Logesh·1d agoHuman-in-the-Loop AI Agents: Approval Gates, Escalation and Human OversightAgentic AI Engineering Series | Article 11/25
Ali Süleyman TOPUZ·Nov 5Memory Is an Update Problem: Three Authors, Three Answers, One DisagreementNakielski measured how long memory stays wrong. Mahmud designed a column for it. Wasowski says the real question is who gets to write. Here…
Logesh·Nov 3Context Engineering for AI Agents: What Should the Model Know at Each Step?Agentic AI Engineering Series — Article 08/25
Erwin Hermanto·Nov 3Rate Limiting AI APIs: Preventing Abuse Without Blocking Legitimate UsersThree weeks ago, one of our internal tools hit the OpenAI rate limit mid-demo. In front of a client. The culprit wasn’t abuse — it was a…
InTowards AIbyAli Süleyman TOPUZ·Nov 2Agent Memory That Learns, Forgets and Stays Permissioned: A Week of EvidenceI collected a week of design notes on agent memory, built a small store in .NET to test three of them, and found two leaks I would have…
Logesh·Nov 1How AI Agents Actually Use Tools: Function Calling, Execution and RecoveryAgentic AI Engineering Series | Article 06 of 25
Navaneethan L·Nov 1The Business Case for Domain-Specific AI ModelsGeneral-purpose AI models have never been more capable.
Logesh·Oct 31Choosing Models for AI Agents: Reasoning, Structured Outputs and Model RoutingAgentic AI Engineering Series | Article 05 of 25A response icon1A response icon1
Logesh·Oct 30How AI Agents Plan, Replan and Know When to Stop?Agentic AI Engineering Series | Article 04 of 25
AI Engineering·Oct 29LangChain Built 3 Internal Agents to Power Its First Fully Functional Company Agent
