Building Enterprise-Ready Agents using Agent Bricks

Summary

• Enterprise AI governance: This video addresses the critical challenge of "agent sprawl" and shows how unified governance through Unity Catalog prevents quality degradation and hallucinated metrics.
• Multi-agent coordination: Learn how Agent Bricks enables sophisticated systems including knowledge assistants for unstructured data and multi-agent supervisors that handle complex reasoning tasks at scale.
• Production deployment success: Discover how 78% of enterprises adopt multi-model strategies, and organizations investing in AI governance ship 12x more projects to production.

Building Enterprise-Ready Agents using Agent Bricks

While AI agent development is rapidly evolving in the consumer space, enterprise AI faces unique hurdles such as data privacy, governance, and the "agent sprawl" challenge. this video introduces Agent Bricks, a unified platform designed to cure these challenges by integrating governance directly through Unity Catalog and observability via MLflow. The presentation details how to move beyond low-quality reasoning on isolated enterprise data to building sophisticated systems, including knowledge assistants for unstructured data and multi-agent supervisors for complex reasoning tasks.
Key Takeaways:

• State of Enterprise AI: 78% of companies now adopt a multi-model strategy to stay ahead of rapid model releases.
• The Impact of Governance: Organizations investing in AI governance and security are shipping 12 times more projects into production.
• Curing Agent Sprawl: Addressing "agent sprawl" through contextual reasoning and unified governance to prevent issues like silent degradation and hallucinated metrics.
• Agent Bricks Capabilities: Leveraging Agent Bricks for automated dashboard authoring, conversational analytics with Genie, and multi-agent coordination.

Chapters

• 0:00 Introduction and agenda
• 1:30 State of enterprise AI
• 5:48 Enterprise use case scenario
• 7:23 Addressing agent sprawl
• 10:05 Introduction to agent bricks
• 13:00 The CURE framework
• 14:10 Demonstrating data analytics
• 21:25 Building and managing agents
• 25:55 Observability and evaluation
• 27:13 Key takeaways and conclusion

FAQs

What is agent sprawl and why is it a concern in enterprises?

Agent sprawl refers to uncontrolled proliferation of AI agents across an organization, which can lead to silent degradation, hallucinated metrics, and loss of trust. This video shows how unified governance prevents these issues.

How does Unity Catalog improve AI agent governance?

Unity Catalog integrates governance directly into Agent Bricks, providing role-based access control and observability that prevents quality degradation and ensures consistent, trustworthy agent behavior across the organization.

What types of systems can be built with Agent Bricks according to this video?

This video demonstrates how to build knowledge assistants for unstructured data, multi-agent supervisors for complex reasoning, automated dashboard authoring, and conversational analytics with Genie.

What production impact does proper AI governance have?

This video highlights that organizations investing in AI governance and security ship 12 times more projects into production, and 78% of enterprises now adopt a multi-model strategy to stay competitive.

Full transcript

0:00 Introduction and agenda

Things look really good, really optimistic. Every new day there's some new person releasing something really exciting which might suddenly replace all the software developers and whatnot, but it's not exactly the same in enterprise AI. A company that's considering AI governance and privacy and all these things in mind, it also shows the maturity of that company, of the leadership, of the team. How many people here are dealing with AI agents or, you know, anything related to that at work?
Okay, so a good chunk of it. Perfect. I am a resident solutions architect at Databricks. I did my master's in data science from the University of Washington, UDub. Uh been in this field for about more than 8 years and I'm directly working with uh enterprise customers or Databricks enterprise customers in manufacturing and healthcare, life sciences sectors, which means, you know, they come up with all these different challenges.
I have the data. I want to do this with my data. And then I help them, uh you know, implement those things. We are going to look at state of AI agents. Uh then we look at uh then we'll look at an enterprise scenario, basically a use case. Then uh I'll briefly or or in a very detailed way go through AgentBrix. Then I'll give a demo. And then key takeaways and we'll have some time for question and answers. Now, the ques- the first one is state of AI agents.

