Sponsored By: Glean | Build with Genie Code and Glean

Summary

Genie Code and Glean MCP work together to combine governed Databricks query results with enterprise context from documents, tickets, Slack messages, CRM records, and email—turning correct queries into trusted, contextual answers.
Glean builds a personal knowledge graph for each employee that understands their work context, then surfaces relevant institutional knowledge directly into Databricks dashboards so analytics teams can interpret metrics with business meaning.
This video walks through a live demo where Genie Code updates a support dashboard by pulling churn context from Glean, showing how teams can move from a raw metric to a governed, explainable answer without leaving the Databricks interface.

Chapters

FAQs

What problem does the Genie Code and Glean integration solve?

Databricks dashboards can surface accurate metrics, but those numbers lack the business context—such as recent support tickets, Slack conversations, or CRM notes—that makes them actionable. This integration brings Glean's enterprise knowledge graph into the Databricks interface so analytics teams can understand not just what the data shows but why it matters.

What is Glean and how does its knowledge graph work?

Glean is an enterprise search and knowledge platform that indexes content across a company's tools—email, Slack, documents, tickets, and CRM—and builds a personal knowledge graph for each employee. This video explains how Glean understands an individual's work context to surface the most relevant information alongside their Databricks analytics.

How does Glean MCP connect to Genie Code in Databricks?

Glean integrates with Genie Code through MCP (Model Context Protocol) patterns that allow Genie to pull relevant enterprise context from Glean at query time. Queries remain grounded in Databricks governance while Glean contributes the surrounding business context, and all results are surfaced in the Databricks UI that teams already use.

What does the live demo in this video show?

The demo shows a support dashboard being updated by asking Genie Code to incorporate churn-related context retrieved from Glean. Genie pulls metrics from Databricks tables and combines them with Glean's enterprise knowledge, producing a dashboard that reflects both governed data and real business context without requiring any manual data stitching.

