EcoCast By ActualTech Media Solutions and Tools that Use AI to Get More from Your Existing Data

  • Automox
  • Glean
  • Everpure
Solutions and Tools that Use AI to Get More from Your Existing Data

About This EcoCast

Modern organizations sit on massive volumes of unstructured and structured information that often remain underutilized due to legacy processing constraints. This EcoCast introduces innovative platforms and intelligent software designed to extract maximum strategic value from your current repositories.

Participants will explore cutting-edge solutions that apply advanced machine learning models directly to internal data stores, enabling faster decision-making, automated document analysis, and enhanced operational visibility. The session focuses on evaluating emerging tools that connect securely to legacy databases, transform raw metrics into predictive intelligence, and streamline cross-departmental analytics without requiring complex system overhauls.

Gain practical strategies for identifying market-ready products that respect enterprise security controls while boosting analytical output. Equip your technical team with the insights necessary to select, deploy, and scale intelligent systems that unlock hidden operational efficiencies across your enterprise.

Why You Should Join:

  1. Discover innovative platforms to transform static enterprise data into actionable intelligence
  2. Evaluate cutting-edge automation tools that integrate seamlessly with legacy systems
  3. Learn practical criteria for selecting secure AI analytics solutions for your team

Agenda & Speakers

  1. Landon Miles
    Landon Miles Senior Technical Marketing & Applied AI Manager Automox
  2. Justin Swadling
    Justin Swadling Senior Solutions Engineer Glean
  3. Austin Boone
    Austin Boone AI Solutions Architect Everpure
    Erin Stevens
    Erin Stevens Product Market Director, AI Everpure
Full Transcript Scott Bekker Hello, and welcome to the actual tech media eco cast. Today's topic couldn't be possibly, or couldn't possibly be hotter or more relevant. It's solutions and tools that use AI to get more from your existing data. I wanna start by saying a big thank you for joining us. On the EcoCast today, we've got some of the heaviest hitters in the industry, with us, including Automox, Glean, and Everpure. So I am Scott Becker with Actual Tech Media, a future b two b company, and I'm excited to be your moderator for this incredible EcoCast. This is gonna be a great event. And I I need to start off by covering a few housekeeping items that are gonna help you get the most most out of your time here with us today. So let's start out in the chat tab on the right hand side of your screen. This is where we hang out during the event, get to connect with our fellow attendees, share thoughts, ideas, stories, whatever we're excited about. You can send emojis and and get to know our community a bit better. It's great to see folks from all over on today's event. We just got people checking in from Buffalo and Nashville, Colorado, South Dakota, Winnipeg, Ontario, Chicago, Arkansas, Western Washington, New Jersey, Wisconsin, North Dakota, Illinois, California, Winnipeg, again, Seattle, Hawaii, Atlanta, Pittsburgh, Montana. We had a comment there about the the Ravens, Chargers game. I couldn't tell, where you're checking in from, Luke. But, anyway, it's great to see everybody there. Keep those keep those hellos coming, and, and, and just, you know, keep using that chat. That's, that's great. Now… So chat is also the place to get help with any technical issues during the session. Don't forget that a browser refresh should get rid of any minor technical issues, but if that doesn't fix it, my colleague Riley and I are gonna be standing by to help you out. Now the absolute best way to dive into the information and insights we're gonna explore today is by asking your questions. So let's take two hops over, in in the tabs there to the right. There's a q and a tab. So while chat is for all those general thoughts and ideas and connections, q q and a is where you can ask your questions directly of our expert presenter, and their teams. So, be sure to take advantage of that q and a section. Now, we're gonna turn to the docs section or the docs tab. We've got some really great stuff to go along with the webinar today. There's a resource from each of the companies that… That's participating. So be sure to grab those and and check them out. Lots of lots of great information to, to supplement the presentations today. And finally, you can set the language and the closed captioning in the lower right hand part of your screen. If you need those functions, there are multiple languages available. As always, you'll get more than amazing content today as we're also giving away Amazon gift cards. Now as a reminder, you must be in attendance during the live event to qualify for the prizes, and all winners must meet the actual tech media prize terms and conditions. You can find them in the docs section at the bottom. And now that I'm talking about prizes, I do wanna just use the react button so you can see down at the bottom, you've got the ability to, to send emojis up the screen. So, have have some fun with that. Alright. Thank you all. Alright. Well, with that, let's get to the main event. So we're gonna start off today with an, an overview of solutions and tools that use AI to get more from your existing data. And we're getting that keynote from IT and tech content host and contributor, Keith Ward. If you've, attended a lot of ATM, EcoCash, and MegaCast, you know that Keith is normally the moderator. Today, we're switching roles, and and he's doing the, the the keynote. So, no escape from Keith. Keith, over to you. Video