1:30 State of enterprise AI

And if you were to look at the like what I call the family and friends version, which is basically outside of your enterprise work. What it means, every day you have got, you know, new models coming in, cursor, uh I don't know, Anthropic, all these things, new open source agents, uh uh I don't know how many of you know the open claw or Claude bot and whatnot. So, things look really good, really optimistic. Every new day there's some new person releasing something really exciting which might suddenly replace all the software developers and whatnot, but things seem to be working out really well.
But, it's not exactly the same in enterprise AI or enterprise world. And when I say this, this is not really out of you know some sort of sales pitch. It's something that I do each and every day at my work. So, one of the things that really recently came out is the Databricks publishing a state of AI agents report. And it provides a snapshot of like how organizations are shaping their data and AI strategies and priorities.
And the source is not the trust me bro benchmark or all those things. It's actually the insights that we have collected from you know 20,000 plus customers that we have all across the world. So, we get to see how they are using the platform, what are the difficulties they are dealing with, how they resolve it, all those things. Some of the summaries some of the key takeaways from that report are here and I'll share a link where you can go through all the details of that report.
So, the first thing is multimodal strategy strategy is the way to go. Earlier when the when Open AI's you know and the Geminis and the Cursor and ChatGPTs of the world came out, people started you know companies tried to pick one model, but then over the time they realized that this is getting too tiring. Every single day there is a new model and that you know claims to beat everything else out there. So, the best way to deal with this is you adopt a strategy which allows you to just use multiple models.
So, 78% of the companies are now using two or more LLM families. The other one is since January of 2025, basically last year, so within a 1 year, there has been a 7x jump in investment in AI governance and security. So, earlier when things were, you know, really new, really exciting, there were a lot of passion around building and shipping these agents, but as dust settled down, you saw you you you see increased concerns around AI governance and everything else.
And so, the other thing is companies that use AI governance were putting almost 20 12 times more projects in production. And you might say, "Hey, well, this is just a correlation, it's not causation." But the one of the things here is to consider the fact that a company that's considering AI governance and privacy and all these things in mind, it also shows the maturity of that company, of the leadership, of the team, right?
So, that's why when all of these different things come together, that's why you have 12 times more things in production. Another thing, agents are driving the core database activities. So, 2 or 3 years ago, there were basically no AI agents or at least the way in the form we know of them today, really popped up in 2024 and then rose sharply in 2025. So, what it says is, you know, this this chart simply says that on the platform that Databricks I mean, Neon, that one of the platforms that we acquired, uh yes, 80% of the databases were actually being created by the AI agents.
And this is just the database. When you look at the branches, that gets even, you you steeper. It's 97%. Let's look at the a typical enterprise scenario. So, let's say there is a bank called Nova Bank. Uh it is a global financial services firm. It needs to monitor threats and that needs to be done in real time. How can that be done? Uh you do it by, you know, monitoring the authentication logs, endpoints, user access, threat intelligence data, so on and so forth.

5:48 Enterprise use case scenario

And you and your bestie belong to the data team, which is in charge of doing this. So, you have got your best friend as well, and you're both uh tagging along on this ride. Simply put, your task is to correlate the data or use the correlated data and contain the threat quickly. That's all the business That's all that business cares about. It doesn't matter how you do it. You build dashboards, you build agents, you, you know, climb the building, doesn't matter.
That's the end goal. So, next one would be, well, that sounds pretty straightforward. We know the problem. We know what the solution should look like. I said, you know, there will be logs and all these things. So, basically, you need the structured and unstructured data. You need a bunch of AI agents. And then you need to slap on a very fancy, nice-looking UI so that if your boss or any manager or a director looks at it, they get uh a nice feeling of it.
So, well, now let's quickly build some AI agents. But, there is always a but, and there's always a meme. There is something called agent sprawl. And what it simply means is you have got low-quality reasoning on enterprise data. When you have these AI agents which are or forget AI agents for the matter, when you have LLMs, the large language models. They are trained on things that are available on the internet, right?

