Coming back to the note from saving reports, we now have the capability to work in Claude and save artifacts that are connected to Semantic Models. So we can come back to them later with updated data and change filters on them with the result being that they query the model for fresh data.
This is a fairly big development.
The demo
I show a report as an artifact in Claude Desktop and a trace on the Semantic Model it’s querying. We can see the queries running against the model as the report filters are updated, proving that Claude isn’t “cheating” and just loading the entire dataset into memory one time.
The timing
This capability came out on the Tuesday before my SQLBits demo on the Friday. The timing was both exciting and slightly terrifying — it validated a lot of what I was showing, but also meant some of what I’d prepared needed context that didn’t exist when I wrote it.
Part of my MCP Servers for Conversational BI talk.