Full transcript

[00:09] Okay. Hi everyone. Welcome in. Thank you for joining here today. Before I dive in, couple housekeeping items, right? Our looking forward statement. Um just keeping this in mind as we go through um our session here
[00:21] today. And then of course to complete your your feedback surveys. This is important for us, for me as a speaker as well as for the overall feedback of the
[00:33] summit. So with that, let's get into the content I have prepared for you today. And then if we could get my clock started, that'd be great as well. Thank you. Um, so hi everyone. My name is Jess
[00:47] Urick. I am a partner SE here with Glean. And I'm very excited to get to talk to you about this amazing partnership we have with data bricks. but specifically the genie code and glean integration. So this is actually
[01:00] going to allow your enterprise to move faster within the datab bricks UI. So a little bit about what we'll talk about here today. We're going to talk about what you can build with Genieode.
[01:12] I'll give you a very high level view here into some of the things we can do with Genieode. And then we're really going to focus on how Glean's context supervis supercharges that data analytics specifically those data points
[01:26] within our data bricks ecosystem. We'll talk about some use cases between Genieode and Glean and I'll even get into a demo where you'll see this in action. We'll walk through a different couple scenarios of ways we can use
[01:39] these tools together. Now, as I mentioned, my name is Jess Urick. I am a partner SE here with Glean. I specialize with our our ISV partners. So, I work really closely with
[01:51] data bricks and have been spending a lot of time building out this content, but most importantly building out these integrations with them. So, I'm excited to get to talk to you all here today. So let's talk a little bit about some of
[02:04] the struggles we see when it comes to analytics, when it comes to building out performance metrics and understanding honestly just what's going on with all of these different data tables and
[02:16] resources we have within data bricks. Now overall we can put together dashboards right we can figure out metrics we can make pretty visualizations but how do we actually make them impactful? How do we translate
[02:31] all of this information with our business context in mind? Which metric definitions are the most important? And how do I know that this metric definition is most important for this team versus a different team who uses
[02:43] the same definition? Which of these slices and filters is going to matter most? How can I easily take one dashboard and slice and dice it to make it more easy for my regional
[02:55] segments or specific groups and users? How can I leverage this information and make these changes quickly? And ultimately, what is the narrative I'm trying to support? What is the action
[03:07] I'm trying to perform? What is the overall outcome when this dashboard is done? When these resources are ready to go and be presented, what is the overall goal that I'm trying to support?
[03:21] So this is where Genie code and data bricks really come together with Glean because we bring the enterprise context, they bring the data analytics. So, we're
[03:33] able to build new KPI dashboards from fuzzy business asks by taking a very random ask from a sales leader, for example, pulling in the business context of why where this sales leader works,
[03:45] why they're important, and turning a very random ask to track of their KPIs into an outcome. We can pair dashboards with the Genie experience for follow-ups. You're not having to constantly context switch to
[03:59] understand and bring in what you know is the information you need to do your job. You can go into uh Genie space, work with stakeholders, and ask questions instead of filing a ticket
[04:12] for upgrading. Instead of having to take all this time to update a new dashboard with the newest updates, with the latest metrics, with all of this backend information, what we want to make sure we do is do it
[04:25] right away without having to go back and forth and look at the Slack message and the email and all of these different resources that we need to understand the data and then make the real context changes on those dashboards
[04:39] and ultimately turn an investigation into a reusable monitor. ing view, right? So, when we start to notice that there's something going on, when we start to do ad hoc information, we're able to stand it up much faster. Instead
[04:53] of taking hours to sift through data, we can actually turn this into something usable by pulling in the metrics, but then adding the business context as to how can we make this a long living
[05:05] document. What is this going to help each team for their review cycles, for example. So that's a little bit about how they come together. So let's take them and break it down a little bit. Starting
[05:18] with Glean. So what is Glean? If you're not familiar with Glean, we we really work with your enterprise context to bring you a deep understanding of your business.
[05:31] Now, this started back in 2019 with the vision for a search and it since progressed into this enterprise AI assistant. Everyone in your organization
[05:43] now gets their very own personal assistant where they can now go and ask information. And then it transformed into this agentic platform where now we have horizontal agents across our business so that teams in sales,
[05:56] engineering, legal all can build on one platform. And all of this is built on a single system of context. Integrating into tools and resources you already under use and understand today, but bringing
[06:09] together a context layer that's a deep understanding of the business and the personas behind the business, the individual users and that breakdown.
[06:25] So here's a glimpse into the Glean platform. At the very bottom, you're going to notice we start to collect all sorts of understanding from the enterprise sources themselves. We connect natively into these data sources
[06:37] and we're governed by those data sources. So, we inherit those native permissions. I always like to say if I can't see it when I go to find it in the native source, I'm not going to see it in Gleam. We of course have our own
[06:49] protect platform making sure we're compliant governed specifically that there are agent guard rails in place. But the most differentiating piece for Glean when it comes to our tool versus
