Swapnil Bhartiya: Nowadays everybody is using AI and AI is making software ship faster than ever. And depending on who you talk to, it is exciting. But nobody slows down to ask if your database can keep up with that. Now there are more queries, more complexities and not nearly enough expert to actually handle it in real time. So you may think the easiest solution, throw some AIs, throw some LLM at it and they will handle it. And yes, they do handle, but what if? Not what if, but they will hallucinate. And when they hallucinate on production data, there is no undo button. That is exactly the gap neverblink was built for. It is the world’s first AI database administrator and it just added support for Clickhouse. And today we have with us Itmar Sin Hreshko, CEO and Founder of neuralblink. To break down why you need your own kind of data based AI administrator, not some general purpose AI. First of all, Akmaar, it’s great to have you on the show.

Itamar Syn-Hershko: Thank you. Great to be here.

Swapnil Bhartiya: It’s my pleasure. As I was trying to understand the problem and try to explain the problem and what you folks are trying to solve. So here, if I was wrong, please correct me and also try to explain what this company is all about.

Itamar Syn-Hershko: Yeah. So when you connect LLMs to your database, you don’t get a second chance. So effectively, if you connect LLM to analyze and hopefully also fix any database issue when it actually happens, you can trigger a really bad domain effect and you don’t want that. So you want something to watch over your databases at all times, let you know when something is about to happen or prevent things from happening and if something has happened to let you know how you can fix it and be safe about doing that. So we built neverblink or in the previous name that it was Pulse way before AI was big. And we had a lot of decision trees and things behind the scenes that can do a lot of smarts. So we effectively built a platform that, that can figure out issues, do root cause analysis on real issues and find ones even before they become issues. And now we have AI to help us do things even better. And because we have that platform, we can be the honesty layer or the truth layer for any LLM wanting to know a database performance, database reliability status.

Swapnil Bhartiya: Can you talk about why do companies actually need an AI database administrator? Can’t they just rely on human experts? Because there are so many of those.

Itamar Syn-Hershko: Absolutely. So database experts are actually not that common anymore. It has been a really big topic or job dba. Right. Database Administrators for a long time, it’s not that common anymore. And also a lot of companies don’t really see a big need for that. Right. So they would say, okay, we have a database, it’s mission critical. Sometimes we need to bring in a company to consult us on fixing issues or optimizing databases. But it’s not a big topic anymore. Nowadays engineers are expected to fill in the gaps themselves, especially in the AI era. And there’s a lot of managed services that offer a lot of those, you know, optimizations or removing the hurdle of running database on infrastructure yourself. But it’s, there’s a hind side. So there is a lot of things that you’re actually not seeing as problems, which is the queries that you write, the table definitions that you do with OpenSearch, Elasticsearch, we used to handle a lot of index mapping issues and so on and sometimes you meet that those issues a little bit too late. So it’s not a problem that you foresee having and then when you have it, you are in some sort of a crisis mode that you want to fix at that point in time. And that is what we are often solving as consultants. And that’s why we build a product that automates a lot of what we do as consultants.

Swapnil Bhartiya: You also talk about why we just can’t use general purpose LLMs like ChatGPT or Cloud or Gemini. There are so many out there to handle the database on its own. Why we need specialized, you know, AI.

Itamar Syn-Hershko: Yeah, it’s a good question. We get that all the time, as you would imagine. And the truth is those models, they’re really good, they’re becoming even better every point in time. But there is two issues here. One, and you can try this yourself. So we are discussing the Clickhouse new support that we have launched. If you go to ChatGPT, you go to Claude and you ask them a question about Clickhouse, 80, 90% of times you’ll actually get, it’s not full hallucination, but you’ll get the LLM to lie to you. It will not be as accurate. And there’s a simple answer to that. There is not enough information about Clickhouse out in the wild. There are documentation, the technology is still changing. There are a lot of changes to the technology itself. And we see that as expert consultants working with customers all the time. There is a lot of things that customers don’t get right, sometimes because of knowledge gaps, sometimes because they asked LLMs and that’s one. And the second, even if the LLMs were good at that you still need some layer of, let’s call it guardrails. I called it honesty layer a few minutes ago. And effectively you don’t get a second chance. You absolutely want to make sure that any decision made on your database to change it, to optimize it, to fix issues will be spot on. And that’s why we built Neverblink also.

