Agent memory needs business ontologies, not smarter LLMs, argues founder

_AustinCalvert_ · x · 2026-11-21

In a reposted thread, @DanielOspina argues intelligence alone won't make LLMs capable of running a business: they must reason about how thousands of decisions, constraints, stakeholders and objectives interact, and about consequences as the business changes — a context problem.

His case: no amount of markdown files or summaries fixes this, and most agent memory systems are filing cabinets — great at retrieving facts but unable to connect the dots. The path forward is combining agent memory with business ontologies that map business logic, then reasoning over the whole dataset — which is what his startup Tortoise is building.

Original post →

More from coding & agent

coding & agent channel →