[07:02] others or even how are you going to get the most out of the Glean platform really comes down to the enterprise context that we provide there. Glean's enterprise context can be broken down into two forms. First you have the
[07:16] enterprise or the business context. That's going to be what data sources do you have? Are you using teams? Are you using Google? Are you using Service Now or Zenesk? What's all connected? What
[07:30] type of data do you store in each of these? What are they used for? Who uses them? Is this just a tool for your sales team? What kind of jargon are we using internally? But then we also have the
[07:43] personal graph. This is how are you as an individual user of our platform interacting with this data? What are your goals? What are your projects and priorities? What's your writing style?
[07:55] And we take these two things and we combine them together and this powers our search, our agentic platform and of course our Glean assistant. So every time I go and interact with Glean, I'm
[08:08] getting a response that's more specific to me, my role, and what I'm doing than anyone else in the company, they're they might get a mildly different response, but it's all grounded in this enterprise
[08:20] context. So, what that means is when I go to find a document that I was working on last week and I give it a vague an question, it's going to know that that's a priority document for me and find it much faster than it would if I was
[08:34] looking for someone else's document, for example. Now, how does this really come together? Well, it comes together in three ways.
[08:46] We start to transform employee productivity. Employees start to move faster with clean. We see this through our assistant and our agents being able to reply to emails quicker by having an
[08:58] agent that can help take action on their follow-up items. We can transform the business by reimagining and automating some of those workflows. Uh think of it and sales. Those were great examples of
[09:11] there's these consistent workflows that we have coming in. this need to escalate or deescalate tickets or process information so that we can prep for our next call. These are things that we do
[09:23] on a daily basis that we can now speed up the way businesses work by building out agentic workflows. And then of course there's the architecture. Now you're able to standardize your AI
[09:35] across one platform. We can be the enterprise context layer whether you're working in glean or in data bricks. We can speed up that innovation by proi providing that context layer as a
[09:48] service to you and your teams where you work. So what is Glean's unique context value? What makes this different? And really how does this drive with data bricks?
[10:03] First of all the metrics. Our analytics are stored where probably in data bricks we have tables upon tables of data. Now, what Glean is able to do is write the narrative. What kind of metrics matter
[10:17] to our business? What's going to drive us forward? What Slacks and emails are we getting? What's our day-to-day like? And then we provide an answer. We look at all of this data, all of the context,
[10:32] and we bring that together in a way that provides you an informative answer. We go and ask the knowledge graph starting to understand why these metrics matter. We look at what a user has permissions
[10:44] so we're not overpermissioning information and across that context we're taking those results from data bricks and our understanding and giving an analytical answer through
[10:56] glean. So really what this is doing is providing you an enterprise context layer that you can use anywhere you can
[11:08] build or use the native integrations to drive that business forward. You can continue to leverage this information. Now I want to break it down
[11:21] one more step. What's the difference between enterprise graph versus personal content? Why do they matter? And why would this change any of the data or results that I'm looking at? First of
[11:33] all, it's not going to change the data. It is going to use the data that it understands to make it more usable to you. So the enterprise graph, we can think of that as all of our our sources. What are we using? Is it email? Is it
[11:47] Slack? What about how our business is organized? Is it workday? That's what we use for the enterprise graph. We look at the documents. We look at how they're being used. So you can
[12:01] see here if we break it down, workday shows us our org chart. Well, Glean's going to use that to build out an internal org chart. We have Salesforce. That's where all of
[12:13] our opportunities live. That's really important to our sellers, right? So we got to make sure they have access to that. But it's also important to our finance team because that's where all of our opportunities for Active Pipeline live, right? So there's all of these
[12:25] different tools that need to come together so that we understand how they all make our business run. But then you have all the people. So now you're taking all that and you're using the
[12:37] data to understand the business and the people within it. So how does Tom interact with Salesforce and Gong? How
[12:49] is Jess using her email? Who is she interacting with? What documents is just creating and then sharing with her wider team? Who's accessing the Zenesk
[13:01] tickets? Who's updating them most constantly? These are the things that matter to the personal graph. They want to understand, it wants to understand you. Then it's going to also look at how
[13:15] does this person like to write their emails? What is their tone and sound? Why does that matter? Well, I don't know about any of you, but I don't like to have to rewrite an AI message, right? If
[13:27] I'm using it to help me, I want it to come out the first time. So, by understanding my tone of voice, how I like to communicate, makes it a lot easier for me to then later on build and automate off of because I know it's
[13:40] going to sound like me every time it produces an answer. These two things come together and they drive the answers and results we get from Glean. So that way if I ask
[13:53] a question about a product feature and the release cycle, right? What what does that look like? Well, it knows from the personal graph that I'm an SE that I