Hey. Thanks. I am so excited to be here with you all today on the eco cast. This is gonna be a little bit technical, but I'm sure you can, stay with me here. So let's get going. Now to understand where AI fits, consider the composition of your current digital asset… Assets. Structured data inside your relational databases is only the tip of the iceberg. Roughly 80% of what most organizations produce is unstructured or semi structured. It lives in places like incident tickets, network packet captures, chat logs, vendor contracts, architecture diagrams, system configurations, you get the idea. Now traditionally, querying this information meant building regex scripts, maintaining specialized schemas, or relying on manual triage from your senior engineers who surely have better things to do. When your data is locked behind siloed systems and inflexible access patterns, your infrastructure costs go up, but your actionable intelligence stays flat. Your teams spend hours hunting down root causes or duplicating effort simply because finding the right context across your environment takes too long. The goal with AI is not to replace your database engines or throw away your schema models. It's about applying semantic research, retrieval, and synthesis across the entire footprint you already own. Where does AI deliver immediate ROI on your current data investments? Well, three primary areas stand out for IT teams. First is semantic search and synthesis. Traditional searches look for exact keyword matches. If an engineer searches an incident record for a connection time out, for example, they might miss a critical post mortem that use the phrase socket exhaustion. Now semantic indexing and vector embeddings understand technical intent, so your engineers can query your entire operational history in plain language and get back synthesized accurate answers in seconds. Sound good? Yeah. Second is intelligent telemetry and AI ops. Your monitoring stacks generate millions of event logs every day. And the reality is that we humans simply can't parse that volume effectively. And basic static alerting generates nothing but noise and alert fatigue. These are the enemies of the efficiency you're trying to create. AI models trained on your baseline telemetry can correlate anomalies across network, compute, and application layers, pinpointing root causes before an incident triggers a cascading outage. Third is automated knowledge retrieval. So, consider this question. How many repetitive tickets flow through your internal service desks? By connecting language models to your existing internal knowledge base and resolve ticket repositories, you enable intelligent self-service that revolves… Resolves… Sorry. That resolves recurring technical inquiries directly at tier one. And I said, I I said revolves accidentally, but it is kind of like a revolving door. So that's definitely something that will help you a lot to get rid of. Alright. From an architectural standpoint, the biggest hesitation for many is data gravity and governance. You cannot easily move hundreds of terabytes into a public cloud or expose sensitive intellectual property to third party model providers. What you need to do is bring the intelligence to your data, not your data to the intelligence. Using retrieval augmented generation or RAG, your your proprietary information never becomes public training data. Instead, what happens is that your internal systems ingest documents and logs, generate vector representations locally or in your private cloud, and retrieve only the relevant snippets when an authenticated query is made. In other words, keeping it all safe. You maintain your existing storage tiers, your object stores, and your database clusters. The AI acts as an intelligent inference layer sitting on top of your existing API endpoints. This approach keeps compute requirements predictable, minimizes your integration overhead, and allows you to run modern, quantized, open weight models directly within your own private boundaries, which again is exactly where you want them. But now, an AI system is only as secure as the data policies governing it. This is an important thing to understand. If an employee queries a system, they should only receive answers derived from data they have explicit permissions to see. So when architecting these layers, you enforce access controls at the retrieval boundary. Identity management, active directory groups, and role based access control must map directly into your vector pipelines. Every query, retrieved chunk, and generated output must be logged for compliance and observability. So you need full visibility into data lineage. Which document informed an answer? Which user executed the query? And what security context was active? By treating the AI interface with the same zero trust mindset you apply to any other core IT service, you are… Have implemented zero trust mindset. Right? By doing that, you satisfy your compliance and legal teams while still empowering your workforce to safely extract insights from proprietary systems. So to turn all this into a reality within your organization, you need to take a focused iterative approach. Start by identifying one or two high friction repositories. Right? Dip your toe into that pool. This could be your resolve ticket logs, your internal technical runbooks, or your change management history, for example. Now these hold dense, highly valuable operational context that can be really difficult to navigate today. Next, stand up a contained private proof of concept using retrieval augmented generation, remember, RAG, within your own perimeter. In that POC, measure real operational metrics like reduction in mean time to resolution, deflection of internal support queries, and