AI Assisted Software Delivery Training Course

Module 1: Context, Scope, and Delivery Challenges

• Comparing autocomplete features with autonomous multi-step execution
• Addressing common AI misconceptions in software delivery
• The limitations of relying solely on improved prompts
• Assessing participant tooling, pain points, and strategic goals
• Selecting the optimal AI operating model for engineering teams

Module 2: Specification Ingestion and Structured Decomposition

• Creating a structural inventory of stakeholder documentation
• Techniques for extracting requirements effectively
• Chunking strategies: structural, semantic, and sliding-window approaches
• Maintaining dependencies and cross-references
• Handling tables, diagrams, flowcharts, and mixed media inputs
• Effective management of context windows

Module 3: Human Judgment Boundaries

• Identifying areas where human decision-making remains essential
• Detecting hallucinated dependencies in AI outputs
• Recognizing fabricated constraints and inverted logic
• Preventing the adoption of unsafe helpful defaults
• Establishing validation frameworks for traceability, consistency, and completeness

Module 4: From Requirements to Code with Agentic Tools

• Implementing an architecture-first delivery model
• Mapping components and defining service boundaries
• Using API contracts as delivery anchors
• Defining persistent rules and constraints within AI tools
• Linking task instructions directly to requirements
• Contrasting minimal prompting with constrained prompting approaches
• Contract-first generation for backend and frontend systems

Module 5: Agentic Iteration Loop

• The self-correction spiral concept
• Managing controlled iterative delivery cycles
• Reviewing diffs and code modifications
• Identifying scope creep and unauthorized changes
• Handling limited context memory
• Leveraging iteration history for continuous improvement

Module 6: Code Quality Enforcement

• Applying prompt constraints for edge cases
• Treating rules documents as living governance artifacts
• Implementing automated gates via linting and static analysis
• Conducting security scans on AI-generated code
• Verifying dependency and architectural conformance
• Establishing human review protocols for AI outputs

Module 7: Feedback Loops and Continuous Improvement

• Reintegrating structured failures into AI workflows
• Setting bounded iterations and stop criteria
• Logging cycles and recording outcomes
• Evolving rules documents over time
• Building reusable engineering intelligence

Module 8: Security Anti-Patterns in AI Delivery

• Common security risks in generated code
• Technology-specific security rule appendices
• Implementing pre-commit security scanning
• Applying Secure SDLC controls for AI-assisted development
• Ensuring human accountability in secure delivery

Module 9: Testing Anchored to Specifications

• Deriving test specifications from requirements
• Designing tests using domain language
• Safely generating test implementations
• Concepts in mutation testing
• Validating specification coverage
• Reviewing assertion strength
• Utilizing diagnostic questioning models

Module 10: Maintaining the System

• Managing living artifacts: contracts, maps, rules, and test specs
• Evolving constraints over time
• Applying AI governance for long-term maintainability
• Preventing technical debt using AI controls
• Defining an operating model for sustainable AI engineering teams