
AI agents need a “new data stack” that can retrieve the right operational data at the right time. Snow Leopard positions itself as middleware between agents and multiple SQL/API data sources, enabling live semantic understanding, live federation, and governance so agents can answer reliably without moving all data into a warehouse.
Deepti Srivastava, founder and CEO of Snow Leopard (snowleopard.ai). Background: builds “automatic semantic data intelligence” for enterprise AI agents; previously discusses database/agent integration and data architecture needs for autonomous workflows.
Written by AI. May contain mistakes.
Discussion on the need for AI agents to access the right operational data in real-time.
“I think a lot of our listeners will agree with this.”
Exploration of federation in data sources and its historical challenges.
“And so autonomous agents, AI agents are meant to be that unlocking force.”
How Gen AI enables real-time data access and the implications for operational efficiency.
“The warehouse is known in its boundaries.”
The role of a semantic layer in understanding data sources and ensuring accurate SQL generation.
“And we can make decisions based on live pattern matching, if you will.”
Discussion on the complexities and practical challenges of managing data for AI agents.
“The hardest part is what Snow Leopard is solving today, which is where is my data?”
Discussion on the importance of a semantic layer for AI data architecture.
“So all of these things that are practical issues that you and I know are hard, right?”
Exploration of the difficulties in understanding and governing data semantics.
“And it's really about two academic economists who, after grad school, went to the U.S.”
Insights on feedback systems and ensuring reliability in data solutions.
“I guess that's why you have this feedback API.”
Learn about the importance of concurrency and latency in cloud and on-prem deployments.
“So we aim to be the strongest link in your chain because clearly with data, there is a chain and there are weak links and strong links.”
Explore the limitations and challenges associated with streaming data for AI agents.
“Because you really do need to have access to the right systems for the agents to really be autonomous.”
Discuss governance measures for preventing rogue actions by AI agents in data access.
“How does this help me in the context of an agent trying to look up something like an order?”
Examine the evolving nature of data permissions and trust in AI agent interactions.
“So I guess what you alluded to this earlier, you have the notion of governance and all of that.”
Understand the significance of semantic layers in managing messy data for AI applications.
“I just don't think there is enough trust in touching, not trust in Snow Leopard, but just trust in AI and autonomous agents in general.”
Learn how explainability tools enhance data management and user feedback.
“and the user interfaces for human beings are also very simple.”
Explore how upcoming changes in data stacks will influence AI agents.
“So, you know, showing it in a visual format is something they're considering for sure.”
Understand the implications of an agent-first approach on data infrastructure.
“So which means actually the data stack itself will change constantly because maybe, you know, because now you're coding, you're using coding agents.”

Get the gist, explore an idea or ask about something said.
On The Data Exchange with Ben Lorica, what are the key points of this episode?
Automatic transcript. May contain errors.
0:03Ben Lorica: All right, so today we have my friend Deepti Srivastava, founder and CEO of Snow Leopard, which you can find at snowleopard.ai. Taglines are empower your AI agents with live accurate data in minutes. Snow Leopard, with its automatic semantic data intelligence, provides 90 plus percent data accuracy out of the box. so you can ship enterprise agents faster and with confidence over that. DP, welcome back to the podcast.
0:37Deepti Srivastava: Thank you, Ben. It's super exciting to be back here.
0:40Ben Lorica: All right. So I guess the thesis is agents need data. In fact, agents need the right data at the right time. I think that makes sense. I think a lot of our listeners will agree with this. So agents need data and data, for the most part, will have to be retrieved. I think that also makes sense, right? So right now, I guess the current state of Snow Leopard is that it sits between your databases and the agents that need information from them. An agent sends a question through an API, and then Snow Leopard works out which database holds the answer, writes the queries, fetches the results, and combines them.
1:31Ben Lorica: That's correct, yes. And the emphasis here, Deepthi, am I right to say the emphasis is on operational data, not analytic data like data warehouses?
1:42Deepti Srivastava: The emphasis is on operational data. I think analytics data is also can be used as part of operational data. But the way I think about this is operational data sits in structured storage, right? So structured storage is SQL databases, APIs like Salesforce or HubSpot or things like that, right? So things that make your business run or are part of the critical business decision making. So, for example, there is a lot of data that is unstructured. And overall, you know, if you remember back to like 23, 24, 23, 24, 25, even RAG was all the rage for unstructured data, right? Because it was the first time that we could actually sort of assemble and make sense of unstructured data.
2:27Deepti Srivastava: But really, the focus from Snow Leopard's side, from my side, has always been operational data that makes your business run. So it's stuff that is in SQL Server or Postgres or MySQL or Snowflake, which can be both analytical and people use it for, you know, operational data today as well. So like things like that and Neon and all of that and Sokol from Salesforce and those things, because they become critical to how you run your business and they are therefore critical to how you will run autonomous agents. Right. Because the whole point is we not only automate current workflows, but we create new workflows with the power of Gen AI to be specific.
3:11Deepti Srivastava: Right. And so autonomous agents, AI agents are meant to be that unlocking force. And for them to work, they need, like you said, access to the right data from the right place at the right time. So if it is a warehouse, we'll talk to the warehouse.
3:24Ben Lorica: So so but basically, so the foundation of Snow Leopard, so to speak, is data in databases. So it could be operational, it could be analytic and then databases that use SQL. That's right. It's another assumption. Yes. So then one of the things that you do is that let's set aside how you write the SQL statement for now. But one of the things you do is let's say I'm an AI agent that's interacting with an external customer. You will, based on the inferred need of the customer, you will decide where the data lives. It could live in multiple places, write the SQL, and then return to the customer what the customer needs.
4:10Ben Lorica: So implicit in this, I think lurking in the background is a dirty word called federation. Am I wrong?
4:20Deepti Srivastava: No, you're absolutely right. I don't think of it as a dirty word, but yes, it is absolutely life federation.