Swapnil Bhartiya: But we have seen. I am heavy user of AI myself and almost 90% of what we do, whether it’s personal or private work, is through AI. Is that because of whole token cost and everything else. The quality of AI is also kind of even some front end models or fable even you can see them working as good as open with like cran. So you cannot even. And when it comes to database you don’t have that luxury to. So can you also talk about the quality control, the whole governance that is also required. Also when you talk about databases, we can also talk about regulated industries, we can also talk compliance. So there is not that much room for error versus writing a code and testing it and doing something like that versus databases. Because apps can come and go. Database is what I would say is like your oil, your solar energy that should not be shaken.

Itamar Syn-Hershko: Yeah, absolutely. So we deal with the operations side of the databases, right? And that side is super important. And it’s like I said many, many times, it’s something like an afterthought, right? It’s so critical but people are just, you know, pushing ahead, pushing hard and a lot of times it’s just easier to throw hardware or money at the problem. So just use larger instances and fix things like that. But there is a point where that doesn’t work anymore and we are there to catch everything before that happens or, and when that happens, give you the, the right solutions around that. We are working on features like you know, gating queries, gating expensive queries, detecting that as that go on and suggesting query optimizations and so on. So the idea is to make sure that we are the depth layer of any knowledge gaps or missing knowledge on the database layer. So you’re, you know, any development team, product team can move fast and not worry about the databases. They didn’t worry about it so much before anyway. The data platform is something that we see a lot of times is sort of, you know, negligent. So there’s a lot of negligence around there. There’s a lot of times where we get to a customer and the data platform is just not built to scale and it’s, you know, being rigged as we go. And nowadays with everything that’s going on with AI, there’s a lot of shift left, movement. So a lot of product teams or a lot of companies, software companies, are expecting their engineers to do more. And part of that is the database. But you cannot expect someone to just know everything. So they become sort of jack of all trades, master of none. And that’s pretty much in the job description nowadays, except you cannot really miss on the importance of databases, the data platforms. And that’s what we are trying to solve here.

Swapnil Bhartiya: Excellent, thank you. Can you talk about what are some of the biggest headaches teams run into once database moves from kind of testing to production?

Itamar Syn-Hershko: Yeah, the scales, the scales are just different. Right. So any testing, any development will always be in small scale. Any query, anything will basically work there. Also in production, you know, when you’re small it will work well and then at some point it’s going to break. If you are an expert and you’re looking at the database and you’re reviewing queries, you’re reviewing how the table is built, you’re going to spot issues early on. And then the idea is to find those things now in an automated way and make sure that doesn’t hit production or we catch that before that happens. And then that is the biggest hurdle. Sometimes you grow into that in production. So everything works nice in production until it doesn’t. And sometimes it’s deploying something faulty from staging, which is large but not large enough, into production, which is too large for what we’re trying to do.

Swapnil Bhartiya: You just added Clickhouse support. Can you talk about, of course, why Clickhouse and what does that actually change for teams running it? And then I would also like to know, you launch it now. So I will not ask about how people are using in production, but I’m pretty sure you did some beta testing as well. So I want to also know what their experience have been so far. But let’s talk about the first part. Why Clickhouse and what does that actually change for teams running it?

Itamar Syn-Hershko: So why Clickhouse? It’s an amazing technology. It’s a really tie breaker technology. Right. So you, it allows a lot of things to be done that you couldn’t do before. And the growth of Clickhouse in, you know, in open source and also Clickhouse Cloud, the company behind Clickhouse that offers the cloud offerings is just tremendous. I don’t remember a technology growing at that rate ever. I’m not that old. But still. And given that, I think Clickhouse is the great candidate for the first technology that we are supporting. Beyond OpenSearch and Elasticsearch. We are already private beta testing some additional technologies. We’ll discuss that in future podcasts I believe. But for Clickhouse it’s just an amazing technology being used very widely for mission critical use cases. And that technology is just not widely known enough. Not by people because the technology itself is still changing and definitely not by LLMs because there’s just not enough information out there about the technology.

