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 versus autonomous multi-step execution
- Common misconceptions about AI in software delivery
- Why improved prompting alone is insufficient
- Identifying participant tooling, pain points, and objectives
- Selecting the appropriate AI operating model for engineering teams
Module 2: Specification Ingestion and Structured Decomposition
- Creating a structural inventory of stakeholder documents
- Techniques for requirement extraction
- Chunking strategies: structural, semantic, and sliding-window approaches
- Maintaining dependencies and cross-references
- Handling tables, diagrams, flowcharts, and mixed input formats
- Effective management of context windows
Module 3: Human Judgment Boundaries
- Identifying areas where human decision-making remains critical
- Spotting hallucinated dependencies
- Detecting fabricated constraints and inverted logic
- Avoiding unsafe helpful defaults
- Validation frameworks for traceability, consistency, and completeness
Module 4: From Requirements to Code with Agentic Tools
- The architecture-first delivery model
- Component mapping and defining service boundaries
- Using API contracts as delivery anchors
- Implementing persistent rules and constraints within AI tools
- Linking task instructions to specific requirements
- Comparing minimal prompting versus constrained prompting approaches
- Contract-first generation for backend and frontend systems
Module 5: Agentic Iteration Loop
- Navigating the self-correction spiral
- Executing controlled iterative delivery cycles
- Reviewing diffs and code changes effectively
- Detecting scope creep and unauthorized modifications
- Managing 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 with linting and static analysis
- Conducting security scans on AI-generated code
- Verifying dependency and architecture conformance
- Establishing human review protocols for AI outputs
Module 7: Feedback Loops and Continuous Improvement
- Incorporating structured failures back into AI workflows
- Defining bounded iterations and stop criteria
- Logging cycles and outcomes
- Refining rules documents over time
- Building reusable engineering intelligence
Module 8: Security Anti-Patterns in AI Delivery
- Common security risks inherent in generated code
- Techology-specific security rule appendices
- Pre-commit security scanning procedures
- Secure SDLC controls for AI-assisted development
- Maintaining human accountability in secure delivery
Module 9: Testing Anchored to Specifications
- Generating test specifications directly from requirements
- Designing tests using domain-specific language
- Safely generating test implementations
- Understanding mutation testing concepts
- 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
- Establishing AI governance for long-term maintainability
- Preventing technical debt using AI controls
- Defining an operating model for sustainable AI engineering teams
Requirements
Participants should possess:
- Experience working on software development projects
- A solid understanding of fundamental application architecture concepts
- Familiarity with APIs, backend/frontend systems, or full-stack delivery processes
- Basic knowledge of Agile or iterative software delivery methods
- Awareness of core software testing principles
- Exposure to AI coding tools is beneficial but not required
- The course is suitable for mid-level to senior technical professionals
14 Hours