4:26Ben Lorica: So federation has had a long history, right? Yes. So let's, I'll have you play devil's advocate first. So why are people skeptical of federation?
4:37Deepti Srivastava: Because historically it hasn't worked, right? Historically, the way to do federation has been...
4:42Ben Lorica: Oh, by the way, maybe you should give a very, very high level definition of federation.
4:47Deepti Srivastava: Federation means you go to different data sources and fetch data from it, whether it's live or not, it's a separate question. But the point is you have some data in one database, some data in another database. So Postgres and MySQL used to be the canonical. And then you don't know how to go get between data from both of them, right? Your customer data can be in Postgres, your product usage data can be in MySQL, for example, or the other way around, right? And so the question becomes, how do you combine that information in order to answer your question, even if it was for a dashboard, right? Like, even if it was historical trend analysis, you still have to go get from both.
5:21Deepti Srivastava: And so the overall thought process has in the past 20 years was you use an ORM and then you use like the base SQL, right? The common NC SQL standard of the time. And then you write every query in that form so that your LAM stack type application would then go fetch from, you know, it would write the program, basically, would write the SQL query in the base SQL language. And so it could run anywhere, right? Because the idea was it was this standardized SQL that could run anywhere. And so you could write basic SQL and get data from, let's say, a MySQL on a Postgres, right? Because both of them would support basic selects and basic joins.
6:00Deepti Srivastava: But what's implicit or explicit in that is that the basic feature functionality set becomes least common denominators. You actually can't use most of the functionality that each database provides completely, right? So it becomes this like hobbled together system and you have to have exceptions all over the place in order to like really use the MySQL stuff versus the Postgres stuff versus the, you know, Teradata stuff versus the Oracle stuff. So that doesn't work. But also, federation used to be like really hard because you couldn't figure out a priori, which is how most software has been built until now.
6:34Deepti Srivastava: By pre-agents, all software is built a priori, which means all the logic has to be pre-programmed, which means you don't know which data silo you have to go to in order to get that information a priori. So putting together a federation became practically really, really hard, if not impossible, which is where this concept, which, by the way, I agree, in the pre-world, this concept of warehousing became so popular because now you dump everything into a warehouse. The warehouse is known in its boundaries. And now you can write your program very deterministically in order to get information from the warehouse.
7:10Ben Lorica: But that's only good for analytics and reports.
7:13Deepti Srivastava: Yeah, so the current warehouse vendors will argue with you that real-time pipelining and sub-minute blah, blah, blah will give you that, but it doesn't. And all of your listeners who have ever done this know that it's not true, right? So you use the analytics style capabilities to run sort of real-time-ish workloads, and that doesn't work.
7:36Ben Lorica: There's always going to be a lag, right?
7:37Deepti Srivastava: There's always going to be a lag. And the problem is, at human speed, this was still okay because we would fill in the gaps ourselves, right? Like, I think this is the biggest thing that people are now sort of facing in real time, right? They're realizing as they build autonomous agents that some of that lag, when the human was the operator, we can fill in, right? We can go look up Salesforce and give you an answer if you're sitting in a boardroom. or we can like the customer support example that you're saying, but the human customer support agent can go look at the data source if they have access, right?
8:10Deepti Srivastava: And give you an answer like, where is my order? Or even if it's not made it to the warehouse. I think the delta today is, and it's a really important delta, that an autonomous agent is not, if he doesn't have access to the right information, cannot give you that information, right? So a lot of support calls today, today, that you call, I've done this even recently, if your e-commerce workflow fails at the wrong time where your user calls in like i didn't get my order number so i don't know if the order went through or not which is the canonical example i give because i faced it the human agent has so you're you were going to talk to a chatbot the chatbot then asks you for your order number you do not have your order number then it has to transfer you to the human to bridge that last 30 gap of where it doesn't have the information And now if you have autonomous decision-making agent, like how much marketing spend to have, which microtransaction and financial services to actually let go, those things you cannot intervene.
9:10Ben Lorica: But still, why does federation work now?
9:14Deepti Srivastava: Two things. In the era of Gen.AI, and this is known, we can actually write text-to-SQL on the fly.
9:21Ben Lorica: Right.
9:22Deepti Srivastava: And we have because of Gen AI, if you actually work with it, with the system's understanding of how systems and databases work, you can actually do live federation across by making real time decisions that you previously couldn't without Gen AI. Right. So that's actually what the premise of Snow Leopard is. This is possible now because both LLMs can do text to SQL at a base level. Right. And we can make decisions based on live pattern matching, if you will. Right. Which LLMs are very good at. So you don't have to have if then else conditions for every single thing that is out there. And that's why it works.
9:58Ben Lorica: So then in the example you gave, right, so you have customer data in Postgres and product data in MySQL. First of all, I think one of the things you first do when you engage with someone is you understand the schema across all these databases, right? So then I guess what people call the semantic layer, right? That's right. So a lot of people have this. Sometimes they have it only for their system. There's some AI to BI tools that have it across different analytic systems, right? So if you use Snowflake, Databricks, BigQuery, they all have it. Yeah. So you're building it across these operational systems, right?
10:40Ben Lorica: So then that means you understand that customer data is in Postgres, the product data is in MySQL, but then you still have to do joins potentially, right?
10:52Deepti Srivastava: And we can do that outside those systems. That is the key sort of insight or value added Snow Leopard is that we can join across those data sources.
11:03Ben Lorica: And the reason is because the types of queries you're working with are not going to be this massive, big queries like here's a billion row table, join it with this, right? So they're operational systems, right?
11:15Deepti Srivastava: So there's two parts to that answer, right? The first part is yes, I think everybody that's in the data space goes into the like, oh my God, but the worst case scenario. Yeah. Which is actually why this federation also didn't work earlier, right? Yeah. Side note, I literally recently wrote an article for the ACM, a research article about what's required for data architectures. I'll send you a link to it.
11:37Ben Lorica: Okay.
