GJGlendel Joubert Fyne Acostainopenmas.hashnode.dev·Jun 18 · 11 min readAI Agents Don't Need More Memory. They Need Governed Recall.Most AI Agent Memory discussions start from the same assumption: If the agent forgets, give it more memory. More chat history. More retrieved documents. More summaries. More vector storage. More co00
GJGlendel Joubert Fyne Acostainopenmas.hashnode.dev·Jun 11 · 10 min readAI Agent Memory Is Not Chat HistoryMost AI agent systems start with a simple idea: "Let's give the Agent Memory". At first, this usually means saving previous messages, retrieving similar chunks, and injecting them back into the prom00
GJGlendel Joubert Fyne Acostainopenmas.hashnode.dev·May 30 · 9 min readBuilding AI Workflows Is Easy. Making Them Reliable Is Systems EngineeringBuilding the first version of an AI workflow is usually easy. Connect an LLM to a few tools. Add some instructions. Let the model decide what to do next. Run the demo. It works. The problem starts l00
GJGlendel Joubert Fyne Acostainopenmas.hashnode.dev·May 26 · 6 min readEvidence Beats Claims: Why AI Agents Need Runtime ProofAn AI agent saying "I did it" is not proof that anything happened. "I sent the email." "I updated the database." "I escalated the issue." "I published the post." Those are claims. In a real production00
GJGlendel Joubert Fyne Acostainopenmas.hashnode.dev·May 21 · 3 min readAI Agents Don't Have Permissions — Runtimes DoRight now, many Multi-Agent Systems are implementing permissions inside prompts. "You may access the CRM." "You are allowed to send emails." "Do not modify billing records." This is becoming one of 10