[14:07] interact with road map and I'm probably asking so that I can relay this information externally. So, it's going to provide me with the answer in a format that's probably externally facing
[14:20] because it knows that I'm talking to externally facing people most of my job. And it's going to site its sources so I know exactly from where in the enterprise graph, from where in the
[14:33] resources it's got its answer. So, if I don't trust that answer, I can see where it came from. And all of these things also help prioritize. So that if I'm asking a roadmap feature, I'm not asking for, you
[14:48] know, the details and the architecture diagrams. I'm asking for a deep understanding of what is it, why does it matter to a customer, and when can I tell them it'll be available.
[15:04] So all of this comes together to power our integrations with data bricks. So it's not just building a context layer and using glean, it's using glean in and where you work. So for our business users, we're probably going to see them leveraging the datab bricks genie inside
[15:18] of glean assistant, right? Where they can work inside of a UI that's maybe not data bricks. We might not have every user using data bricks, but they can use the glean knowledge source in the UI while leveraging those analytics. So I
[15:31] can quickly ask questions to glean instead of going to my data analytics team if I'm a leader. Right? Then you have the direct SQL and in assistant and in agents. So there's another piece of
[15:43] this. What if I want a very specific workflow? I want it to produce my monthly reporting. I want it to help me do research in previous financial information inside of data bricks and
[15:56] correlate that to future projections. These are all things that we can do inside of glean, right? I can take that and take my direct SQLs as an someone that uses glean or excuse
[16:09] me uses data bricks and build it into a report that I don't have to then generate myself for my leaders moving forward. So I'm operating faster because
[16:21] I'm providing a autonomous workflow that gives access to the data. Doesn't move. It just gives access to it, understands it, contextualizes it, adds the business context to it, and we see where teams
[16:35] start to move faster. Now, for a lot of us here, we're probably data bricks users. We probably want to see how we can use this in our day-to-day roles. And there's a couple different options. We have the data
[16:47] bricks connector in glean. So this one is going to allow us to search for our dashboards and our genie spaces inside of glean. Why is this important? Well, I
[17:00] have a hard time searching for things in general, right? I have a lot of different resources. I have a lot of things that are named the same. And when I want to go and find something I'm actively working on, unless I go back through my history and or I search
[17:14] through specific information, finding information like the dashboards or the spaces I'm supposed to go to, I need to speed that up. So, we're already leveraging that that search capability and then in assistant, it can go out and
[17:27] find that information in those dashboards and in those search functionalities and provide the response back in. But what we're focusing on here today is how can I actually leverage this inside
[17:39] of data bricks? How can I use this to help me build out my dashboards faster? And that's where the data bricks genie, Genieode and MCP come in. Glean has an MCP server that allows us to connect in
[17:52] directly to data bricks genie and inside of Genieode. So there's kind of two different platforms we can use. The best of that is now I want to ask a question of
[18:04] I got an update from my leader that I need to translate into this dashboard. I need to change these metrics and update it to reflect that instead of me having to go to my email, go to my Slack, maybe
[18:16] go to Salesforce and collect all this information that I need to use to update a dashboard to create a brand new dashboard out of absolutely nothing. I can use glean to pull in that context
[18:28] and take action for me. And that is what we'll focus on. So how does that actually work? What's that flow look like? Starts with a question. Starts
[18:40] with for example, I'm new on this team and I was asked to build out metrics around previous forecasts. What are those metrics that I need to focus on?
[18:52] Well, data bricks has those metrics, right? It has all these data warehouses with all sorts of information. So, how is it going to know what's important to me? That's where Glean's
[19:05] enterprise contacts come in. Glean then goes, okay, she's a new seller. These are her customer lists. She's going to build out a dashboard to help her
[19:17] understand product usage over the last six months or the last they've been a customer forever, the last 12 years. And she wants to see how that translates over into their current usage.
[19:31] It takes all this context that maybe was in a email that said, "I need you to build a new dashboard on product usage or here's your new customer list. can you build out all of these these
[19:43] dashboards? Or better yet, I got an email. I'm on the data analytics team. They want me to make all these new updates to a dashboard. I don't even know where they're stored.
[19:55] Genie does. And the Glean MCP has this understanding of what my executives want to see, the updates I need to make, and why they're important. And then I get an
[20:07] output. It's going to create the dashboard. It's going to then give me follow-up questions and pull in this context. So, as I use it, it can be even more useful. Let's say I get an a
[20:21] question that says, you know, it has jargon in there like an MBO, for example, or ABC or whatever that acronym is. If you're not sure what it is, before you have to put it into a dashboard, you can ask Lean right
[20:34] through Genie what that looks like, what that means. What's the definition of this jargon? Why is this important? And you're getting this all right within where you work. So you're not having to go back and forth between platforms
[20:47] context switching all the time between structured and unstructured data. So there's few different use cases and I I've given some examples but here's one for a request from a stakeholder.
[21:03] They want support escalation health dashboard. That's a pretty vague request, right? I just get a Slack message. I need this dashboard. Great. Now, what do I do? Well, I'm going to go
