# Youssef Mrini Youssef Mrini (Senior Solutions Engineer, Databricks) was a guest on AI with Sach, a podcast hosted by Sacha Gucciardo in Montréal. ## Episode 14: Democratizing Data and AI: Insights from Databricks' Youssef Mrini (October 2024) A Databricks solutions engineer explains data and AI democratization, governance with Unity Catalog, open source compute, and why compound AI systems beat single models. Page: https://aiwithsach.com/episodes/14-democratizing-data-and-ai-insights-from-databricks/ > So it's really different from this monolithic AI models, which will rely, for example, on a single model to perform all the tasks. So you can like have this compound AI system that will use various models and traditional technologies to enhance furthermore the accuracy and the efficiency. > — at 15:58 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=958s) > And I think this part of the, the LLM, I think it did change a lot, uh, this vision because now you've seen that everyone can start, I don't know, uh, running queries or asking just simple questions. And then those questions are, uh, uh, uh, uh, SQL queries or now like English is the new language. You just need to write your prompt and it will do a lot of magic for you. > — at 1:34 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=94s) > Of course, we know that LLMs alone won't be able to solve this actually for now. You still need some human interaction over there because, uh, it can hallucinate, can give some, some awkward queries. > — at 2:00 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=120s) > And you no longer need, I mean, we want to replace, of course, data analysts, but it can answer some questions quickly without having this, um, uh, human feedback, like human interaction being there. > — at 4:03 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=243s) > I think the, the, the biggest problem may be around governance. And I think also this is a topic that Databricks tried to address. And I believe it did address successfully with unity catalog. So, and I think this is very, very important because as the company is growing, then you need to make sure that you're not giving access to some, I don't know, PII data to an entity that is not supposed to access this data. > — at 4:31 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=271s) > But again, it's all about, for example, the success of the rag application may, may be based, for example, on the checking tech, on the checking strategy, strategy of checking your following. Maybe you need to check by whenever you have, I don't know, return to new line or maybe by after a dot. And sometimes it's hard because there, this is not straightforward or say, okay, if I do this, then it will work. It's all about testing. > — at 11:31 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=691s) > So in your opinion, say, OK, maybe for translation LAMA is better than I will go for LAMA. If it's coding, then I will use Cloud because it gives me and then you can have this logic. So by combining multiple models. > — at 17:27 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=1047s) > Then these tickets can be just sent to the application. It can be translated, classified, whether it's a product issue, system issue or it's hardware. Then automatically how angry is this customer? If this customer is angry, then trigger, I don't know, an agent or like a person who's going to interact with this person > — at 20:04 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=1204s) > Just keep in mind that you need to learn something that would help you, because if you try to learn everything, that's that's impossibly going to be overwhelmed. So make sure to choose one topic and deep dive and something important. > — at 21:23 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=1283s) > So before we had ACLs by those ACLs were on force through the, the compute, which means you need to, to say, okay, with this compute, you can't access this specific table. But then you would be limited because if someone has the permission to create a new compute, then you can simply bypass those ACLs. > — at 6:02 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=362s) > So Databricks introduced since the beginning, this, um, open source, uh, frameworks. Like we can talk about Delta Lake, uh, which means you can store your data by an open source. So, um, that's not much, which means if you want to use it in another, I don't know, technology, you can use the same data. You're not locked in same thing for the engine. > — at 7:54 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=474s) > Again, handling everything through Unity Catalog with the governance, like track, for example, okay, Sasha can only use, I don't know, maximum 1000 tokens per day. So you can enforce this, you can track how many tokens Sasha use per day, do this. > — at 12:29 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=749s) > The only thing I know is we have some technology called guardrails, where, for example, you can specify a list of topics that cannot be, that will be, let's say, filtered, say, okay, we cannot do the answers. > — at 13:39 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=819s) > But how I think, regarding the question you ask, it's on the models that will be used, because we're not developing now, we have DBRX. But for the others, like if you are using LAMA, then it's on like the data that LAMA has used. > — at 14:05 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=845s) > I've been using Databricks Assistant since it was released for the first time, I think maybe 14 months ago. It saved me a lot of time because like, you know, sometimes you don't know the syntax very well. > — at 17:57 (https://www.youtube.com/watch?v=hQcryGgQ1EM&t=1077s)