faster engineering onboarding. So think about it this way. You've already made the capital and operational investments, right, to collect, store, and secure your data, and they are quite likely very significant. So now is the time to activate it. By deploying targeted AI on top of your current architecture, you transform passive data storage in… Doing nothing at all for you into a strategic operational advantage for your entire business. You're gonna hear a lot more about these things on the EcoCash today, so it is high time to stop listening to me drone on and get to those presentations. Back to you. Scott Bekker Sorry about that. I muted myself. Thanks for that awesome keynote, Keith. Lot of great technical detail in there. That was that was fantastic. Alright. Now before we get to our our first session of the day, we do have a quick poll question for you. So let me open that up, and that'll appear there up in your, in in in the upper right kinda next to next to chat, between chat and docs. You should see a poll tab there. And the question we've got for you is what's your time frame for adding new or updating existing IT solutions at your company? Of course, we're talking about, you know, mostly the kind of solutions that we're that we're, exploring today, And, you know, the options for time frames are under six months, six to twelve months, twelve to twenty four months. And then beyond that, kinda not sure. So just giving you all a little time to to vote on that. And let me go ahead and put that up on the screen so you can you can kinda see where where everybody's at on this, on this question. So, the poll's still open. Keep those votes coming. But right now, it looks like six to twelve months is kinda one of the… Is is sort of the the leader on the field here, and, not sure is second, but six to twelve months is, like, in the the 35% range. O to six months, is is, like, around 28%. Twelve to twenty four months looks like around 14%, and not sure is is around a quarter of you. So, great. Thanks everybody who's voted already. I'm gonna I'm gonna stop sharing this poll on the screen, but, we'll just leave it open there, to the right. So if you didn't get a chance to vote yet, we'd still love to we'd still love to, to to see what you, what you what you think about that where you are sort of in your journey. Okay. And, so now it is time for our first presentation in the EcoCash. And this session is gonna come from Automox, and, presenting for Automox is Landon Miles, who's senior technical marketing and applied AI manager. So I'm gonna turn things over to, Landon to get us started. Video Joining our webinar today. I'm Landon Miles, and I'm the senior manager for technical marketing and applied AI here at Automox. Now at Automox, every year, we put together and commission a report called the state of endpoint management report. And for the 2027 edition, we surveyed a 150 IT leaders at companies anywhere from 600 to just under 10,000 employees, and we asked them how they patched and how they… How much they've automated and how well it's actually working. And one answer stuck with me more than any other one and… Which was not one of those 150 organizations could deploy an emergency patch within hours. That matters because at this point, attackers are using AI to find and exploit vulnerabilities faster than ever. And meanwhile, many of the responses are still moving at human speed, so tickets, chained windows, and someone reading advisory and writing a script by hand. So for the next twenty minutes, I wanna talk about how to close that gap. So here's how we'll spend that time. I'll start with a few findings from the report, and then we'll walk through three steps. The first is visibility. The second is deciding what to automate, including the things you can't patch yet. The third is governance, which I know sounds like it's really boring, but that's actually where a lot of the speed games come from. So… And since this is an Automox webinar, I'll also show you a couple things that we've built along the way, but I'll keep that part short. We're gonna be focusing on what a lot of the things you can do are. So let's get into the research. The headline is right there on the slide. Automation is everywhere, but the outcomes haven't been able to keep pace. What gets me every year is the gap between how automated teams think they are and what they actually can do. The report calls that gap operational debt. So teams rate their endpoint operations as more mature than they are than their results can prove, and the difference between that is what we call operational debt. The reasons are probably the ones you'd guess, so too many tools, slow patching, automations, and automations that never really turn into repeatable workflows. One of the things in this is the automation paradox that we like to call that. So, most field teams feel automated and mature, but it still takes them a whole quarter to make something new part of the routine. A team can be busy, well equipped, and highly automated and still not necessarily be fast. And what really matters is whether the automation gets the outcome you want every time. So when we look at the numbers, 81% of the people we surveyed said that their endpoint management is mostly or highly automated, and 69% described their operations as very mature. But, also, 92% said they need at least three months to turn a new capability into a repeatable workflow. Three months is is three patch Tuesdays, and the patch Tuesdays of the last three months have also each broken a a new record. So let's continue. So part of what's behind that gap is also tool sprawl. So 93% of teams use more than five tools to manage their endpoints, and more than half use over 10. I'm not one to talk here, by the way, but I keep buying tools for my garage, and it hasn't particularly made me any better at fixing things. But you know what? I really do enjoy buying tools. So the problem is that buying tools doesn't always buy outcomes. 