[21:15] into Genie and I know Genie has my tickets, my escalations, the SLAs's, who the owner is over time. So I might go in and ask to genie what are some of the
[21:30] useful dashboards for support escalation and health. From there it's going to look at the tickets. It's going to say okay here are all the tickets that are related to it. Glean
[21:42] is going to come in and review those. It's going to say okay here's the context. This support escalations health dashboard was asked for by our leader in support. They want to understand how to
[21:56] reduce Jira tickets. That was in an email. Genie doesn't have that. So, it called and asked the glean MCP. The MCP gave it the context as to what types of metrics we're looking for, who asked for
[22:09] them, why they asked for them, and then it creates the dashboard. It pulls out all the KPIs for support on how many tickets they they have, how many of them are specific to health and
[22:27] then we look at how can we reduce them and we can build that dashboard over time. So brand new dashboard, not a lot of context as to why, but now I've built it out.
[22:39] On the other side, I have a million dashboards that I now own and I'm in charge of updating them and I get requests all of the time on I need the data to be changed. I need a duplicate
[22:52] of this dashboard but for a different region. Make these changes, update this metric. How can I go about doing that? Well, for example, with Glean, you can pull in that enterprise context that
[23:04] says, "Hey, I just got a request to slice the data on this dashboard in a specific way. Can you pull that in?" It's going to go ahead pull in that request that you got via email,
[23:16] ask for approval or automatically approve those dashboard changes and put them right into the context that you already have. So from there, what about labels? How
[23:29] can I align these metrics, make different naming? We have decided to change all of the names of these teams. They they all got updated. I don't want to have to go through and update every single one of these. I can use Glean to
[23:41] do that. This allows us to work faster, make changes quicker, build faster, and get to the work that's more impactful for our business. So with that, let's get into a demo. so you can
[23:55] see this in action. So, I'm going to go ahead. I'm going to switch laptops here.
[24:25] There we go. Perfect. All right. So, I have a brand new dashboard on the the right hand side here. You can can't really see it. Let's zoom in. Um, I'm going to make hopefully this a little bit bigger for us.
[24:38] Perfect. Hopefully now we can actually read what I've written out here. So, we're in Genie Code. We're in data bricks. I got a request. Someone says, "I need a dashboard." Great. For what?
[24:53] Well, for Frraasier Automotive, of course. Don't you know? No. I don't have enough context to start building out this dashboard. We have maybe a thousand different customers who have product usage. I'm on the analytics team. I'm
[25:05] building these dashboards all the time. What do I do now? Well, let's ask Genie.
[25:17] So, what we'll see is it should be pulling the context in from Glean here. There we go. That's what I was looking for. There is the glean mcp being triggered. We see that as a step here. And now we're getting
[25:29] all sorts of information about Frasier Automotive. So what we really see is I asked a question. Genie doesn't know what Fraser Automotive is. It might have tables named Fraser Automotive. It might have
[25:43] details in those tables, but it doesn't understand why Frraasier Automotive is important to me. Here we can see why it's important, who the account owner is, who's going to
[25:56] manage it, what it covers, right? So now I know what part of the product they're probably wanting to have metrics on here is some available data. I might not
[26:10] have known this was tied there, but now I do. I think I have some product usage, some sales data, and some customer data. So from here I can start to explore this. Now Genie is really great. It's
[26:23] already going to prompt me for some examples, but I want to be a little bit more specific. I want to make sure this is specific to the internal team. I want them to stay up to date on the product usage. So help
[26:36] me build a dashboard that I can share with them. Now this is going to take a minute. I'm but going to show you a little bit about what it's going to run and then I'm going to show you my pre-built dashboard so that we don't have to sit here and
[26:49] watch it run the whole time. But here you can see it's starting to pull in from those tables. This was a table that it had already identified as one I needed to use. Here we can see it's pulling in the key metrics. Genie is
[27:01] really doing its work here. We pulled in the context from glean why it's important what type of data that we have and now it's going to go and make this this dashboard.
[27:13] So I went ahead and I built this dashboard out and here we can see an example of a product usage dashboard. Now again I went into it didn't have any
[27:25] context about Fraser Automotive. I didn't even really know what was important and it started to build out this great dashboard for me here from what is the churn risk to the trends to
[27:39] are we seeing an uptick in their usage. We have things like seat utilization. All things that if I were trying to track customer usage, product usage over
[27:51] time, whether it be by customer, by total product, these are all pieces of information that are going to be important to me. So from here, I can see churn risk. This
[28:04] is an interesting one. If I'm not familiar with my organization, maybe I don't know what I should be identifying here and I I want to understand a little bit better. So what
[28:16] I can do is come back into Genie here and I can actually ask it and I I did this a little bit in advance here so that we could see it here together.
[28:43] Might have closed it out. So I'll just run it as well here.
[29:18] So, let's say they want more information on churn. And excuse me, I didn't know much about what churn was. I don't know what those priority metrics are. I'm going to ask Genie and it's going to start to think about some of these metrics here. And what we should see
[29:32] hopefully is it should trigger the Glean assistant because it should be starting to identify what's going on here. Um, so here we can start to see it's actually rolling out what all these metrics mean,
