What a million-user mistake taught me about backfills, thundering herds, fan-out, and why randomized delays exist.
Every engineer has that one story they tell at team dinners. This is mine, and it starts with me hitting "run" and closing my laptop for a weekend. It's probably the biggest learning curve of my five years in engineering, and I loved it — not the incident it…
Read the guideFrontend work at Slack for agentic AI — the surfaces where agents reason, pause, and hand control back.
Working notes on designing frontends for AI, published while the ink is still wet.
Explaining the A2A protocol that powers complex orchestration systems — Agent Cards, task lifecycles, streaming subscriptions, and why an unverified card is an open door.
Why LLMs can't make the creative leap from data to discovery, and how JEPA — Yann LeCun's world-model architecture — might finally close the gap between language models and real reasoning.
Inside the graph theory powering AI agent orchestration — how DAGs, topological sorting, and Kahn's algorithm enable parallel multi-agent execution, reliable agent-to-agent communication, and dynamic MCP server loading at scale.
Offload the repetitive chaos to AI-powered tools and MCP servers, and save your focus for the tasks that actually make you a better engineer.
UI/UX research and process — starting from the person, treating the model as a material.
Working prototypes for agentic AI — interfaces that reveal an agent’s state, confidence, and thinking, beyond loaders and progress bars.
