Course Outline
The Four-Level Personalisation Stack
Level 1 | Knows – Rules and AGENTS.md
Key areas include: • Defining project conventions and coding standards • Documenting architecture and technical constraints • Establishing tool-neutral project guidance • Ensuring consistency across development teams and AI tools
Level 2 | Can – Skills
Key areas include: • Creating reusable units of specialist knowledge • Loading contextual information on demand • Optimising context size to enhance task performance • Developing libraries of reusable workflows and expertise
Level 3 | Reaches – MCP
Key areas include: • Linking AI tools to external systems and services • Accessing repositories, databases, and documentation sources • Expanding the capabilities of AI coding assistants • Implementing secure integrations and governance controls
Level 4 | Acts – Agents
Key areas include: • Understanding autonomous AI agents and their capabilities • Autonomously reading, writing, testing, and revising code • Managing goal-driven workflows and delegated tasks • Implementing oversight and human review mechanisms for agentic systems
Day 1 | Delegation and Extending the Tools
Module 1 | From Assistant to Agent
Key areas include: • Distinguishing between AI assistants and autonomous agents • Comparing inline code completion with agentic delegation • Analysing how agentic workflows reshape development task structures • Identifying tasks suitable for agent delegation • Best practices for collaborating with autonomous AI systems
Module 2 | Delegations That Work Without Babysitting & Loops
Key areas include: • Crafting effective instructions for AI agents • Supplying adequate context and business requirements • Defining execution constraints and boundaries • Setting clear acceptance criteria and success metrics • Reducing human intervention while preserving quality • Constructing effective loops
Module 3 | Personalisation Stack and What Applies Where
Key areas include: • Understanding the four-level personalisation stack • Utilising Rules and AGENTS.md to establish project conventions • Determining applicable personalisation mechanisms for various scenarios • Managing context efficiently across tools and projects • Creating consistent AI-assisted development environments
Module 4 | Skills and Subagents
Key areas include: • Developing reusable Skills for common workflows and tasks • Packaging specialist knowledge for repeated application • Understanding the role of subagents and isolated contexts • Delegating bounded tasks to specialised agents • Enhancing efficiency through modular AI workflows
Day 2 | Connecting Tools, Parallelism and Governance
Module 5 | MCP: Connect and Build
Key areas include: • Understanding the principles of the Model Context Protocol (MCP) • Linking AI tools to external systems and services • Integrating browsers, databases, repositories, and documentation sources • Building a custom MCP server • Managing access control and security considerations
Module 6 | The Disciplined Agentic Workflow
Key areas include: • Establishing a repeatable AI-assisted development process • Brainstorming and planning with AI agents • Collaboratively building and implementing solutions • Testing and validating generated outputs • Reviewing and finalising deliverables with appropriate verification steps • Setting up effective goals
Module 7 | Parallel Development
Key areas include: • Executing multiple AI agents simultaneously • Working with isolated branches and Git worktrees • Coordinating development activities across parallel workflows • Merging and validating outputs from multiple agents • Boosting productivity through parallel execution strategies
Module 8 | Risks, Review and Governance
Key areas include: • Evaluating and vetting external Skills and MCP servers • Understanding security and governance risks • Managing permissions and access rights • Protecting sensitive data and intellectual property • Establishing review processes and quality assurance practices
Module 9 | AI Adoption in Software Development: Use Cases and Next Steps
Key areas include: • How organisations integrate AI into the Software Development Lifecycle (SDLC) • Real-world use cases and implementation examples from various industries • Common AI adoption approaches: individual, team-based, and organisation-wide enablement • Typical use cases across the SDLC: • Requirements gathering and documentation • Code generation and prototyping • Testing and quality assurance • Code review and refactoring • Documentation and knowledge management • DevOps and incident management • Governance models, policies, and security considerations • Measuring productivity and ROI of AI-assisted development • Building an internal AI adoption roadmap • Defining practical next steps for participants and their teams
Interactive Discussion Workshop
• Current challenges within the participants' development teams • Identification of high-value use cases for immediate adoption • Risks, blockers, and organisational considerations • Creation of an initial action plan for AI integration.
Requirements
Participants should possess professional development experience, proficiency with the terminal, and solid Git knowledge. Regular use of AI coding tools or completion of the Foundations course is required.
Target Audience
The course is tailored for developers actively using AI tools, technical leads managing team adoption, and platform or DevOps engineers responsible for developing Skills and MCP servers.
Testimonials (2)
Considerations about privacy and policy
Angelo Stefano Soglia - Parkino srl
Course - Claude AI for Workflow Automation and Productivity
Learning how to prompt Claude and use it to digest all of the data I have available.
