AI Engineering
MAF v1 — Context Providers (Python + .NET)
Add per-request context with focused providers, compose them before each LLM call, and plug in TextSearchProvider for simple RAG.
Read article
Journal
Solutions Architect specializing in Azure, AI, and enterprise cloud-native development. Writing about architecture, AI agents, and building things that scale.
AI Engineering
MAF v1 — Middleware and the Agent Pipeline (Python + .NET)
Use middleware to wrap agent runs, intercept tool calls, and redact PII before the LLM sees it in both Python and .NET safely.
AI Engineering
MAF v1 — Observability with OpenTelemetry (Python + .NET)
Wire OpenTelemetry spans for agent runs with GenAI attributes, using console export for dev and OTLP for production tracing.
Deep Dive
AI Agents: Concepts and Your First Implementation
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.
Read article
Deep Dive
Prompt Engineering for AI Agents -- Grounding, Roles, and YAML Configuration
How to write agent prompts that prevent hallucination, adapt to user roles, and stay maintainable -- with YAML-based configuration you can version-control.
Deep Dive
Building Domain-Specific Tools -- Giving Agents Real Capabilities
How to build production-quality agent tools that query databases, validate business rules, and automatically scope data to the current user.
Deep Dive
Multi-Agent Architecture: Orchestration and the A2A Protocol
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.
Deep Dive
Observability -- Tracing Multi-Agent Workflows with OpenTelemetry
How to instrument multi-agent systems with OpenTelemetry -- auto-instrumented traces across agents, LLM calls, and database queries, visualized in .NET Aspire Dashboard.
Deep Dive
Frontend: Rich Cards and Streaming Responses
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.
Deep Dive
Production Readiness: Auth, RBAC, and Deployment
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.
Deep Dive
Agent Memory -- Remembering Across Conversations
Give your agents persistent memory -- store user preferences, recall past interactions, and personalize responses across conversations.
Deep Dive
Evaluating Agent Quality -- Testing What You Cannot Unit Test
Build a repeatable evaluation pipeline for multi-agent correctness -- golden datasets, automated scoring, and CI/CD integration.