The Library - Your business context organized by queries
by•
The Querri Library is where your data gets organized around the questions your business asks, so every answer comes from the same trusted, shared foundation.. The library learns your definitions, business context, and past analysis, so its answers are grounded in how your business actually works. And when it doesn’t know, it says so, instead of making things up.
Replies
@annachianna great questions! This is definitely all collaborative. We built permissions and workspaces in Querri to mirror the shape of real organizations which are rarely super clean. The definitions themselves get written with the Librarian agent's help, so if your operator describes something that doesn't exactly match the data, it can assist in getting that right and ask for clarification. That said, for companies that have the luxury of a data team, we see the data team also as admins within the system and able to check in on the SQL being written behind the scenes and help troubleshoot and improve as the business iterates on their dashboards and agent interactions.
The other big thing we do is have an agent run on a nightly basis and look at the questions other people are asking to surface the "hard" ones (for example involving several agent turns or involving complex joins) and then the workspace owner can review and help to clean it up.
Anyway, data is messy and probably always will be, but we've found a lot of ways to give tools to both the technical user, as well as the business user who is often in the best place to know if the numbers are actually correct or not.
Saving what the team means by “sales” is the detail that stood out. It gives people something concrete to check when two reports disagree.
@oleksii_sekundant it's made a huge difference to both accuracy and usability of the whole platform. You can't run a business on AI without trust!
Really like this approach. Building AI around a business’s actual context rather than just giving it access to data feels like a meaningful step forward. Good stuff!
@stephen_doyin yes, that's what separates Querri from other data tools because now Querri can give accurate and relevant responses as opposed to spitting out numbers that dont make sense.