Build an AI-Ready .NET App with an AI Pair: Clean Architecture, MCP, and Agentic Workflows
Full-day, hands-on workshop: one day, the whole SDLC with an AI pair
Attendees take one .NET 10 app from an empty solution to production with Claude Code as the pair. They plan it spec-first with CLAUDE.md, AGENTS.md, and portable Agent Skills, then build it with aggregates, the Result pattern, and CQRS handlers behind a decorator pipeline, test it from unit to API level, and guard it with architecture fitness tests, hooks, and sandboxing. From there they ship it through agent-written CI with branch protection and a tagged release, run it under Aspire while the agent reads live telemetry to fix a planted bug, expose it to any AI client through an in-app MCP endpoint, and score its architecture with one agent while a second tries to disprove the score. Everyone leaves with an MIT-licensed starter kit (context-file templates, hooks, deny rules, a fitness-test seed, CI and release workflows, an Aspire seed, Agent Skills, and a mini rubric with scorer and verifier agents) to adopt in their own repo.