11:37Deepti Srivastava: Because it talks about what was wrong with federation in more detail and why it works now in more detail. But the point is we can build these semantics a priori, first of all, like at connection time. And we can use that at query time to write the SQL, right? So that's one part of the system. But to go back to your question of why this will work and how come we won't go into the pathological case, I think data shows, like operational data queries are generally, generally speaking, point lookups or small joins, right? So when we talk about this customer example, it's one customer making 10 orders, maybe.
12:15Deepti Srivastava: So those are not the pathological cases. So yes, we work really well. In fact, you know, if you demo it, if you use it yourself, like we can answer these questions in real time, like very, very quickly, right? Because we're doing all this stuff with point lookups and point joins, and we can parallelize and we can sort of distribute and put the information together very quickly. So that's one thing. The second thing is any data person that has worked for databases, et cetera, knows like there are known optimization techniques, right? So, for example, if we see joins that are large, we can break them down, first of all, right?
12:47Deepti Srivastava: We can optimize the query. The databases themselves do that. Secondarily, if we have had to do it once, like we can cache it. There's like multiple, like there's caching and there is sort of sub-query generation. Like, you know, you can do a map reduce kind of thing with queries, right? where you can break them up, you can pull the data in separately, and then you can put it back together. This is what we did at Oracle for large joins and joins and things like that. You can create views and things like that. So there's multiple ways in which we already know how to optimize that part that we can apply.
13:18Deepti Srivastava: And these are known and solved problems. So it's a matter of application. The hardest part is what Snow Leopard is solving today, which is where is my data? How do I connect it? How do I get the right context so that the text to SQL is highly, highly accurate, right? How do we get governance, right? So that the agent doesn't touch the wrong data. And how do we actually use the SQL databases with the agents where the answer today is, oh, just MCP it. And like, I think we're coming out finally from the trough of disillusionment around MCP, right? Like there was this whole hype. The last time we talked, it had just come out and there was this whole hype of MCP will solve everything, doesn't solve governance, doesn't solve accuracy, right?
14:02Deepti Srivastava: Actually burns a lot of tokens. So all of these things that are practical issues that you and I know are hard, right? Like data is one of those things. It's like, I don't know, like hold or things like that, right? Where you can say, oh, I know how to solve it. But the devil is in the details and you spend like 90 % of your time trying to deal with the edge cases, outliers and things like that, which become very common. Those are the hard parts.
14:28Ben Lorica: So this semantic layer, right? So this is key to what you do, right? So you go in to a company and then in order for you to do your magic, you have to infer automatically this kind of semantic layer, correct? Yeah. So semantic layer, broadly defined, basically understanding what data is available, where is it and what are the right permissions and so on and so forth, right? But key is this column, which might be called, I don't know, 1, 2, 3, 4, 5 is actually customer ID, right? So how well does that automatic construction of the semantic layer work out of the box?
15:14Deepti Srivastava: So we ran a benchmark against Sonnet 5.6, Opus latest versions and, you know, the GPT laser version at the time, like four months ago, these things move really fast. But we were 90 plus percent accurate, 95 plus percent accurate in our benchmark. And we didn't shenanigan it. Like we literally just ran us. So Snowlapper with the datasets, which is BigQuery and Postgres, and public assets, we didn't shenanigan the dataset either. And these LLMs plus MCP, right? And we didn't do like 10 questions only, right? So we ran 100 questions three times. like there is a benchmark that we published. So number one, we do really well.
15:54Ben Lorica: By the way, the operational data tends to live in these really ginormous schemas, right? So thousands of tables, potentially. Yeah. Right, so ERP systems are a mess, right?
16:07Deepti Srivastava: Yes, I think that all of that is true. I again think if you look at the sum total, right, of all the databases that people are even trying to use with autonomous systems today, like there's a bell curve, right? The meat of the bell curve is maybe 5 ,000 schemas, that kind of thing. And those are very simple. The way we've built the system is that it is scalable. So it doesn't get trapped with we have 10 terabytes of data because we don't care. The schemas are large, yes. But I think I want to go back to what does it mean to build semantic intelligence? What does it mean to have semantic layer?
16:40Deepti Srivastava: Because people focus a lot on ontology definition on the one end of the spectrum and schema reading on the other. And Snow Leopard is built on the premise that you need both and more, right? So I think in order to have semantic intelligence, you have to understand not just the schemas, but also the system from whom you are reading those schemas. So SQL Server is very different from Postgres, is very different from MySQL, is very different from BigQuery, right? From Snowflake, etc. And I'm not even getting into Socle. But each of these databases has a way in which you define the schema and the data.
17:15Deepti Srivastava: So the way Snow Leopard works is, first of all, we have ER harnesses that are custom to that database type, which means we understand that BigQuery has schemas a certain way. Like names, for example, are like differently put in BigQuery versus in Postgres versus in MySQL. MySQL has schemas, Postgres has namespaces and data sets. BigQuery has only data sets. Right. So these things make it step one for accuracy is you have to know what the layout is going to look like. Step two is, yes, we read the schemas, but any fool can read the schemas, right? Like at this point. So that is not it. We read the schemas, but we actually have an LLM-based harness with judges and adversarial LLMs or systems that actually probe the data within the schemas, which is how we know that column 1, 2, 3, 4, 5 has floating point decimals and therefore must be a currency column or a discount column or things like that.
18:10Deepti Srivastava: versus it has whole numbers and they're five digits. So therefore it might be zip codes. This is how we build that intelligence. And we do all of this at the time you connect the data source. So that's number one. That's how we get our accuracy out of the box. And the number two piece is we completely agree that tribal knowledge today exists in people's heads. And so we actually provide you with an air phase to then give feedback, we literally call it the feedback API, to the system, to Snow Leopard, so that you can say, oh, actually, you thought column A, B, C, D, E was a discount number, but it's actually our price reduction number, right?
