Chad Cloes, Intuit | Neo4j GraphTalk 2026

Welcome back to the cube here in San Francisco for Neoforj's Graph Talk San Francisco. They have an event in New York City which will be there as well in in New York City in September. an event where all the practitioners, insiders, and also the innovators get together to talk about the innovations around graph databases, ontologies, but also the future of the infrastructure uh and data structures in in AI that's that's really flourishing things into production. We're starting to see evidence now of of the of the data stack, how it fits into the AI equation. Chad Close is here. He's a senior software staffer at at Intuitit. Um those guys are well known for their open source work and innovation. Uh Chad, thanks for coming on. Appreciate it. >> Glad to be here. Thanks for having me. >> First of all, love into it. Have friends who work there. Great Silicon Valley company. But also, you know, hat tip to Intuitit for really being an enduser contributor to open source Linux Foundation, very active. And so props to to to you and your team. >> Yeah, we we we're proud of what we've done and uh we're glad to be part of the community. >> All right, so we're here at the Neoforj Graph Talk. This is where you know I seen this early in the early agent side agent infrastructure where you know the real you know experts come together to share what they're working on and graph databases and Neo4j in particular have had recent success just financially and on the business side but also the standards bodies you start to see graphs a key ingredient data structure with knowledge graphs in the AI equation uh explain what's the rationale behind this what's your perspective why is it happening is it just the moment in time. It's perfect timing. Everything's clicking. Or is there is there something else going on? >> Well, I I think it it's piggybacking on all the the inertia surrounding AI um and how everybody's trying to make it relevant and capitalize on the the ecosystem that is or andor the the buzz and you know the bubble around AI in general. Um I think graphs already were very relevant from a how do I make my data valuable? How do I make it useful? How do I monetize and or democratize that data? And I we have found that into it that that the graph layer gives that contextualization. And oh by the way, it's a it's a byproduct uh the byproduct of it is you can handle hand all that context that you've built with the graph to your LLM. Um what we found is that LLMs in general are all commodity now, right? you you turn to one one's a little bit ahead of the other. What differentiates your use of it is the context andor the data and how it's related in your ecosystem so that when you ask the questions it has the the the information that is relevant to your company. >> Yeah, Philip and I were just riffing about, you know, graphs and talking about he's like I'm like it's like uh you know, it's like 2D 3D, it's like black and white and color. Um and you know I I look at it simply as well there's grinding database work tables and schemas and then there's like freedom. Uh now I he went more black and white and color I went more you know grinding freedom. What are the what is your use case where where did you take uh particular attention to on the graph uh insight into it? Was it um security data? Was it explain your your your use case or where you leaned in and drilled into it. So for our team specifically, we're with the skip team security knowledge and insights platform. So the platform that we built was all around taking the the silos of data and tools, security tools or data swamps, uh data lakes, even if they were healthy. Um and taking that data and contextualizing and connecting it so that um you know the funny thing that that Philip talked about in his his talk is the the you know the 120 line SQL joins, right? you know, or we had some that were as long as 2,00. And the the irony in those SQL statements is you're recreating the relationships between the tables and the silos in SQL. Well, graph, you don't have to do that. It's just inherent. Uh you I think Emil is can be quoted as the relationships are first class citizens. The relationship between your data is almost more important than the data itself. And we found that that in that journey of connecting the data together, it it slipstream straight straight into AI. And we we predicted it about a year ago that graphs andor our platform was going to be key to our AI adoption and it truly has >> and it worked out that way. It did results. What specifically are are you doing? What's what's the outcome? What was the what was the result? >> Well, so our platform is uh it's all in service of doing security attribution. what resource is uh owned by what project, what team, how is it related to other things? Um for instance, you know, we have to do socks compliance or we have to do uh there's a 7216 is a is is a dictate by the federal government for tax data. So having the relationships between the data and and where that data is is is being used is relevant and is is paramount for us to be able to track and and uh make available um to the the company so they can make use of it. >> So you're mapping resource to projects, people, places, things, those kinds of things. >> That's great for audits, but I mean explanability is a huge issue right now on AI. I'm sure there's up upside there. Unexplainability. >> Yeah. So it the we actually have a property said that we use graph data science or GDS that we explain and the property is explainability. So when we we do an attribution of a resource to a um a resource or a project or a person it has that explanability. that says well this is the lineage that we manifested from our graph data science insight and we give that to the customer so that they have that data as well on top of it. >> Yeah I mean that's the holy grail right there. I mean people love lineage but when you actually have it inherently in the system as a first class citizen talk about production and reliability because you know you're seeing a lot of AI projects some make it to production some get it right some don't they get stuck in you know PC purgatory some say or just kind of just sit there on