Your OpenTelemetry traces stop at HTTP
OpenTelemetry auto-instrumentation gets you started, but business operations stay invisible. Claude Code helps you add custom spans, choose useful attributes, and configure sampling that survives production.
Posts
Your running Aspire app, queryable over MCP
The Aspire dashboard exposes runtime data through an MCP server. Claude Code can query the running Aspire app directly — logs, traces, and resource state — so you stop tab-switching and copying stack traces into chat.
The Aspire AppHost is your architecture map
The .NET Aspire AppHost makes your distributed application topology visible in code. That’s exactly the context Claude Code needs to be useful — from wiring new services to debugging startup failures.
Building a feature from ticket to production
What does it actually look like to build a real feature with Claude Code? Not a toy example — a complete ASP.NET Core feature from ticket to PR. Here’s the full walkthrough.
Performance optimization with Claude Code
Claude Code can spot performance issues that are easy to miss — N+1 queries, unnecessary allocations, blocking async calls, inefficient LINQ. Here’s how to use it as your performance reviewer.
Security auditing with Claude Code
Claude Code can scan your .NET codebase for security vulnerabilities — SQL injection, XSS, broken auth, insecure deserialization. Here’s how to use it as your first-pass security reviewer.
Claude Code in your CI/CD pipeline
Claude Code isn’t just for your terminal. Plug it into your CI/CD pipeline and it reviews every PR, catches issues before merge, and enforces your team’s standards automatically.
Multi-agent development: three AI agents, one feature
A single AI agent loses context after a few hours. Three specialized agents — a planner, a generator, and an evaluator — hand off structured artifacts and keep going. Anthropic’s three-agent harness changes how autonomous coding works, and .NET developers should pay attention.
The LLM Wiki: Karpathy's pattern for compounding knowledge
Andrej Karpathy dropped a GitHub Gist that got 5,000+ stars in days. Not a framework. Not a library. An idea file. Here’s what the LLM Wiki pattern is, why it’s different from RAG, and what it means for developers who use AI agents daily.
Computer Use: Claude Code controls your screen
Claude Code can now control your screen — opening apps, clicking through UI, taking screenshots. No Playwright setup, no test harness. Just tell Claude what to check and watch it work. Here’s how Computer Use works and why it matters for .NET developers.