Weekly deep dives on context engineering, agent architecture, and building software that builds itself.
Senior Software Engineer @ Microsoft (GitHub · Copilot Ecosystem)
I build agentic systems — 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 — calendars, meals, finances, health tracking, content creation, and more — all powered by GitHub Copilot CLI.
My core thesis: Make the right thing to do the easy thing to do — 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 |
|---|---|
| 🧠 Context Engineering | Prompt architecture, memory systems, skill files, and making AI agents actually useful |
| 🤖 Agent Skills & Architecture | Multi-agent orchestration, delegation patterns, agent-to-agent communication |
| 🔌 MCP Ecosystem | Model Context Protocol servers, tools, and integrations — including turning your phone into one |
| 🪝 Extension Architecture | Copilot hooks, extensions, governance layers, and guardrails for safe AI coding |
| 🔒 AI Governance | Safe agentic development, content signing, approval workflows, human-in-the-loop patterns |
| ⚙️ Platform Engineering | GitOps for AI, infrastructure-as-code for agent systems, CI/CD with AI in the loop |
📬 Get the deep dives in your inbox → Subscribe to the Newsletter
- [The Agent Infrastructure Layer Is Here](https://htek.dev/articles/the-agent-infrastructure-layer-is-here/) — My laptop is in the same room and I almost never open it. Persistent agent compute just became a product category — and trust is the only thing standing in the way.- [AI Harness v0.6.0 — Harness as Code Gets Its Reference Implementation](https://htek.dev/articles/ai-harness-v060-launch/) — v0.6.0 is the first AI Harness release where the artifact model, the agent loop, and the docs all line up with the Harness-as-Code thesis: typed capability bundles, a hardened finish_reason guard, full reference docs, and context observability you can actually inspect.- [Agents Are Your New Customer](https://htek.dev/articles/agents-are-your-new-customer/) — WorkOS's Auth.md named the category I've been building in for months. Agent-first infrastructure was already here — I just didn't have the vocabulary.- [I Answer Questions. AI Writes the Blog.](https://htek.dev/articles/i-answer-questions-ai-writes-the-blog/) — I built an interview-driven blog pipeline before Google named commodity content. Here's what it looks like when workflows — not posts — become the moat.- [I Replaced Playwright With Raw CDP](https://htek.dev/articles/i-replaced-playwright-with-raw-cdp/) — My agent chose raw CDP over Playwright for 11 viewports. Then it invented a visual validation pattern I hadn't seen: mosaic compaction.
Languages
AI & Agents
Cloud & DevOps
Frontend & Frameworks
