Building effective agents
The one I send people who think 'agent' means 'framework'. Start simple. Add complexity only when it pays.
Reading, watching, writing.
Model Context Protocol
An open standard for wiring tools and data into models. The plumbing layer agents were missing.
Your AI product needs evals
If you ship agents without evals, you are flying blind. This is the case, made plainly.
Why we replaced RAG with an LLM-native wiki
For a year our agents retrieved. Then we let them reason over a curated knowledge base instead — and most of our reliability problems quietly disappeared.
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
The original RAG paper. Worth re-reading once you've felt where retrieval breaks in production.
Why Temporal, durable execution
Durable execution is the backbone for long-lived agents. State that survives restarts, retries, and human-in-the-loop.
Running a company as a fleet of stateful agents
Domain-based AI roles instead of Scrum. How Temporal coordinates long-lived agents across billing, operations and support — and what that does to an org chart.
Opus, Sonnet or Haiku: a cost & latency model
A practical framework for model selection under real rate limits, latency budgets and unit economics — from someone who pays the bill.
Nothing here for that tag.