Your Semantic Layer is not a Context Layer. And neither of them is an Ontology.
If you are building data workflows for autonomous AI agents, it helps to know the difference.
-Semantic Layer: The rigid logic compiling to SQL (metrics, dimensions).
-Context Layer: The unstructured human knowledge (docs, wikis) agents desperately need to make decisions.
-Ontology: The "digital twin" mapping your real-world business entities.
Dive into Simon Späti's new primer to see how to organize your data architecture for the Agentic Era: https://t.co/occq09z3iP
@JSON_JEFF@sattyyouneed It’s getting more fun to use. I wish I had more control over some of the configs but when you treat it like paperclip, it’s really powerful
Helpful — one gap left on my end: the LiteParse guide states top-left origin, but I can’t find the origin corner (or the points/1-based/rotation contract) stated anywhere in the LlamaParse parse docs themselves, only in the granular-bboxes example. Is the coordinate system documented normatively for LlamaParse, and is it identical across cost_effective/agentic/agentic_plus?
@matsonj@Tamurphy Feels like with the enhancements to MCP, it would allow for an even better method to allow certain provisioned domain experts to write back skill updates