18:49Ben Lorica: This is actually key. Your API is quite simple, right? So you have response, you have retrieve, response, and then this feedback, right? Correct. And the feedback allows you to go from 95 % to more and more accuracy, right? Correct. Yes. And actually, this is interesting because one of the books I read recently, which I really like, is called Everywhere Millionaires. And it's really about two academic economists who, after grad school, went to the U.S. Treasury Department. Oh. And they were trying to understand small businesses and they got stuck trying to understand it until one of them gave a talk somewhere in Utah and ran across the guy who built the system.
19:40Ben Lorica: And all of the understanding around and the whole book and their entire research agenda flowed out of this guy explaining to one of them what these tables are. And, you know, because it's just not documented. Yes.
19:55Deepti Srivastava: So this is my concern about things like catalogs and ontologies, because once you document it, it becomes stale.
20:02Ben Lorica: Yeah.
20:03Deepti Srivastava: And it's always fragmented.
20:05Ben Lorica: Right.
20:05Deepti Srivastava: Right. And so those are great as starting points. But in order to understand the system, you actually need to know what the live beating system looks like. Right. So we do automatic schema detection, drift detection, and then update semantics as an example. These are like little things, but they are so difficult to deal with and require so much manual work, even today.
20:26Ben Lorica: So to the defense of the rest of the industry, you're not the only one trying to do this kind of automatic semantic layer construction, ontology using AI, right? So have you paid attention to what others are doing and where do you think you shine in this area? Yeah.
20:48Deepti Srivastava: To be honest with you, I really don't think people are treating it as a holistic problem. So Snow Leopard is based, built on the fact that we need a new data architecture, a new data stack for AI.
21:03Ben Lorica: Well, for one thing, you're not a data management provider. So you're not assuming that everything we just mentioned, semantic layer construction, ontology construction, is limited to your data management layer, right?
21:20Deepti Srivastava: That's right. So we pull out from being part of any one data management system because that data management system is very optimized for them and don't care about all the other systems out there.
21:31Ben Lorica: And the reality is most big companies use many different vendors. That's right.
21:35Deepti Srivastava: Data silos are a fast of life, right? And so number one is that. Number two is we're actually looking at it as a holistic problem. So not just ontology and automated semantics generation, but also upkeep and maintenance. So we have three pillars, right? We have the automated contacts, which is automated semantics intelligence, automatic and live federation, right? Governance. And on top of all of these is ease of use. So we care really a lot about most of the people on your podcast probably have this problem. Like we care a lot about how do we make the lives of people who are managing these systems easier, which is why other.
22:12Deepti Srivastava: So other to your point about competitive analysis or landscape, people focus on just the ontology or just a schema reading or just a semantic layer overall. Right. Build a graph database and you'll have semantic layer. Build it. Use this ontology system and you'll have ontology. right but you need more than dbt has a great way for you to do metrics google has a similar one to define ontology to define metrics to define pipelines but you have to do the work right with with non-operative approaches we'll do all the work that we can and then allow you to tweak where you need to that's number one number two there's going to be another system that will federate i don't think any system is federating right now by the way i've looked many times unless there's a verticalized solution where they're selling you a solution right an analytics solution, most people that are in this space are selling an analytics solution.
23:02Deepti Srivastava: We are selling a platform on which you can build your own analytics solution and you can build your own agent of any cunt, right? And so the third thing is governance, which is then the governance becomes a third solution. So the main point is you as the end user or the builder have to pick multiple different solutions in order to build a full end-to-end application you want. And with Snow Leopard, We're trying to make most of that, like, not something that you have to deal with, like pick this vendor for governance and this vendor for MCP and this vendor for semantics and this vendor for federation.
23:34Ben Lorica: So this is a hard question to answer, but how much of this unwritten business knowledge can an AI reasonably infer? I guess that's why you have this feedback API. That's right.
23:47Deepti Srivastava: Yeah. So we started with no human feedback is required. And then I very quickly got to SAP HANA and SQL Server and Salesforce are not that easy to read. Right. And so, yes.
23:59Ben Lorica: So this feedback API, let's say I provide you this feedback, right? So there's two departments and they define active customers differently. But actually, department A's definition is more accurate. So then I give you that feedback. How quickly does the system adjust?
24:21Deepti Srivastava: Within a few minutes.
24:22Ben Lorica: Okay.
24:23Deepti Srivastava: So again, just because you've given me feedback or Snowy feedback doesn't mean we're going to take it, right? So we have a whole verification and analysis and judgment layer in the feedback system that will actually look at where it applies, whether it makes sense or not, and then it'll apply it, right? And then we have, like, we apply it immediately to your session, and then we see how the session is going, right? And then based on that, we will bake it into the system. So we are very careful because we don't want bad actors to change definitions, obviously. But we can take it and absorb it in real time.
24:56Deepti Srivastava: So this thing you gave me, just to pinpoint on that, like you said, Department A's definition is different, let's say, from Department B. Whether it's accurate or not, the system doesn't know. But we can actually say this is Department A that's talking to the system, to the same system, to the same set of data sources.
25:12Ben Lorica: You know based on my role. Correct.
25:15Deepti Srivastava: And so we can actually apply it for you and not apply it for the other one. So the technical solution here is we layer semantics.
25:23Ben Lorica: But what if I assert that actually it's universally understood by the rest of the company except for company B, that my definition is the correct one?
25:33Deepti Srivastava: You mean team B, right?
25:35Ben Lorica: Yeah, yeah.
25:36Deepti Srivastava: Yeah, and then that's fine. If it's team B, that's, again, we have roles. So if it's somebody from Team B asking the question or using the agent or the agent is assuming the role of Team B, we can answer that way versus not, right?
25:49Ben Lorica: So 95 % accuracy sounds great, but that 5 % might break my business. If I'm 5 % inaccurate, it might drive my customers away.
26:02Deepti Srivastava: Yeah, I think there's two answers.
