Weekly deep dives on context engineering, agent architecture, and building software that builds itself.
Senior Software Engineer @ Microsoft (GitHub Β· Copilot Ecosystem)
I build agentic systems β software that doesn't just assist developers, it collaborates with them. My work lives at the intersection of context engineering, agent governance, and platform architecture.
By day, I work on the GitHub Copilot ecosystem at Microsoft. By night, I run a 43-agent AI home assistant that manages my family's entire life β calendars, meals, finances, health tracking, content creation, and more β all powered by GitHub Copilot CLI.
My core thesis: Make the right thing to do the easy thing to do β for humans AND agents.
I write about what I learn, ship the tools I build, and teach the patterns that actually work. If you're building with AI agents, you're in the right place.
I create content at the frontier of agentic software development. Here's what I write and teach about:
| Pillar | What It Covers |
|---|---|
| π§ Context Engineering | Prompt architecture, memory systems, skill files, and making AI agents actually useful |
| π€ Agent Skills & Architecture | Multi-agent orchestration, delegation patterns, agent-to-agent communication |
| π MCP Ecosystem | Model Context Protocol servers, tools, and integrations β including turning your phone into one |
| πͺ Extension Architecture | Copilot hooks, extensions, governance layers, and guardrails for safe AI coding |
| π AI Governance | Safe agentic development, content signing, approval workflows, human-in-the-loop patterns |
| βοΈ Platform Engineering | GitOps for AI, infrastructure-as-code for agent systems, CI/CD with AI in the loop |
π¬ Get the deep dives in your inbox β Subscribe to the Newsletter
- [What Is Context Engineering? A Practical Guide from Building 50 Production AI Agents](https://htek.dev/articles/what-is-context-engineering-practical-guide-50-agents/) β Context engineering is the discipline of designing what AI agents see, remember, and act on. Here's what I learned building a 50-agent, 71-skill platform.- [Why Your AI Agents Keep Forgetting Everything (And the Fix)](https://htek.dev/articles/why-your-ai-agents-keep-forgetting-everything/) β AI agents that lose context between sessions are the #1 failure mode. Here's a preview of the 4-tier memory system I use across 43 production agents.- [Azure Weekly: Security First, Developer Experience Second](https://htek.dev/articles/azure-weekly-2026-05-13/) β Service Bus goes confidential, AKS patches kernel exploits, and azd adds multi-language hooks. This week was about hardening production workloads.- [VS Code Weekly: Agent-First Features Land in 1.120](https://htek.dev/articles/vscode-weekly-2026-05-13/) β VS Code 1.120 ships with planning for Claude agents, context size picker, and terminal secret detection. Agents are no longer experimentalβthey're the workflow.- [Stop Trusting AI Agents with Git β Start Governing Them](https://htek.dev/articles/hookflows-governed-git-for-ai-agents/) β AI agents make silent git mistakes that compound into real damage. Here's the pattern I use to block raw git and replace it with governed tools.