[29:45] defining them, and if I wanted to take this a step further, once this produces me an answer, I can actually use this to update my
[29:57] scorecard or What is the risk of Fraser Automotive turnurning? Now what I'm doing in this
[30:12] particular case is this should go to Glean and pull in the risk. Now this is going to rely on a few pieces of information. Um
[30:24] here so here we can see it's pulling in these metrics from 2026. These are from May of 2026. These are not metrics that are currently in our
[30:37] Genie. These are pulled from Glean. We are using it right for our legacy data in this case. So I can get an understanding of what this means,
[30:49] what turn risk is today, when to worry, and I could even go back and say, what should I prep for my QBR? Or if I were someone working in data
[31:01] bricks,
[31:15] I can update my dashboard. So it's pulling in this met these metrics understanding why churn is something I would want to focus on and then updating it with this information in mind with the context being churned pulling in from both the glean context and data
[31:28] bricks genie. Now I have pretty good feeling this isn't going to fully run before we run out of time here today. But if we hop back over here, we can
[31:41] actually see while this is running how it's using the Genie and all of the pieces here from Glean to the agent and assistant and the
[31:55] widgets to plan and build and create these dashboards, structure, overview page. So, we're not only getting the context, but we're getting the step-by-step walkthrough. So I'll understand where the data came from and why Genie made the choices that it did
[32:07] to build out this dashboard for me. So I'm moving a lot faster. I have the context. I can actually go in and ask like questions about the emails or the most recent updates or make a change
[32:19] based off the most recent request from my leader. And these will push through and we'll be able to see them live in data bricks.
[32:33] So, with that, I know there's not going to be enough time for this to fully build out, but it looks like maybe we might be seeing some updates come through over here for churn and utilization. So, this one looks like it's about halfway done. Updated local
[32:47] metric view. So, we can actually see where it's located, where it's pulling it in from, things like that as well. It's planning the edits. We'll give it just one more second and see if it'll
[33:00] finish for us because I'd love to show the updated version. As we know, things like this do take a few minutes. I do have it set on auto approve as well, which has helped quite a bit. Um, you can see down here I have it auto approving. Uh, that way when it calls
[33:13] out to the Gleam NVP, I don't have to give it permission every single time I want to access the MCP, for example. So, we can see some of the updates that are coming through. I am going to go
[33:26] ahead for the sake of time switch back to my slides. Uh we were able to see at least a few examples of how the glean mcp is pulled into data bricks genie.
[33:38] I'm going to show one more video here. There is no audio so it should play just fine.
[33:53] Maybe the video won't play. It doesn't look like it's going to play for us. Anyway, this was going to show the exact same thing really in intelligence. You can see the Glean MCP going in being
[34:06] able to see that it's active and available to you there in the UI as well. So, that was really the call out for this video. I apologize for the the technical difficulty there. So, finally, let's do a quick little
[34:18] wrap-up off why this all matters. Glean allows you to move faster with data bricks by unlocking better apps, dashboards, and workflows. Now, the nice thing about all of this is we can update
[34:31] the narrative quickly and in real time. I don't have to sit down, sit there and analyze through what metrics are important, why the business leader came to me for this. I can do it all at once. We can save the notebooks or query for
[34:44] re reuse. So, reusable assets, right? As I'm building these out, I can make them adjustable. I can use the context and switch it. So I can say, okay, I just created this dashboard for one team.
[34:57] Let's reuse this notebook. Let's reuse this query, but adjust it for another segment, for another team. We can refine the metric definitions. By pulling in the enterprise context, we actually have
[35:09] a better understanding of metric definitions because now we're not only using what's stored natively. We're also using that internal understanding and that internal context around docs and
[35:21] decisions and KPIs that matter to the business and that are driving it forward. And then of course the one of the most important things you can make changes without leaving where you work. So if you're someone that working in data
[35:34] bricks that's working with those dashboards that's working with teams on the analytics side you don't have to go back and forth between your emails slacks and all these different messages you can bring that right into the UI where you work
[35:48] now glean with GD code builds for success right the better metadata pulling in this context that has a understanding that's governed in your business
[36:01] this improves the decision quality, right? Our metrics are more up to date. They're more grounded in what matters to us most. So when I go to make a decision, the quality of the information I'm looking at is better. And that
[36:14] drives better outcomes. Right? When the information I'm looking at, when the data I have in front of me is better prepared, grounded in what we know and understand from our business, I can actually make these outcomes happen
[36:26] faster and drive the business forward. So essentially, context plus control helps our builders, our analytics teams move and ship information faster.
[36:40] So with that, that is the end of my session. If there are any questions, I'd love to answer them now. If not, please feel free to stop by our booth. We have a ton of people there ready to answer
[36:52] any questions that you may have and show you our product.

Learn more about the Databricks Data and AI platform.

The information provided herein is for general informational purposes only and may not reflect the most current product capabilities or configurations.