No Memory, No Harness: Why the Database Is the Last Line of Defense — Kay Malcolm, Oracle
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
It argues for treating AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → memory as a distinct architectural layer with five types (short-term, long-term, episodic, procedural, semantic), and warns that spreading truth across multiple specialized stores makes agents guess rather than reconcile.
videoAgents Without Code: Skills, YAML, and Filesystems Replaced Python — Philipp Schmid, Google DeepMind
videoWe let an AI agent execute Bash and lived to talk about it — Sarah Sanders, PostHog
videoHow We Solved Agent Building — Andrew Qu, Vercel
videoEvery step you take, every call you make: the reliable agent stack — Giselle van Dongen, Restate
videoMemory Harnesses for Long-Running Research Agents — Stefania Druga, Sakana.aiAI Engineer
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQLAI Engineer
videoBuild-Time vs. Run-Time: Why Dev Tools Fail in Production — Averi Kitsch & Prerna Kakkar, GoogleAI Engineer