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
09:00 – 09:15 — Welcome and Agenda Overview
- Daily objectives, technical configuration verification, and participant introductions
09:15 – 10:00 — Module 1: AI Code Quality and the Plan–Execute–Review Framework
- Key determinants of output quality: model selection, codebase context, tooling integration, prompt specificity, and workflow design
- Rationale for separating planning, execution, and review phases to enhance reliability over single-prompt approaches
- Decision-making framework for applying best practices throughout the session
10:00 – 10:45 — Module 2: Transitioning from Autocomplete to Agentic Workflows in Claude Code
- Differentiating Claude Code from Copilot, Cursor, and standard chat-based tools; implications for federal software development
- The agentic cycle: read, plan, act, and verify
- Live demonstration: managing multi-file tasks via a single directive
10:45 – 12:15 — Module 3: Configuration and Customization: CLAUDE.md, Skills, Hooks, Agents, and MCP
- CLAUDE.md: Establishing project memory, architectural standards, and team coding conventions
- Skills and hooks: Developing reusable slash-command workflows and event-driven automation
- Sub-agents: Mechanisms for internal delegation of parallel tasks
- MCP (Model Context Protocol): Integrating external systems—including GitHub, databases, and internal APIs—while maintaining security perimeters
- Practical exercise: configuring Claude Code and tailoring the environment to operational needs
12:15 – 12:45 — Lunch Break
12:45 – 13:45 — Case Study 1: Code Generation with Claude Code
- Delegating implementation tasks with clear context and defined acceptance criteria
- Iterative refinement: strategies for accepting outputs or redirecting instructions
- Practical exercise: end-to-end implementation of a functional requirement
13:45 – 14:45 — Case Study 2: Code Review with Claude Code
- Structuring review delegations with focus on security, design integrity, and performance
- Conducting multi-file reviews with traceability: documenting changes, rationale, and verification steps
- Practical exercise: reviewing code samples provided by participants
14:45 – 15:45 — Case Study 3: System Design with Claude Code
- Generating architectural decisions and Architecture Decision Records (ADRs) from project requirements
- Evaluating design alternatives and identifying trade-offs
- Practical exercise: designing a component or feature using Claude Code
15:45 – 16:15 — Summary and Questions
- Review of key concepts and commitment to three actionable improvements for government software development
- Open forum for questions and discussion
Requirements
- Demonstrated proficiency in at least one programming language.
- Ability to operate effectively within terminal and command-line environments.
- Fundamental understanding of Git workflows, including commits, branching, and pull requests.
- Access to a laptop with reliable internet connectivity; a Claude Pro subscription is mandatory, with onboarding instructions provided upon registration. This requirement is strictly enforced for government personnel to ensure compliance with federal data security and software licensing standards.
7 Hours
