Writing on software design, AI and infrastructure.

All of my long-form thoughts on technology, collected in chronological order.

AGENT.md: Why your README matters more than AI configuration files

The AGENT.md specification emerged in July 2025 as an attempt to solve a real problem: developers maintaining separate configuration files for each AI coding tool (.cursorrules, .windsurfrules, CLAUDE.md, and more). Created by Sourcegraph’s Amp team, AGENT.md promises “one file, any agent”. A vendor-neutral standard to unify AI assistant configuration. But a surprising truth has emerged: the proliferation of AI configuration files has inadvertently revealed that most projects have terrible documentation, and fixing your README is more important than adopting any new standard.

Git-Driven Infrastructure: Why Configuration as Code Beats Click-and-Deploy

It was 11:47 PM on a Friday when Sarah’s phone buzzed. The authentication system was down, and customers couldn’t login and use the product. After two hours of frantic debugging, the culprit emerged: someone had “temporarily” changed a security rule in the deployment dashboard three weeks ago and forgotten to document it. The staging environment worked perfectly because it still had the old configuration. Production? Nobody remembered what settings had been changed.

Beyond Tool Calling: Understanding MCP's Three Core Interaction Types

The Model Context Protocol (MCP) changes how AI applications connect to external data and services. While most developers have experience with tool calling, MCP offers three distinct interaction types that work together to create richer experiences: prompts, resources, and tools. Understanding these three primitives and when to use each one gives you more control over building AI-powered applications.

AI revolution in cloud infrastructure: the next wave of DevOps evolution

Cloud infrastructure management has reached a complexity threshold where traditional approaches are struggling to keep pace. As organizations deploy increasingly sophisticated applications across multiple services, the challenge of maintaining efficiency, security, and performance has never been greater. Artificial Intelligence is emerging as a transformative force in this landscape, promising to revolutionize how we manage cloud infrastructure across six critical domains: cost optimization, operational efficiency, security, performance, scalability, and sustainability.