26:04Ben Lorica: So then you have this feedback mechanism, right? Right.
26:07Deepti Srivastava: But I think, Ben, the answer is let's be realistic. What are you getting today out of the box? Right. Like for anybody that's doing this. Right. Like if you just connect and go, which is what we're promising, which no luck. We're just connect and go. Right. The idea is, again, like you can see how far the system can get and then you can give feedback. Right. That is the point. And like you can do acceptance off the system as the administrator. Like we give you the tools to do the acceptance on your own, but without having to build everything. Right. And so no probabilistic system is going to give you 100 percent determinism out of the box.
26:40Deepti Srivastava: Our aim is to marry these probabilistic engines with the deterministic outcomes, reaching as close to 100 as possible. Like even humans make mistakes. Right. So obviously, we're not promising anything that is like foolproof or bulletproof, but we're trying to make it as close to that as possible. And I think today it's even more possible with LLMs and Gen AI than it used to be even three years ago, even when we started two years ago.
27:06Ben Lorica: So then now I have, let's say I deploy Snow Leopard, right? So now I have my agents having access to the right data at the right time. But now I have a single point of failure, which is Snow Leopard. If Snow Leopard goes down, I'm screwed. Good. So what do you say to listeners to say, well, I'm going to wait until DeepTee and company have more of a track record. I know that this is hardened and so on and so forth.
27:33Deepti Srivastava: Yeah, I think nothing I say will make somebody change their mind about what risk they're able to take or want to take. I will say try it. And the other thing is we have been with financial services companies that have been using us. And so I think the point is we work with you. Yes, we are an early stage company, but we work with you in order to get you to add the kind of reliability you want. And then because our solution is BYOC, we can be inside your cloud. We can be on our own cloud. So we aim to be the strongest link in your chain because clearly with data, there is a chain and there are weak links and strong links.
28:10Deepti Srivastava: I want us to be the stronger link on the chain, not the weak one.
28:12Ben Lorica: So what are some of the DevOps numbers that people want to know? So uptime, latency. Latency depends on the source system to a large extent. Concurrency. What if you can only support two users at a time?
28:31Deepti Srivastava: Yeah, I don't think that's a matter of... That's not the case, right? Because we are from the NARDA built to be cloud resilient. And so we have high concurrency. We can support hundreds of users at the same time. The on-prem deployment, again, concurrency is a function of like how much resources you give to it. Right. And so like the on-prem deployment, we can like parallelize. We have built a system to be parallelizable and highly efficient from the ground up. Right. We are a bunch of like systems engineers and AI engineers to start. So then we've built it that way. I think in terms of latency, we add some microseconds, if at all, to those responses.
29:12Deepti Srivastava: We are faster, by the way, 10x faster than MCP directly.
29:17Ben Lorica: And you don't burn all these tokens, right?
29:19Deepti Srivastava: And we are half the tokens. Yeah, I was going to say that. We're 10x faster than MCP and half the tokens on average. Again, it depends on what you're doing, but we're half the token on average.
29:27Ben Lorica: But also you have this federation, which is key to, I think, a lot of making agents useful moving forward, right?
29:37Deepti Srivastava: Yes. I truly believe that without having federation in some format, people will not be able to use autonomous agents for critical workflows, right? Because you really do need to have access to the right systems for the agents to really be autonomous.
29:50Ben Lorica: So since you've made federation respectable, I have to point out that Databricks, I'm an advisor to, has also made another thing respectable, which is, what is it called? The hybrid transactional analytic systems, right? So unifying OLAP and OLTP. So let's set that aside. It works well, but you have to be in the Databricks world, right? So another approach besides this unifying transactional analytics storage is, I guess, streaming? Are people trying to do this with streaming?
30:26Deepti Srivastava: I think they're trying to. From the people I speak to, I spoke to a head of data and AI in MarTech. It's the second largest MarTech firm in the US. And they were like, it just doesn't work for them, for a lot of use cases.
30:40Ben Lorica: So maybe explain to our listeners what we mean by streaming in this context. Yeah.
30:45Deepti Srivastava: So the idea is going back to Kafka and the pre, I think all of this is pre-world, pre-AI world is what I'm talking about, right? Like pre-gen AI world to be specific, where consolidation was the only way to do a bunch of things because we hated federation for various reasons. And so one of the things was you stream data out of databases and into a warehouse or into a lake. And in the stream, you can do a bunch of cool things like attach SQL on top of the stream. So you could like, you know, make queries happen for dashboards or things like that. Right. And then you have high, like faster streaming or broader streaming.
31:23Deepti Srivastava: so you can have multiple databases that are pushing to the same data warehouse or lake. And then you can then do sort of transformation in those streams so that you can basically have views on this data in motion so you can make faster decisions than you could with only the warehouse, right?
31:41Ben Lorica: How does this help me in the context of an agent trying to look up something like an order? Are you going to be honest with you?
31:48Deepti Srivastava: I don't know. Because how reliable is the stream? So you're doing a bunch of manual work and it makes for those people who are doing a bunch of manual work to build functionality around these streams, like maybe it works for them for specific use cases. Right. I think the point I'm trying to make is.
32:04Ben Lorica: But it's very hard to every use case. You have to do it. That's right.
32:09Deepti Srivastava: It's custom. It's brittle. and you have to, like any column that was added to the table, source table, now you have to change the stream because streams have definitions to add that and then put in the warehouse.
32:22Ben Lorica: Well, I have an AI to do the semantic layer for the stream.
32:26Deepti Srivastava: Yes, yes. And to like not have to, I think the point is people started using streaming as the way to query because putting it in the warehouse was taking too long. So this is, again, another way to say near real time, near real time. It's not real time. And also you define streams, again, for specific workflows, like data pipelines are designed to be specific. So if you try to use a data pipeline or a data stream for everything at all times, it's going to break because it's like, you know, it's like round peg square hold situation. Right. So the way to build applications on top of streams became a way to do sort of fresher data.