40% of the teams we surveyed can tell whether their endpoint operations are delivering what they're supposed to. Sorry. 40% of the teams we surveyed cannot tell whether their endpoint operations are delivering what they're supposed to, and 68% said that measuring ROI makes it harder to expand automation. So if you've ever asked for a budget, you know, the first question is always what the last tool got you. And as the title says that more tools haven't changed patch times, and most teams still take five to fourteen days to patch. And, remember, not one could push that emergency patch within hours. So that isn't just an IT metric anymore. It's a business risk. Some teams are being told by their board to patch or mitigate high risk vulnerabilities within three days, and Sysa keeps tightening its timelines for federal agencies also. While that is just federal agencies at this time, the rest of the industry does tend to end up following that also. Attackers have AI too. Copy fail is a Linux bug from the spring that you may remember and could get you root on every major distro back to 2017, and AI platform found it in about an hour of scan time. And attackers aren't just gonna wait fourteen days… Five to fourteen days at all. And, I mean, even with a lot of the the latest bugs coming out too at the end of October with PHP and the the email address certs and just all of that stuff. It's… The timeline to attack is… Well, the timeline to finding the vulnerability is slowing… Is increasing significantly. And, I mean, luckily, some of those we're not seeing a lot of attacks on, but it's still, I mean, it's still something that you don't want to have exposed. It's a very high operational and business risk. So if you've been there, you know what this looks like. One tool patches Windows, another handles third party apps, and something else covers Mac, and then someone pulls it into a spreadsheet to start figuring out where things stand. So try following a single vulnerability through that, and it's not something that is particularly efficient or fun. So security finds it, hands it to IT. IT hands it to whichever tool covers that OS or app, and someone opens a ticket, and somebody else has to go check that it's done. If if people are the glue holding your tools together, you've automated tasks, but you haven't automated your workflows really. And every tool needs its own maintenance and someone who knows it, so you get a lot more activity without getting any faster. So getting tools set up is its own problem, and I always like to use the example. So I've I've got, I don't particularly enjoy mowing the lawn, and I've got a nine year old son and and a perfectly good lawnmower. But right now, it's a a lot more work to get him set up to mow the lawn than it is to just do it myself, and tools are all the same way. Once they're set up, they save you a ton of time, but getting there can be can be painful. And the person who sets it up all… Sets it all up, if they move on, and then you start over. So one… That's one of the reasons we built Automox turnkey results. Also, it's software that we run on your behalf. So when you're onboarding two Automox, you can start with our best practices and… From day one. So it's software. It's not consulting. It's a… It's more of a support tier, but it takes what we've learned from 1,600,000,000 policy runs and builds out a blueprint for your environment, where you are today, where you want to be, and where you want to get there. It starts with about a twenty minute conversation, and, we can help you build out kind of what exactly you're wanting for your environment based on your environment, what we have seen. And then, one of the crucial things about it is that it's not just a one time thing. We'll have monthly meetings with your team afterwards. We can deploy it we'll deploy it for you. And, so after those monthly meetings, we'll continue validating, watching for Drift, and helping you fix when when your goals change also. So tools, again, are only part of it, though. Even where our tasks are automated, the work can still stall. So nearly every team in our survey automates core patching and software deployment, but, looking at the split on this side, 91% treat automation as a tool they use here and there, and only 9% treat it as the foundation of how they run things. So I hear a version of this all the time. Patch Tuesday might have been record breaking, but it's still one patch Tuesday and the patches deploy themselves. Right? The the deployment, right, but figuring out which endpoints are affected is oftentimes still manual. And so is prioritizing and handling exceptions and checking that the fix actually worked. There's a lot of times a gap between what we think happened and and what actually happened. The report refers to this as the automation plateau. So, last line on this one, ownership depends on specific people. Only 13% of teams we surveyed describe their endpoint automations as very distributed. So in most teams, it's one or two people that hold the knowledge that keeps everything running. And a lot of times, we want to make sure that's distributed so that we're not burning people out, we're not relying on one person if they're out sick or if they're on vacation for a week during a zero day. So when we take a look at this to get past the automation plateau, so task automation is where everybody starts, and that is the one answer, but it only answers one question, the job run or not. So a governed workflow asks whether you