7:23 Addressing agent sprawl

But the data that is sitting in your enterprise, that's not really available on the internet. So, it has absolutely zero clue of what your data looks like, what's the business logic inside of it is. No idea. Then it guesses. And you will see what I mean by that. So, that's one. Number two, no visibility or auditability. Well, you you decide to, you know, the best way to deliver some results fastest in the in the best in the fastest manner is to maybe it make an API call, send in some data, get the data, get the result, and say, "Hey, I got the result."
But then the problem is you have absolutely no idea what's happening behind the scene with your data. Is the LLM storing it? What kind of data you are sending? What kind of response you are getting? Nothing on that front. Too many AI vendors. Nowadays, I mean, I mean, yeah, you have got Google, you have got Anthropic, and you have got OpenAI. There are and you have got Meta as well. And there are a couple of others. And then you have the last problem is you have no way to measure the quality, right?
So, every person has or every team comes up with their own standards of like what a nice agent or what an accurate uh agentic system looks like. And but that's what it is at the end of the day. A team-based metric of what quality looks like. And to sum it up, the governance is the nightmare part. The governance and the you know, everything that comes with it. And so, in case you still needed some convincing, this was a post that I saw I think two or three days ago.
And I'll just you know, ask you to read it maybe 10 seconds. Just look at the box, the red box. It says, "Built an AI agent." It was answering some leadership, you know, it was answering to the leadership about metrics. The leadership made a whole bunch of decisions on it. But then I later found out that it was hallucinating numbers for the past 3 months. And the person at the end says, "I caught it by accident." So, nobody wasn't even like questioning the outputs that the model was generating.
By pure luck. And so, this is where something called Agent Bricks comes in. What is Agent Bricks? It's that one unified agentic platform that cures the sprawl. And what is cures? It's a it's a word, it's a big word, it's a fancy word, but I'll give you the meaning around it or behind it. But before that, let's look at what's happening in in this uh architecture or in this platform. At the base of it all or at the core of it all is what we have uh is Unity Catalog.

10:05 Introduction to agent bricks

So, and that's the governance layer. And so, any AI gateway models, MCP agents, or evals, files, tables, anything and everything related to your data and AI is directly governed by Unity Catalog. You don't need to slap on an additional governance layer. On top of Unity Catalog, you have something called MLflow, that Z covered. And that MLflow is useful in uh really kind of monitoring and observing and evaluating a whole bunch of things, a whole bunch of components that sit at different levels.
So, that is vertically uh it it is uh vertically spread out. This is horizontally spread out. So, this means a combination of them gives you a good coverage. On top of Unity Catalog and along with MLflow, you will be building models. You'll have, you know, data serving. You'll have vector store, vector search, feature store. You have You'll have different libraries to train your model, and you'll use different, you know, developer tools to do that.
On top of that, I mean, or or using these things, you will do a whole bunch of these things. What it mean What will you be doing? You will be doing data reasoning and retrieval using the structured unstructured data, maybe document processing and other things. Then you have got Agent Factory, and this is what I'll be covering in my demo. You will have a supervisor agent which can work with a bunch of other agents that live in your data platform, and it's able to answer questions.
Then you have got Agent Deployment. You can do LangChain and CrewAI, and I don't know how to even say it, DSPy or Dispy. But, yeah, you have a whole bunch of things here. And then you have different model providers. And so, that's So, basically, the point that I'm trying to make here is this one platform is what really helps the enterprise team to really not care or or really not spend a whole lot of time building the foundational layers, but start using what's already available, what's already built out for you, and quickly deliver value.
And so, if you remember, I covered Q learning. So, what is Q learning? I'll briefly cover it. So, your problem was initially that I shared was we had low-quality reasoning on enterprise data, and the solution for that was contextual reasoning. And that contextual reasoning is coming from your business data, which resides in Databricks. When you are When you as a user are using the platform, there is some sort of learning that's that happens behind the scene depending on how you use it, what kind of questions you ask, and so that's contextual reasoning.

13:00 The CURE framework

The other problem was no governance, data leakage, and absolutely no visibility. For that, you have Unity Catalog, which provides you the unified governance. Next one is you have too many vendors and a and a fragmented stack, and a solution for that is the run on any model or run on any framework that comes built in with Agent Bricks. The last one is no measurement, and your agent is degrading silently, just like the example we saw earlier.
And the solution for that was the evaluate and improve method that comes with MLflow. So, this is what a data pipeline would look like. You have logs from at 10 different places. I mean, this is not exactly what it look like, but this is just a sample of like what a job would look like, which brings the data from all these different places. So, to represent that, I used a block called generate data. Then you will do a whole bunch of SQL transformations, and so on and so forth.