the one yard line you know to can you tush push it in and they don't make it there's no governance identity screwed up you're when you talk about security >> accountability >> I mean you can't screw that up I mean this is like there's audits There's also penalties. >> I mean, yes, there's a lot of pressure. >> How did you get it into production? What's the secret sauce? >> How did you nail the reliability? >> So, so if you're talking about reliability specifically, we do leverage the the reliability of of Aura and um knock on wood, you know, we've been we've been flawless in that in that regard. With regards to the re reliability of the data, um the reliability of the data uh evolves as you learn. And one of the things that we've we've found is that we don't know what we don't know and uh we democratize and we just try and make it visible because you know the the term I always use is I don't make the news I just report it. If we bring the data together and we we we make it available to people then they can make their own determinations and from a security perspective bringing things to light really is the the the way to solve those security those hard. >> So when you talk about authorization governance these are the table stakes we're hearing a lot in a lot of the AI convers especially around you know AI safety and whatnot. >> Yeah. >> Um >> what's the timing impact that graphs give you? um is it weeks to to days, weeks to months, months to weeks, what's the scope of some of the the benefits in terms of when you look at the outcomes that you get from say figuring out what the root cause of that or this was? >> Yeah. So, one of the one of the main tenants of what we attempt to do is we attempt to drive down MTR, which is meantime to remediate. And you can't do that if you're spending all your time figuring out where or who or what it's connected to. Um and uh when we started we were you know it would take days to do analysis on how things were connected. You have to log into seven different things. You had to have three different people with different credentials. Once you start drawing that data in and connecting it in a in a way that's um relevant um you again democratize the data such that it takes it from days to seconds uh days to seconds. We can we can actually run API calls against our system that immediately manifests this endpoint is associated with this project which is associated with these resources which is associated with these people. >> Is there a human in loop there? Is there agents doing that because seconds means this automation there? >> Yeah, that's right. Yeah. So we do we have automated systems that are constantly querying and then manifesting the the the the results to the the consuming systems. >> So the humans are curating or watching and managing okay keeping an eye on it. So the human is in the loop in the sense of are they doing what they need to do? >> Yes. So one of the systems that we we use is the human will prompt and say hey I I need information about this this this these sets of assets or these endpoints and um and then that data will get presented back to the the the the person. Um we do have automated systems that say okay if it meets these criteria this criteria is something that needs to be escalated and then it just automatically >> you said Aurora you guys use >> Aurora the Neo Forj aura in >> okay not Aurora AWS okay want to make sure I clarify that all right so this brings up the whole data ecosystem discussion and you know >> API cloud era was easy connect to an API all good but when you start getting into data transfer with agents and systems the the relationships of the vendors change. So how should people think about the their their data ecosystem platforms when they start bringing knowledge graphs in >> Yeah. >> It's a data inclusive environment. It's open. >> Yeah. >> Yeah. So one of the things that that we have prided oursel on is is if you pull that data in to we use Neo forj uh pull that data into the graph you can you can um abstract your system from whatever tool that you know the data lives in um you know whiz or uh you know data bricks or an S3 file or any of that stuff you you you create an abstraction layer that allows you to not be so reliant on the underlying tool or vendor. if that's what you're asking. >> Yeah. So, you can just ingest it. Yeah. And then manifest. Okay. That's right. Uh in your in your world um in security, root cause is a big deal. I know there's a lot of compliance too involved in if something happened, reports got to get spit out, all kinds of you know, forensics happen. How how much are you involved in that? That is that included in is a full suite of like okay just agents go to town, press a button metaphorically speaking like take us through. >> Yeah. So on the operation the security operations side um that that is not our team. Our team is is more about making the data available ingesting it um contextualizing it and then the the the SOC uses it for their type of forensics. Uh we're definitely getting drawn into those areas and uh one of the challenges that that we're going to have to face is some of that data can be sensitive and so we need to segregate andor uh you know make it available. um in in all of our cases from an AI perspective there's there is human in the loop now if it meets certain like I said before if it meets certain criteria then it can be automatic >> so they're your customer basically they're the customer >> wellense their user >> well our customers range from just the developer saying hey I I inherited this project I don't know anything about it give me all the context associated with this GitHub repo or this endpoint or this asset or where the AWS accounts so it really enables just you know >> all right take me through that I think that's a really good instru instructive. Let's just say I inherit the the project. >> I I need to look at okay, open up the book. Here's my GitHub. So, what plugs in? So, I'm going to what what do I what happens? >> What is it? What's my what my interface? What does it look like? Take me through that. >> Again, play byplay. >> One of the one of the things that we're proud of is that we have created this platform and on top of