Course Objective & Scope
The costliest software defects happen not during typing, but when vague or incomplete requirements are translated straight into code—and coding agents amplify ambiguous requirements with silent assumptions at high speed. This course bridges product analysis and software engineering through a structured AI-assisted workflow.
Participants practise interrogating PRDs and user stories for gaps and edge cases with LLMs, generating technical design docs (RFCs/ADRs) grounded in the actual repo and Figma MCP, writing Gherkin acceptance criteria, slicing vertical tasks, and executing traceable implementation on a real feature request.
Who Should Attend?
- Software engineers and tech leads
- Technical product managers (PM/PO) and business/systems analysts
- Agile delivery teams and solution architects
- Prerequisite: experience with software delivery lifecycles and backlog/issue management
Key Takeaways
- Surface ambiguities, contradictions and missing edge cases in raw business requests before coding
- Generate technical designs and API contracts grounded in existing codebase constraints
- Translate user stories into testable Gherkin/BDD acceptance criteria
- Slice epics into small vertical tasks sized for a single human or agent PR
- Maintain end-to-end traceability from requirement to pull request and acceptance test
Curriculum
Interrogating Requirements and Ambiguity Analysis
- Stress-testing PRDs and user stories with devil's-advocate LLM prompts
- Surfacing missing business rules, permission matrices, failure states and NFRs
Technical Design Grounded in Repo and Figma Context
- Scanning the existing codebase to identify affected services, tables and screens
- Contract-first UI and API design with Figma MCP and OpenAPI/JSON Schema
Testable Acceptance Criteria and Vertical Task Slicing
- Writing Given/When/Then (Gherkin) scenarios and negative test cases
- Splitting features into independently buildable, review-sized pull request slices
Traceable Code Implementation and Acceptance Verification
- Feeding structured issue specs and acceptance criteria directly to coding agents
- Verifying generated code and tests against every item in the original requirement
Other Courses in This Category
-
Advanced training on building execution harnesses around coding agents—fast test/typecheck/lint feedback, custom tool wrappers, AST/LSP verifiers and internal eval benchmarks—so agents succeed reliably in enterprise repos.
- Live Course
- 5 modules
-
Advanced training on designing closed-loop autonomous coding cycles (generate → compile → test → observe logs/traces → repair) with convergence criteria, budget caps, anti-reward-hacking rules and nested loop architectures.
- Live Course
- 5 modules
-
Combining static analysis metrics with LLMs to understand unfamiliar codebases, detect technical debt and code smells, execute safe refactoring backed by characterization tests, and optimise performance.
- Live Course
- 5 modules
-
Developer training on generating unit, integration, contract and property-based tests with AI, using mutation testing to verify that generated test suites actually catch defects rather than mirroring implementation bugs.
- Live Course
- 5 modules
-
Solving complex software bugs through hypothesis-driven debugging with logs, stack traces, OpenTelemetry traces, git bisect and minimal reproducible examples (MREs) instead of blind trial-and-error prompting.
- Live Course
- 5 modules
-
Building living technical documentation directly from codebases: Architecture Decision Records (ADRs), C4/Mermaid diagrams, OpenAPI/SDK references, onboarding guides and automated doc-drift checks in CI/CD.
- Live Course
- 5 modules
Get in touch
