Field notes from the studio
Practical write-ups on shipping AI agents, RAG systems, and data infrastructure into production. No fluff, just what worked.
Do You Actually Need an Agent, or Just a Workflow With an LLM in It?
Before you scope an agent project, answer one question first: does this task need model-driven judgment, or a fixed sequence of steps? Here's a buyer-usable checklist for making that call.
Read articleAll articles
18 posts
MCP Went Mainstream. Now Somebody Has to Vet the Servers.
MCP just got donated to the Linux Foundation and crossed 97 million monthly SDK downloads. Adoption is real. So is the security debt. Here's what we now check before wiring an agent to a new MCP server.
Read moreSkills, Tools, and Docs: Sorting Out Where Agent Context Actually Belongs
Anthropic's new Agent Skills primitive gives teams a third option for loading context into an agent, alongside MCP tools and RAG retrieval. Here's a practical framework for deciding which one to reach for.
Read more
How we backfill years of GA4 data into BigQuery without gaps
GA4 only keeps a rolling window of raw data, and the native BigQuery export only starts the day you turn it on. Here is the pipeline we use to reconstruct years of history, and how we prove nothing is missing.
Read more
RAG implementation: a buyer’s guide to retrieval, evaluation, and cost
Scope a RAG implementation with testable retrieval, document permissions, evaluation, and cost controls. Know what to ask before moving a knowledge assistant into production.
Read more
What it actually takes to ship an AI agent to production
The gap between an agent demo and a production agent is enormous. Here are the parts nobody shows in the demo: tight tools, guardrails, observability, and a human in the loop.
Read more
Integrating Claude into an existing product without a rewrite
You do not need to rebuild your app to add real AI. A pragmatic pattern for dropping Claude into a production codebase with evals and guardrails from day one.
Read more