33:05Deepti Srivastava: Right. Like not have staleness because it's stale by the time it gets to the warehouse. But the other problem with that is it's transformed. And so you've lost meaning in the pipe because you had designed that pipeline to be for analytics, for example, for historical trend analysis, for example. So you've made the columns and rows picked specifically for that use case. Right. And so now you don't have the full picture. So if you're going to put something that is a decision making agent on top of that stream, it's not going to have the full picture. It's going to give you wrong answers, like just point blank.
33:34Ben Lorica: Right. So what I like about what you do is you're not making copies of the data, right? Yes. So you're hitting the data where you need it. And then you make the reasonable assumption that, hey, data is not going to be conveniently located in one system. It's going to be located in multiple systems. And I need the freshest data. So I don't want that data to be copied first and then before I hit it. All of that is well and good. But obviously, one thing that people have been reading about is these agents going rogue scenario, right? So now I have a scenario where these agents can interact with an application that's hitting my live systems and making all sorts of potentially nefarious requests.
34:21Ben Lorica: So I guess what you alluded to this earlier, you have the notion of governance and all of that. So what are some of the things you can say to reassure listeners that this doesn't open up their systems to rogue agents?
34:36Deepti Srivastava: Yeah, I will say like if you are using MCP today, you're already open to rogue systems, right? Because MCP by definition, by on its own, is just like HTTP, right? It doesn't have any of that governance built in. So I actually feel scared when people are using MCP on top of their databases, right? And then because once you have MCP, there's just two APIs, right? So all it does, it has access to all of your data and all of your schema, unless you do custom work inside the MCP or on top of the MCP, right? So again, now we've gone to custom work. So just as like a rule, I think by itself, MCP doesn't help you solve this problem.
35:10Deepti Srivastava: So then people are, as I was saying earlier, vendors sell governance on top of MCP or governance built MCPs, right? That then you have to configure. So with Snow Leopard, the point is because we sit outside of all of your data sources, like in between your agent and your data sources, We can actually be that person, sorry, the system in the middle that can arbiter, like I can route things to different places and only when it's allowed. So one of the things I talk about in this ACM article is like governance on not just roles and access control, but who and why. Because an agent can impersonate.
35:45Deepti Srivastava: In fact, that's how most agents work today. You impersonate somebody else's role.
35:49Ben Lorica: I mean, people are going to start using agents like Muse and Dots, right? Right.
35:54Deepti Srivastava: Yeah. I mean, the thought is scary without governance. And so the point is, because we sit outside the systems, when an agent makes a call, the agent itself can tell us and needs to tell us like who it is and what it's trying to do. Right. Team A versus Team B in your earlier example. And based on that, we can like federate maybe Team A only has access to.
36:13Ben Lorica: Or what about if I'm a Muse agent acting on behalf of Ben?
36:17Deepti Srivastava: Yeah, same thing, right? Like, because again, if Muse has to interact with Snow Leopard and you, so there's two things happening, right? One is Snow Leopard knows it's Muse and therefore has access to Ben's credit cards, but maybe not direct bank account and direct sell. And so we will not let Muse do that, number one. Number two, so what that means is we arbiter where you're going to go, or we have the ability to arbiter where you're going to go based on who is asking the question, which agent and on behalf of whom. Second is you can actually set up Snow Leopard to have access to only certain set of data to begin with, right?
36:52Deepti Srivastava: And because it's just a matter of connect and go with Snow Leopard, you can just add or remove not just data sets and data sources, but tables. So, for example, you can give today access to Snow Leopard to one of your, let's say, BigQuery data sets and some of the tables in that BigQuery data set, right? So we use a combination of existing data-based access control as well as agent-based access control of what are they trying to do and why are they trying to do it and then push that down to get the right information. So because this stuff is outside, even if Ben has access to all of their financial systems, all of your financial systems, maybe the agent Muse does not.
37:34Deepti Srivastava: And so we can enforce that because we're sitting outside.
37:36Ben Lorica: So as I opened this podcast, I used the word retrieval. So that implies read only. Correct. So do you think that there will be a future where Snow Leopard can update these databases or never?
37:50Deepti Srivastava: 100 % yes. It's just a matter of giving read access versus write access. I think right now, based on where the world is at, read itself is hard enough and scary enough.
38:02Ben Lorica: It's scary enough, yeah.
38:04Deepti Srivastava: Yeah, I think the scary part is more important. Like select versus update are just permissions, honestly, to a database. The way I think about it, right? Like a build database. This is just about whether you can do select statements or whether you can do update statements. And right now, we're not allowing Snow Leopard to do update statements, but we can. It's just a bit set. Again, these things are known. I just don't think there is enough trust in touching, not trust in Snow Leopard, but just trust in AI and autonomous agents in general. And we can, this is just a technology problem. And that's very easy to solve.
38:34Deepti Srivastava: I think the trust problem is a different problem.
38:36Ben Lorica: So this is probably something that is outside your system. It's more of a question for security teams, right? But when an agent uses Snow Leopard to retrieve information across these systems, whose permissions is it using?
38:53Deepti Srivastava: Right now, the permission is either granted through a service account or through a role that Snow Leopard is given access to. So, for example, for BigQuery, we use OAuth and SSO. And so then it becomes whoever the user is. Right. But if you set up a service account, then we can use a service account. Right. So it's up to the user administrator, really, to set up the right security role right now. And I don't think the security problem is solved. I think what I'm excited about for us is that we've built a system in a way and that we can actually add on to security and governance practices as they evolve for agents.
39:29Deepti Srivastava: Right. Because, again, we are not tied to one system. So we don't have to have if you are in this world, then you can do this. Otherwise not. Right. Like we are very easily evolvable. Like I believe in evolution because AI agents and autonomous agents themselves are evolving. And so I believe in evolving the system to that. And I think the way we've set it up, there's a lot of room for us to evolve as the industry evolves.
