Ideas on AI, observability, and operations.
Practical writing on the Model Context Protocol, OpenTelemetry, durable workflows, and what it takes to run AI in production.
The future of AI Operations
AI is moving from experiments to production. The teams that win won't have the flashiest demos — they'll have the best operations. Here's where AIOps is heading.
Why every AI project needs observability
AI systems fail quietly: a slightly worse answer, a slowly rising bill, a drifting model. Without observability, you find out from your users. Here's why it's non-negotiable.
Building AI-ready APIs
Your APIs were designed for developers. AI agents are a new kind of consumer. Here's how to make your APIs something a model can use safely and well.
Temporal vs n8n
Both orchestrate workflows, but they solve different problems. Here's how to choose between Temporal's durable execution and n8n's visual automation.
OpenTelemetry for AI Agents
AI agents are distributed systems with a mind of their own. OpenTelemetry gives you the traces, metrics, and logs to actually understand what they're doing.
What is MCP?
The Model Context Protocol is becoming the USB-C of AI — a single, open standard for connecting models to your tools and data. Here's what it is and why it matters.