AI Systems Engineer Journey

A Hands-On Guide to Agentic RL

Issue #06 — How RL actually trains an agent, when it's worth the cost, and the real Prime Intellect environments behind the open models

Jul 1 • Miguel Otero Pedrido

Building a Local Ambient Agent That Never Sleeps

Issue #05 — The theory, the design trade-offs, and a Kafka + Ollama agent you can run today

Jun 13 • Miguel Otero Pedrido

Building Agent Memory with Knowledge Graphs

Issue #04 — The theory, the trade-offs, and a Graphiti + Neo4j assistant you can run today

Jun 4 • Miguel Otero Pedrido

Don't Marry Your LLM Provider

Issue #03 — Why every production agent ends up behind a reverse proxy

May 19 • Miguel Otero Pedrido

Hidden Technical Debt in Agentic Systems

Issue #02 — Eleven years later, the same diagram is being redrawn

May 6 • Miguel Otero Pedrido

Welcome to The AI Systems Engineer Journey

Issue #01 — One single role behind a dozen titles

Apr 29 • Miguel Otero Pedrido

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts