Solutions Architect specializing in Azure, AI, and enterprise cloud-native development. Writing about architecture, AI agents, and building things that scale.
Hold a keyboard shortcut, speak, release — audio goes to Azure OpenAI or OpenAI Whisper for transcription with an optional GPT rephrase pass via Smart Keywords, and the polished text is injected into whatever app is in focus. The Rust hot path for audio capture, accessibility permissions, overlay window, and the non-obvious bits of shipping a Tauri app on macOS.
Read article
A 12-part hands-on series on building production-ready multi-agent AI systems with Microsoft Agent Framework, A2A protocol, and a real e-commerce platform you can run locally.
What AI agents actually are, how they differ from chatbots, and a hands-on walkthrough to build your first working agent with Microsoft Agent Framework in under 30 minutes.
How to write agent prompts that prevent hallucination, adapt to user roles, and stay maintainable -- with YAML-based configuration you can version-control.
Read article
How to build production-quality agent tools that query databases, validate business rules, and automatically scope data to the current user.
How to build an orchestrator that routes requests to specialist agents, and the A2A protocol that makes agent-to-agent communication standardized, secure, and framework-independent.
How to instrument multi-agent systems with OpenTelemetry -- auto-instrumented traces across agents, LLM calls, and database queries, visualized in .NET Aspire Dashboard.
Transform agent text responses into interactive product cards and order cards, then add token-by-token streaming via SSE so the UI feels instant -- all without changing the backend agents.
JWT authentication, role-based access control, user-scoped data isolation for a multi-agent system, then Docker Compose architecture with a one-command startup for all 11 services.
Give your agents persistent memory -- store user preferences, recall past interactions, and personalize responses across conversations.
Build a repeatable evaluation pipeline for multi-agent correctness -- golden datasets, automated scoring, and CI/CD integration.
Replace hand-coded tools with Model Context Protocol servers -- standardized tool discovery and execution for any agent framework.