## Metadata - Author: [[jason-ganz|Jason Ganz]] - Full Title:: Should We Even Care About Using LLMs to Query Enterprise Data? - Category:: #🗞️Articles - Document Tags:: [[Data team topologies|Data Team Topologies]], [[Ser data driven no es de guapas|Ser Data Driven No Es De Guapas]], [[Foundation models|Foundation Models]] - URL:: https://roundup.getdbt.com/p/should-we-even-care-about-using-llms - Finished date:: [[2023-12-18]] ## Highlights Touche >  ([View Highlight](https://read.readwise.io/read/01hhwxnadh6f8dh2g7bwnq19vk)) > nothing kills a flow state like the stakeholders dilemma. More often than I’d care to admit, I end up not going looking for that piece of data that would complement (or more importantly contradict) my point. ([View Highlight](https://read.readwise.io/read/01hhwxrppzwm6nx6x58sjy6jh4)) This would be great >  ([View Highlight](https://read.readwise.io/read/01hhwxrvrnvty262dvn2xxd00x)) > very smart people were asking whether we should even care about text to SQL or text to trusted dataset. ([View Highlight](https://read.readwise.io/read/01hmb060hk53zfgtxa9nss9mrg)) > This would take some pressure off data teams and give more agency to the rest of the organization. I expect the real, if modest gains from this would be enough for many organizations to consider this a worthwhile pursuit. ([View Highlight](https://read.readwise.io/read/01hmb06nrx7ez2ke5kg6gyedwt)) > I call this *the stakeholders dilemma -* do I bother the data team for a request, do I try and pull it myself or do I handwave away the question and not bring in the numbers I was looking for? ([View Highlight](https://read.readwise.io/read/01hmb0d6254ryf4f1amf45r5s9)) > More often than I’d care to admit, I end up not going looking for that piece of data that would complement (or more importantly contradict) my point. ([View Highlight](https://read.readwise.io/read/01hmb0d0nzsx18w3ytw1q1qca5)) > imagine an interface that connects both to the document I’m writing and to my Semantic Layer - allowing it to make some pretty good guesses about the types of data we have that would be most relevant to what I’m writing about. ([View Highlight](https://read.readwise.io/read/01hmb0e9agfeyqz7rjjbtamnew)) > If we move up the ladder of abstraction one more time, we get LLM systems that have a specific goal and the ability to interact in the digital (or physical world) in some way. This doesn’t need to be as sci-fi as it sounds - you can imagine systems with relatively bounded goals that can operate somewhat independently. > • An advertising agent that can test and deploy new creative and then measures the efficacy of new campaigns > • A support agent that not only answers a ticket, but validates that the expected behaviors in product follow the resolution of a ticket (or escalates if not) > • (Slightly more speculative) An inventory control agent which is able to suggest when products in a physical store need to be restocked or have their schedules updated ([View Highlight](https://read.readwise.io/read/01hmb0h1bnbetp63qzwdar5rw4))