it, we've created an API and and that GraphQL API lends itself nicely to creating MCP and skills. So in the AI world, we have created an MCP server on top of our data ingest and our APIs that we can get out within minutes. And then the MCP server you you build the tools that are relevant to the developer. And then you know every developer nowadays is ingest is is using skills andor MCP servers in their AI context. And you basically ask the AI here you give the AI this is the MCP server that has the all all the contexts associated with our company. tell me about this particular piece and then it will then spider out and it uses the MCP server that uses Neo forj behind the scenes to give that context so that the developer can just ask >> summary I want to take the take my bike ride home give me a podcast >> exactly exactly right >> that was a dream scenario eight years ago now it's happening all right what's the coolest thing if you had to explain to a friend you know tell me about the crafts why should I do it what's the motivation what's your experience with it you know people seem to be jazzed up about graph s graph rags are we getting that good of results what's the pep talk or motivational speech um to give someone because I think once people see it and touch it and taste it they don't really go back >> yeah so I think Emil said you know once you see graphs you start thinking of graphs you see graphs everywhere the discovery I think is probably the coolest thing um being able to say well I don't know what I don't know I'm just gonna start ingesting it and it's going to evolve over time and that evolution and that journey really is the fun part of of being able to just stitch stuff together and see it grow over time. It really is a >> and the alignment with AI is pretty fantastic. And what's not really reported well and I want to get your reaction on this had more comment is that it knowledge graphs align beautifully with computer science. >> Yes. >> If you look at AI, it really is a testament to the the most alpha computer science wave we've hit since structured programming and punch cards went away. and and graphs can recurse. >> You can run through them super fast. It's aligned with kind of the neural network philosophy of of AI and deep mind and all the tools and and all the um great work that came out of the past, you know, decade. >> Yeah. >> What's your reaction to that? How would you I mean, that's kind of the probably the best motivation. It's how people think and work basically. >> Yeah. I think the the AI and the LMS it's I don't know if this analogy works or not, but I'm going to use it. AI and LM they're commodity. They you're just buying them off the shelf. Now graph is the Nordstrom experience of that data, right? You you put you put your graph in the context of what you're trying to do or your company or your specific use case or your exper like I think John was talking about in in his his um his talk is he uses it for health. It really is the way to take that commodity and make it relevant and make it real for you. Um, so >> yeah, I mean LLMs and are not the product anymore. They're just a part of the input. Yeah. The system. Yeah. >> It's funny. We were at the AMD event. Was doing a live stream there today, too. And uh, you know, we were commenting about, you know, oh, is who's got the best GPU? The real game is, is Nvidia going to win? Is AMD, Intel, everyone? Sorry, is the new hot IPO? And I said to Dave, I said, you know, to me, it's like whoever can in the fastest way possible redefine computing >> Yeah. to fit the way people think and work. >> Yeah. >> And that's because that's the utility that's growing bottoms up from AI which is it's not a guey anymore. So it's not like SAS. It's a natural language interface. >> So the experience is going to dictate to the stack which is growing. Every user is going to want it. So that change that changes the entire nature of this data stack >> completely and also changes the relationship for computing architecture. >> Yeah. I frankly I don't even care who wins, right? because I'm going to be pulling the data I'm going to be pulling the data into a graph making it relevant and real for me and you know it's going to be chat GBP today it's going to be Amazon Bedrock tomorrow it's going to be whatever it doesn't really matter because I'm going to be able to contextualize and use it in the most >> well this is the best thing about it general intelligence is the internet they already got that covered but if you look at a company like inuit and others there's domain expertise there's specialty intelligence there so that's that's the real value so you don't there's going to be a lot of inference going on. So you don't need the mega models to do inference and cool things >> even within the company. We find that you know there are silos of domain experts and if you connect inside those subdomains you're going to have the smaller graphs and the smaller graphs are going to connect the larger graphs and it really does >> I think that's where the models fit in. So again the it's funny we predicted this three years ago that the power law models and then that the power law they had is the popular ones. Yeah, >> that's general. But as you move down, open source and specialty comes in. And again, mixture of experts is just mixture of domains. And that's where I think grass highlights. J Chad, great conversation. Um, we could probably go another hour on grass again, but the strategic importance of graphs is it's compatible with the future architecture of where AI is going with easy results and benefits that you can get out of data. >> Yeah, in a lot of ways, I think it's a prerequisite. >> Yeah, great job. Thanks for coming on. I'm John F with the cube here. Neo4j graph talk San Francisco. This is where all the top engineers and practitioners get together to share their results and best practice and also new ways to use graphs. How to build that AI data layer, semantic layer, ontology. The new data engineering is going to be abstracted away with agents and of course the architecture and the data structures are all changing. Graphs are at the center of it. We're doing our best to bring that coverage to you. Thanks for watching.