39:51Ben Lorica: So this semantic layer construction, automatic semantic layer construction, it seems like, so do you think most companies have systems in place where when you come in and you try to infer their data, the semantic layer automatically, do you think their systems are well architected enough so that out of the box, this semantic there is reasonable? Yeah. Because the reason I ask is there's these teams in companies. One of the most awful jobs in these companies is this thing called master data management. Have you heard of it? Yes. Right? So it's like a manual. A lot of people doing all of these things manually, right?
40:34Deepti Srivastava: Yes.
40:35Ben Lorica: And so then to me, that implies that maybe because their underlying systems are a mess. So if their underlying systems are a mess, then how well will this automatic inferring of the semantic layer work?
40:50Deepti Srivastava: Yeah, I think this is a common refrain from people who are on the data side of the world, right? From people who are trying to build agent side of the world, they're like, just give me something because right now I have nothing, right? So yes, data is a mess. I think it's messier than most people think it is. But also, there's a lot more we can do. like it is surprising to even us what we can do with the harnesses in the way we've built them for Snow Leopard, right? So we can actually get a long way through. And the last, this is why we added feedback, because whatever the last mile is, because nobody's guaranteeing that the data will not be messy.
41:26Deepti Srivastava: I think there are two things. One, getting started is the hardest part with this data, because if you're going to have a two-year-long project to move everything onto Yeah, yeah, yeah.
41:35Ben Lorica: That doesn't work. System of choice. So you guys come in, you infer the semantic layer, and then I assume the first set of users are people in the IT group. Yeah, the administrators.
41:47Deepti Srivastava: Yeah, exactly.
41:48Ben Lorica: So then they're trying to give you feedback before they deploy, right?
41:52Deepti Srivastava: That's right. And the thing is, you can continue to adjust, right, very easily because the APIs for the agents are very simple and the user interfaces for human beings are also very simple. So if IT approves something for the marketing department, the marketing department can then go off and fine tune it. The other problem with these master data management jobs is that there's few people trying to address the needs of the entire company. So if you can set it up so that each team at least can use something without you having to worry about it and without you having a huge queue of work for each of those systems, I think that's a huge unlock for the company overall.
42:31Deepti Srivastava: all, right? And then the other thing is, like, I want to just sort of bring it down to, yes, data is messy, but we can do go a long way, right? With that, without too much human intervention. And then you can add the human intervention to tweak, which is a time saver versus start from scratch. Second, you can allow, because of the way the APIs and the feedback is set up, even people who are not in the IT department can give feedback in order to like adjust semantics, etc. Right? So you're not constantly going back to the IT department. Very quickly, I'll give you an example. Like, again, this fintech company we worked with, we worked with the founding engineer who is also like basically the head of data managing all of this stuff.
43:12Deepti Srivastava: And he could reduce his workload because he could just point people to the Snow Leopard based agent to answer a bunch of questions instead of him having to build DBT pipelines and then writing the SQL and then iterating over the SQL and then giving them the answer. and then having to do that for every team and every question all the time.
43:33Ben Lorica: As I understand it, you have some sort of tool for explainability, right? So in other words, when I first deploy you and I'm in the IT team, not only am I giving you feedback, there's a certain level of explainability. So I'm reassured that, okay, so it's hitting the right systems, it's writing the right SQL.
43:55Deepti Srivastava: That's right, yes. Yes. And that sort of built-in explainability is sort of right in front of you. So if you look, so the API returns it, by the way, so that even if you build autonomous agents, agents can verify if you put the verification loops in there, by the way. So we have APIs for both the agents and the humans. The humans can see this on our website, too. The human can see the SQL being generated, the data sources being targeted. And the reason why and how we built like so it's national language explanations of the SQL query we built and why we built it. So you're talking to your agent or your agent is talking to Snow Leopard and it can see what happened.
44:30Deepti Srivastava: So you can say, oh, it built SQL with this table and this column, but actually it needs to use this other table or this other column for this specific question on churn or on profit. Because these can be very, very ambiguous terms that you said, different for different people.
44:47Ben Lorica: So what feedback have you gotten about this explainability tool? Is it good enough or do you have plans to tweak it and improve it?
44:57Deepti Srivastava: Both. We have gotten feedback that is better than what they've seen. So they're excited about it because they didn't even know that you can guess this kind of like detailed information. And then the common one I get is, can you draw it as a picture? Essentially, can you build an ER diagram? Right. Right. And I think that's like, or a graph or something that says we went here, we went here, we went here. So that's something we are considering adding. We can also do it custom for like, you know, especially for messy data or for large teams. Like it makes more sense to just visualize it very quickly, especially the ontology part of it, the semantic layer part of it.
45:32Deepti Srivastava: Because it is hidden and a lot of data people are like, I don't like hidden. So, you know, showing it in a visual format is something they're considering for sure. But I want no feedback. And if people are more interested in having one way or the other from your audience, I would love that. So please let me know.
45:48Ben Lorica: So if someone makes an adjustment to the schema or gives you feedback, and therefore you have to make an adjustment. So some adjustment is made, right? So can you go back in time and understand, okay, so we showed Ben this last week, but we should have shown him this in light of what we know now?
46:10Deepti Srivastava: Yeah, that's a good question. So we have auditability because, again, I come from the day world. I don't like it if I don't know what the steps were. So, yes, we have like auditability where you can see even today in the cloud product today, we have some auditability where you can say this person gave this feedback. and it was applied to this database, right? And once it's applied, it means it's there, right? Now, do we explain or have the whole stack exposed? I think we have it exposed to us in the backend from a debuggability perspective, from DevOps perspective. I don't think we show all of that in the front end, but again, we are early, we're very open to feedback on how people would want to see it.
46:49Deepti Srivastava: But again, we've built a system because I know our people want to see more and more and more and have more transparency.
