zero
- How Large Language Models Work: Tokens, Context Windows, Temperature and Hallucinations
- Prompting Fundamentals for Engineers: From Vague Requests to Reliable Results
- AI Coding Assistants Explained: Autocomplete, Chat and Agents, and How They See Your Code
- RAG, Tools, Agents and MCP Explained: How AI Gets Knowledge and Takes Action
- Choosing a Model: Capability, Cost, Latency, Privacy and Open versus Hosted
Stage 2 · Practitioner
Ship faster without lowering quality
Using AI across daily engineering work
0 of 8 complete
- AI for Requirements and User Stories: Clarify, Split and Find the Gaps
- AI-Assisted Architecture and Design: Options, Trade-offs, Design Docs and Threat Models
- Effective AI Pair Programming: A Reliable Day-to-Day Workflow
- Legacy Code and Refactoring with AI: Understand First, Pin Behaviour, Then Change
- AI for Test Generation: Meaningful Unit, Integration and Edge-Case Tests
- AI-Assisted Code Review: Faster Reviews Without Lowering the Bar
- Debugging with AI: From Stack Trace to Root Cause, Faster and Safer
- Documentation and Knowledge with AI: Docs That Stay Current and Answers People Trust
Stage 3 · Builder
Build and run AI-powered systems securely
Automating delivery and building AI features
0 of 7 complete
- Agentic Coding Workflows: Specs, Sandboxes, Guardrails and Reviewing Agent Output
- AI in CI/CD Pipelines: Smarter Builds, Failure Analysis and Safer Releases
- AI for Operations and Incident Response: Triage, Investigation and Postmortems
- AI Security Risks: Prompt Injection, Data Leakage, Insecure Output and Supply Chain
- Building Your First LLM Feature: From Idea to a Production-Ready Design
- Evaluating LLM Features: Test Sets, Metrics, LLM-as-Judge and Regression Gates
- LLMOps: Shipping, Monitoring and Operating AI Features in Production
Stage 4 · Lead and get hired
Lead AI adoption and prove your skills
Setting standards and growing your career
0 of 6 complete
- Licensing, IP, Privacy and Compliance for AI-Assisted Engineering
- An AI Usage Policy and Governance Model for Engineering Teams
- Measuring AI's Real Impact on Engineering: Beyond Lines of Code and Acceptance Rates
- An AI Adoption Playbook for Engineering Teams: From Pilot to Everyday Practice
- AI in Engineering Interview Scenarios: How to Think Aloud and Answer Well
- Careers and a Learning Plan for Engineers in the AI Era