Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Module 1: Context, Scope and Delivery Challenges
- Autocomplete vs autonomous multi-step execution
- Typical AI misconceptions in software delivery
- Why better prompts alone are not enough
- Identifying participant tooling, pain points, and goals
- Choosing the right AI operating model for engineering teams
Module 2: Specification Ingestion and Structured Decomposition
- Building a structural inventory of stakeholder documents
- Requirement extraction techniques
- Chunking strategies: structural, semantic, sliding-window
- Preserving dependencies and cross-references
- Working with tables, diagrams, flowcharts, and mixed inputs
- Managing context windows effectively
Module 3: Human Judgment Boundaries
- Where human decisions remain critical
- Spotting hallucinated dependencies
- Detecting fabricated constraints and inverted logic
- Preventing unsafe helpful defaults
- Validation frameworks for traceability, consistency, completeness
Module 4: From Requirements to Code with Agentic Tools
- Architecture-first delivery model
- Component mapping and service boundaries
- API contracts as delivery anchors
- Persistent rules and constraints in AI tools
- Task instructions linked to requirements
- Minimal prompting vs constrained prompting approaches
- Contract-first backend and frontend generation
Module 5: Agentic Iteration Loop
- The self-correction spiral
- Controlled iterative delivery cycles
- Reviewing diffs and code changes
- Detecting scope creep and unauthorised modifications
- Managing limited context memory
- Using iteration history for continuous improvement
Module 6: Code Quality Enforcement
- Prompt constraints for edge cases
- Rules documents as living governance artefacts
- Automated gates with linting and static analysis
- Security scanning in AI-generated code
- Dependency and architecture conformance checks
- Human review protocol for AI outputs
Module 7: Feedback Loops and Continuous Improvement
- Feeding structured failures back into AI workflows
- Bounded iterations and stop criteria
- Logging cycles and outcomes
- Improving 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 rules appendices
- Pre-commit security scanning
- Secure SDLC controls for AI-assisted development
- Human accountability in secure delivery
Module 9: Testing Anchored to Specifications
- Generating test specifications from requirements
- Domain-language test design
- Generating test implementations safely
- Mutation testing concepts
- Specification coverage validation
- Assertion-strength review
- Diagnostic questioning models
Module 10: Maintaining the System
- Living artefacts: contracts, maps, rules, test specs
- Evolving constraints over time
- AI governance for long-term maintainability
- Technical debt prevention using AI controls
- Operating model for sustainable AI engineering teams
Requirements
Participants should possess:
- Experience in software development projects
- Understanding of application architecture fundamentals
- Familiarity with APIs, backend/frontend systems, or full-stack delivery
- Basic knowledge of Agile or iterative software delivery
- Awareness of software testing concepts
- Exposure to AI coding tools is helpful but not mandatory
- Suitable for mid-level to senior technical professionals
14 Hours