46:56Ben Lorica: So Snow Leopard is basically all about SQL databases and data and SQL databases. So any plans for other types of data?
47:05Deepti Srivastava: Yeah, it's not just SQL databases anymore. It's Salesforce as well, which is Socko, is an API. And like graph databases are not SQL. So we will add as many connectors as we need based on the customers. So far, we've had mostly folks who want to connect or join across sort of one of these databases, right? SQL databases and Salesforce seems to be the most popular API, but we are absolutely set up for APIs as well. Structured APIs, not blob APIs.
47:32Ben Lorica: Never unstructured data.
47:34Deepti Srivastava: I just think there's a whole body of work and research and vendor. Vendors out there that are doing that. I think this is a hard problem and I have expertise in this. I just want to solve this problem.
47:45Ben Lorica: So if you look three years ahead, what will the data stat look like? Obviously, Snow Leopard is right there.
47:51Deepti Srivastava: Yeah, I think the data stack needs to have agents, a data, this is another bad word, middleware, but data middleware, right? And then the data sources at the end, right? So one of the things that I didn't say earlier is, you know, we are not saying no to warehouses. If the data exists in the warehouse, we can go get it from the warehouse too. Really, it's just a question of where is the data? And like, if you have a RAD vector store, basically, for RAD pipelines, like, we can query from that too. That's not a big deal either. I think the point is federation is key because you need to know where the data is and how to get it from there.
48:29Deepti Srivastava: Right. So I imagine the stack having governance as a pillar where the governance is around both the data as well as the agents. So not just what, but who and why are one of the key pillars for the data stack for AI agents. The other is just federation has to be key. And so it needs to be really, really easy. It cannot be consolidate everything into one place. I just don't think that works. I mean, I love, I'm not saying what Databricks or Snowflake are doing are not great. I can, it is, but not everybody's data everywhere is in one place. And so federation has to be key, live federation. And then the third thing is this machine readable, automatic understanding of the business context, which we call the semantic layer, but really it's automatic understanding of the business logic.
49:16Deepti Srivastava: has to be a part of it with human feedback, whatever form that takes, right? Regardless of no leopard, I think these three are the key pillars in order to make autonomous decision-making agents work.
49:28Ben Lorica: And by the way, if agents actually start writing more code, so there's no reason why they wouldn't write code for the data teams and the data engineering teams. That's right. So which means actually the data stack itself will change constantly because maybe, you know, because now you're coding, you're using coding agents. Oh, let's rebuild the schema in the database tomorrow, right? So fire up agents. Next week, we have a completely different schema and whatever, right? Or we never used this piece of infrastructure because we didn't have in-house expertise. Now we can use it, right? So then people might be constantly making adjustments to their data infrastructure, which means this middleware might actually be super important, right?
50:19Ben Lorica: As long as the middleware constantly infers all these changes, right?
50:23Deepti Srivastava: But this is my point to you. Like, I think we're talking, a lot of the concerns that you brought up, which I hear these are legitimate concerns, are from a world where like humans are curating carefully all of this stuff, right? But we are going to an Asian first world, right? Some of us are already there, others are getting them, right?
50:40Ben Lorica: So in a world where people are throwing away code.
50:44Deepti Srivastava: That's my point. Even in an agent-first world, it does not matter what the pipeline is, what the code is, because it's going to change every time. And so that's why we have automatic semantics and automatic schema drift detection, right? Because we have to actually update based on what the agents are doing, right? So if the agent is changing the data underneath you, like you didn't even know what it was doing, right? Because you care about outcomes. Muse is about outcomes, for example, right? And so to your point, if everything is changing, the middleware has to understand that something changed semantics changed context for you know getting data from the right place has changed and so all of this it just has to be like automatic at machine speeds not human speeds and with enough verification where governance comes in right so i think the agent first world requires us to be in this sort of three pillar system right for data especially and yes like we will get there in time until we do need to have human interfaces but agent first means agent interface agent machine like agent speeds machine readable stuff and not worrying about everything always being hand curated because it cannot be and
51:54Ben Lorica: and static right because i guess the the world i'm imagining is these data teams who will become bolder and move faster and they will you know throw away pieces of their infrastructure more quickly and then so you need you need this kind of snow leopard layer so that your agents can access the data as the data team is constantly ripping out and replacing things underneath you
52:22Deepti Srivastava: right yeah and you have to be efficient with that right so so we i think static is a great world Like, I just don't think we are going to go from a static world to a dynamic world. We're already going there. If we believe like agents are going to create and undo databases as a result of whatever work they have to do or as part of whatever work they have to do, then these things become all automated, right? Like the middleware has to exist and has to have strong boundaries in automation in order to enable the data teams to do that.
52:51Ben Lorica: And with that, thank you, Deepthi. And you can learn more by visiting snowleopard.ai.
52:56Deepti Srivastava: Thank you, Ben.
53:02Ben Lorica: You can follow the work of D.T. Srivastava online at snowleopard.ai, and you should definitely check it out. I think it's going to be one of the more useful things you will be trying as far as building agents. Please join the thousands of people who subscribe to our newsletter, which you can find at gradientflow.com slash newsletter. Thanks for joining us. If you like the show, please subscribe and rate us through Apple Podcasts or Overcast or TuneIn.com or Spotify and never miss an episode. The Data Exchange Podcast is a property of gradient flow. And I'll be back next week and we will do this all over again.
Deepti Srivastava, founder and CEO of Snow Leopard, joins us to discuss why AI agents need access to live enterprise data and why traditional approaches to data integration may not be enough. We explore how AI is making data federation and automatic semantic layer construction more practical, and the challenges of accuracy, governance, and reliability.
Subscribe to the Gradient Flow Newsletter 📩 https://gradientflow.substack.com/
Subscribe: Apple · Spotify · Overcast · Pocket Casts · AntennaPod · Podcast Addict · Amazon · RSS.
Detailed show notes and transcript, can be found on The Data Exchange web site.