Swapnil Bhartiya: Now let’s talk about what has been users feedback who have been testing it in beta.

Itamar Syn-Hershko: Yeah, so we’ve been working with a couple of customers. Some were already customers of ours, but also have Clickhouse so we just let them use the platform and then some are dedicated customers. So customers who have been using Clickhouse on Clickhouse Cloud or self managed Clickhouse and they just needed a way to better understand what’s going on and improve performance. And most of the benefit for those customers were actually looking at the table. Our tables are defined and our queries are sent. So it’s ingestion into the Clickhouse and optimizing that or executing queries and making sure that the queries scan as little data as possible and run as fast as possible. And that has been the main benefit. So effectively getting a lot of queries improving their performance, dropping the P99 and P50 insignificantly to one or two digit milliseconds in many cases and just making sure that everything works well for them, even if they just don’t know the platform well.

Swapnil Bhartiya: Can you also talk about. Of course people are running their shops with cloud. Of course with MCP and MCP’s open source it has to totally change the game. Can you also talk about how well does you know your tool integrate with their solution, how it works with what they already have in place.

Itamar Syn-Hershko: So when people think about mcp, many times is connecting to a database and getting data from the database using an mcp, which effectively translates things that you ask into something that you can do with the database kind of commands or queries that you can ask it. We’re going to release pretty soon an MCP that is aimed at operations people, so SREs, which is site reliability engineers, platform engineers, DBAs and DBRs. So the people who are actually maintaining databases. So if you are a database specialist, the MCP that neverblink is going to expose will let you get good answers, grounded answers about your database performance, your database state and health and get those answers in a very safe way and grounded way so you can trust it in doing your job. If you are an sre. So you have wider capability, wider responsibilities way beyond the database. You can also rely on that to give you answers on the database. But what we see a lot is that developers who are now assigned platform responsibilities and are not in any way experts in databases or data platforms in general, they can now move faster by relying on neverblink to get them solid operation advice on managing and deploying and optimizing their databases.

Swapnil Bhartiya: Can you also talk about your business model?

Itamar Syn-Hershko: It’s pretty simple. Neverblink is a platform and the platform goes by what we think is very modest and an affordable price. And that’s just a platform you get. You can connect your database. Obviously we are stock to compliant, we don’t touch your data. And an agent, it’s a terrible name for that, but it’s still what we call it. You install an agent, which is just a metrics collector in your premises. It sends metrics to us and then based, we just optimize. We understand that and we provide those insights on the platform. On top of that we provide developer support. So our experts are available to help your team build anything and optimize anything. On top of clickhouse and again open Search and Elastic Search as well, and more technologies coming soon. And then we also offer 24.7enterprise support for Clickhouse, OpenSearch, Elasticsearch and that is on top of that. So you can think of it as a platform, platform plus consulting and enterprise tier, which is platform and full support end to end 24. 7.

Swapnil Bhartiya: And can you also talk about the importance of partnerships for you folks, what kind of partnership you have with the ecosystem?

Itamar Syn-Hershko: Yeah, we work very closely with aws. We are under several programs of aws, ISVA and others and we work very closely with them. We’re being brought into places where our expertise is needed and also now where the platform can help with optimizing cloud usage and so on, as well as some cloud researchers and system integrators, other consulting companies that are in need of expert help, and a platform like neverblink that basically it reduces friction and makes sure their customers are just moving faster and better with their data platform.

Swapnil Bhartiya: Itmar, thank you so much for breaking this down for us and of course for our audience who are watching this. If you are running Clickhouse, OpenSearch or Elasticsearch, please go to Neverbling AI and see it for yourself. Test it out. And once again, Itmar, thank you so much and I look forward to chat with you again.

Itamar Syn-Hershko: Thank you, thank you for your time. Swap and have a good time.