14:10 Demonstrating data analytics

Now, once you have the data in Databricks, it will look something like this in your catalog. So, I have a a catalog called Agent Bricks Demo. Within that, I have a schema called FSI cyber. And I have whole bunch of these tables. And these tables are have all gone through the medallion layer, you know, the transformations, raw, sorry, bronze, silver, and gold. So, here you can see raw, silver, gold, and everything in between.
Now, I'll very quickly cover this. One of the things that I myself I have I did hear about it earlier, but something that I tried today, so I had no plans of covering it, but here I am. Once you have the data in your catalog, the first thing you would say is, "Hey, let me see let me visualize what the data or the final uh massage data or the gold layer data can do for me. So, you would start with building some sort of dashboard.
At least that's what you would do. Now, within Databricks or and as part of the whole Agent Bricks platform, what you have now is you get to say and this is the dashboard section. You say add sources. You'll go here. Uh select all the let's say gold level tables. So, we'll not spend a whole lot of time, but I'll I just wanted to show this very quickly. Okay. So, it has I I added and I added a whole bunch of tables that I was interested in visualize visualizing on my dashboard.
The next step would have been me going to this you untitled page and start to add some you know, visualizations. I'm not going to do that. There is something called this assisted authoring, the agent mode. And what I will do is I'll simply click on this button called create a sample or yeah, sample dashboard. And then off it goes. It will look at my data. It will try to make sense of it. It will find out what it has what kind of insights it can provide.
And so, as you can see it's already starting to think. It will do its thing. We'll come back to it at the end of the demo. But this is what I was able to you know, create without typing literally not typing a single word apart from that pressing that button. So, it went through a whole bunch of my tables, identified the comments or anything that I have added. And so, as you can see it has added a whole bunch of these things on its own.
The other thing you would want to do is you know, you have visualized the data. Now, what if you want to really talk to your data and so for that we have a tool called Genie. It's again a conversational analytics tool which basically lets you talk to your data or which lets business users talk to talk to your data. And the way it works is you would here go ahead and click new and you will add your data. I'll just add one single thing so I can show what it does.
And so once I finish doing that I have this ready to go. I'll add some more instructions to explain or to instruct the LLM how to behave, what to do, what not to do. I'll add a couple of these SQL expressions, add a add some business logic inside it just to get it ready and just to help it understand my data better. But once I have done that what I have right now is an interface with which business users can start talking.
And what I'm doing is there are some ready-made questions the agent thinks might be most relevant to the users. So I'll just click on it. And the question was what what recent temporal patterns emerge in this data set. So basically I'm asking during the whole duration for which this data is available, do you see any sort of temporal patterns? And so here you can see on the right-hand side when I expand it, you can exactly check line by line of what what it's doing.
So you see it's looking at the data set time range, it identified first from to date ranges, then what are the business impacts and whole bunch of other things. I mean and so having this can really help you confirm that your LLM is not really hallucinating, right? And this does not really need a technical person to jump in and look at things. I could be a business user and I don't have to do I I probably won't be seeing this.
I'll just have this interface. And while this agent tries to answer my question, I have all I have to do is click on this and all of this shows up. So as a business user, I can There is this something called Databricks One. So you will add on your business users to your Databricks platform and you'll shoot out this link and they will have access to it. The clusters will run, of course, because the data the agent is generating the response.
It's actively querying the data behind it. So the warehouse the data warehouse will need to run. But yeah, the Databricks One thing, that's a new thing. It takes away a lot of complexity. Now, while we were while I was yapping, as you can see, it went through the whole data set and it identified these sort of authentication anomalies and patterns and events and all those things. And you can edit the visualization, you can do a whole bunch of other things.
You can download it as a PDF. That there's no glory to that, but Now, the other thing that the coming to the main topic, you have Agent Bricks. This is the available here at the bottom corner. Once you click on that, you will see a whole bunch of options or different types of agents that you can build. So one is document parsing, information extraction, knowledge assistant, AI BI Genie. So the thing that I was showing you earlier, the AI BI Genie, that is part of the Agent Bricks platform.
Now, let's say I'll I'll try to finish this soon. So there are two things that I'll be covering. Number one is knowledge assistant. Number two is multi-agent supervisor. To build a knowledge assistant, what you will do is you'll see this guy over here. You'll click on build and it brings up a very minimalist interface for you where you provide the name, you provide the description, and you say where are my files on which I want this to be built.
And so, here they are. They can be in the PDF format. So, I'll go here and I'll select this PDF uh folder. I can just name it something and in the options I'll say, "Hey, you need you are a so-and-so knowledge assistant. You need to act in this certain way." And once I click on that, well, maybe it's asking for agent as well. I mean, description. So, I do some of this and it goes off to create the knowledge assistant.

