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.
More from coding & agent
- PowerShell creator's Meetup: start AI agents in an empty directory, ditch old cost estimates — dfinke · 2026-11-21
- Time awareness and async input: engineering patterns for personal agents — nikunjhanda · 2026-11-21
- MCP Events extension finalized in beta, ready for client and server adoption — dsp_ · 2026-11-21
- Using Notion as an AI context layer with an external Claude skills-db — ivanhzhao · 2026-11-21
- Gaussian splats in Godot: full tutorial plus using Fable agent to plan a pixel apartment layout — XRarchitect · 2026-11-21
- Skip agent memory: a folder structure and index beats it — NewsLewis · 2026-11-21