Insights

Field notes from shipping production AI.

Essays by our team on what works, what doesn't, and what we've learned the expensive way so you don't have to.

Why most enterprise RAG systems fail (and what to do instead)

A vector database, an LLM, and a prompt template is not a product. Here is the pattern we've seen fail in a dozen engagements — and the engineering discipline that separates demo RAG from production RAG.

Admin·Mar 18, 2026·9 min read

Read the piece

Agents

Architecture

When to use an AI agent — and when a workflow is better

Everyone is building agents. Most shouldn't. A practical framework for picking the right pattern for your use case.

Feb 27, 20267 min read

Evaluation

Production

A practical guide to evaluating LLM systems in production

Offline evals get you to launch. Online evals keep you alive. Here's the evaluation stack we deploy with every production LLM system we ship.

Feb 10, 202611 min read

Strategy

Leadership

AI strategy for mid-market companies: a playbook

You don't have Google's research budget. You shouldn't try to act like you do. Here's the AI playbook we use with mid-market leaders who need to move now.

Jan 22, 20266 min read