21:25 Building and managing agents

It will take about, you know, 10 5-10 minutes to pass through all the data, all the PDF document and everything else that you have. But in the end, you will have something like this. So, you have the knowledge assistant built here and I'll ask it a very simple question. So, this this knowledge assistant has been fed a whole bunch of PDF files which cover topics around, you know, what are my SOC or it has documentation around security policies in in the organization.
And again, here you you can see everything that the agent is doing. You can you are able to click on that thinking tab and it will, you know, come back with details on what exactly it's doing. And so, now it's able to give you the answers that you are looking for. For PDF files, it can be in any form. In the PDF form, you may have a mix of free-flowing text, you can have tables and everything in between, right? So, it will be able to pick that up.
And if you go to the documentation, it's uh list down all the supported formats that uh you know, that will work with this. Okay, but basically, uh you you saw this whole bunch of uh response coming down. And towards the end, it also cites the page or the section from where it got the information. So, you have uh for threat correlation workflow, I don't know. I've never read this PDF file, and probably most of the analyst will probably never will.
They just want to understand or they want to get an answer. And so, if you want to kind of refer that or confirm whether the answer is correct, you can always click on those citations and get the answers. And so, that is the knowledge assistant. I'll very quickly cover the multi-agent supervisor, because this is the part which kind of gets exciting. The multi-agent supervisor, if you remember just few minutes ago, we had created Genie, uh the thing that loves working with structured data.
And we also created knowledge assistant. Knowledge assistant loves working with unstructured data. And so, the multi-agent supervisor can really bring these both of them together. It can understand whether the question that you're asking needs to be answered by the uh knowledge assistant or by Genie or by combination of both of them. So, I'll copy this question. It's not something that I have There is no predefined answer to this.
There it will go through the entire stack to figure out where it's getting the data from or where it should get the data from. So, if you see here, I was asking according to the SOC playbook. I asked it a question related to my SOC playbook, and it immediately identified that this needs to go through the knowledge assistant, right? And so, then it asked it a question, and then it came back with oh, this is a bit too fidgety.
Okay. So, Yeah, so basically it does a whole bunch of things and it gets you the answer. You have the knowledge assistant going first, then it will come back. It will maybe ask questions to Genie. And so, it will get you the answer is is the point that I'm trying to make. Now, this was something that I had asked it. So, earlier, you know, I asked it, you know, what are our IAM and privilege access policies? And so, it said, "Okay, let me look at that."
And then whole bunch of things come back. And then everything that it mentions there are these citations that you can click on and get access to. The last thing that I would like to cover is the integration with MLflow. So, I built it. All I did was, you know, a simple user interface, click through things, selected a whole bunch of things, and off it went. Now, let's see where let's see where observability and all these things come into picture.
I will go to experiments and this is where you'll see the integration with MLflow. So, there are a couple of things. You have the multi-agent supervisor, you have knowledge assistant. Let's say I want to look at what multi-agent supervisor was doing. So, here you can look at each trace of like how the whole thing went. When you asked a question, what did the model do? What was the context like? Uh then what was the response?

25:55 Observability and evaluation

Whole bunch of those things. Uh I can again go back. Uh you know, it will probably take several hours for me to cover everything, but you can also look at each session, like how different users interacted with different uh in in their different sessions. You can also create judges, meaning LLM-based judge, where you are constantly monitoring whether the response uh you know given by your LLM or this whole agentic system is compliant with certain rules and regulations that you may have.
So, let's say safety is one of them. You can create another LLM judge. It will ask you to select a type. So, here. So, guidelines, relevance to query, a whole bunch of these things. Basically, what did you achieve after this? Just because you have this platform where you don't really have to you know worry about the governance, you don't have to worry about observability, everything comes baked in. What you were able to do is you were able to immediately identify, you know, the kind of data you have, the kind of insights you can drive out of it.

27:13 Key takeaways and conclusion

It's a good platform. That's what I would say. The key takeaways for me and for that I would love everyone else to take as well is agents are now creating most of the databases and the branches and this is all happening to you know because of wipe coding, the new term wipe coding. Now, we can discuss whether wipe coding is good or it just adds to tech debt. Irrespective of that, it's happening. A vast majority of enterprises have adopted the multi-model multi-model approach.
The enterprises that are investing in governance, they are shipping 12 times more AI projects in production, already mentioned. One of the other things is enterprises have many high value use cases for agents but they are mainly limited by these different sprawls that you know the other challenges that I had mentioned. And because Databricks had that advantage of being able to see what's happening with their client, it gave it a lot of clarity about you know what kind of challenges they are dealing with, what kind of solutions will be helpful, so on and so forth and that would help them help the enterprise cure the agent sprawl.
And that's pretty much it. Uh if you have any questions or if you would like to connect with me on LinkedIn, it's here. Thank you.

Learn more about the Databricks Data and AI platform.