got the outcome. So take patching and Deploying a patch is a single action, and a patching workflow decides what has to happen and under what conditions or who owns the exceptions and how you know it'll work. So the way to build one is to start with the outcome and work backwards. So writing down the decisions you keep making by hand, for example, if a vulnerability is on CISA's kev list and it's on an Internet facing server, it probably needs to be it needs to go out in the next maintenance window absolutely. So no ticket, no meeting. If there's no patch yet, but there is a known mitigation, the mitigation goes goes out instead. So someone has to keep owning these workflows. Workflows, there's a story in the in the report about a large organization that set up a network with automated maintenance through a contractor. And after a few reorganizations, they lost track of it for for several years. And it was maintained that whole time, but only to the standard from twelve years earlier. So at the pace that things move now and automation nobody owns can turn quickly into a risk that you can't see. So how do you get there? So there's there's really the basics. The basics of IT are still the same. However, the risk of not getting the basics correct is getting larger and larger than it ever has been. So, these are the next three steps and what they're about. So step one is visibility. It sounds basic. Honestly, it is, but the fundamentals are cool again, and everyone else… And everything else depends on getting this right. So you need to be able to see every endpoint because you don't know what you don't know. Blind spots are where things go wrong, and whether that's the laptop that hasn't checked in for a month or the server that no one owns anymore or the patch that failed without anyone noticing. Seeing everything comes with its own problems, though. Notification fatigue. If every alert is a red alert, which one do you work on first? If everything's an emergency, nothing is. So tune your alerts, tune your notifications, and if an alert never lands, never leads to anyone doing anything, turn that alert off. Then set a baseline. IT and cybersecurity is the the act of discovering what your baseline is and looking for things that are outside of that baseline, deciding what's in scope, what looks good, and which systems matter most. So when something new drops, when a new vulnerability asks three questions. So is there a patch? Is there a proof of concept for the vulnerability exploit? Is it being actively exploited? If it's actively exploited Internet facing in in your software stack, it goes to the top of that list pretty quickly. Then if it's deep inside your network with no easy way in, you've got a little bit of breathing room. It still gets patched. Just… It's not on fire. So… And, also, remember that a CVSS score measures technical severity, not business risk. So a 9.8 CVSS score on a text box with no route to anything is going to be a lot less urgent than a 7.5 on a public facing app that's tied to revenue. The last box on the slide is payoff. Once you see everything, your reporting starts to be… Starts, stops being guesswork. So here's a simple test that that I always recommend people try. So when a new CVE drops, how long does it take for you to find out which systems are affected? If it takes more than a few clicks, that's that's your homework. And, I always joke at trade shows that there's two kinds of of reporting, the c suite kind with nice pie charts and the kind that you actually use as a practitioner. Both matter, because sometimes you have to give those nice pie charts and graphs to your executives. But, if the pie charts are all you have, your reporting isn't helping you do the work. So Automox offers both, but being able to dive into what you need to do as a practitioner really quickly is is critically important in the in the visibility area also. Okay. So step two is applying those insights into action. So once you've got visibility, that's when things start to become more fun. You can… The question becomes what you hand to automation and AI and what you keep with people. The way I think about it, people are good at judgment and owning the outcome, and computers are good at doing the same thing thousands of times without getting bored. So give each one the work it's good at. That applies to AI as well, and attackers are using AI to find vulnerabilities faster than ever. And, honestly, the only realistic way to keep up is to have AI on on your side too. We don't think autonomous agent should ever directly control patching without a human in the middle, but where an agent really helps is turning what you ask for in plain English into a policy that you can review. It comes back and says, here's the patching policy. It can help you find the gaps. At Automox, we have an MCP server that is great at doing this. You can connect it through your existing controls and, ask kind of just any basic question or build out policies with the two or just… One thing I like using AI for is finding the spots that I don't know are blind spots and just having it review your configuration, having it review your policies, and looking for things that are slipping through, and then tweaking it, checking it, owning it, and making sure that it's working in the way that you want it to, and then you approve it. And then from then on, that policy runs the same way each time. So why automate it all? And there are really three big reasons for it on this slide. And the first is time savings because repetitive work stops landing on a person. The second is compliance. A policy leaves a record every time it runs. So when an auditor asks whether every server got the patch, you pull a report and say, we're good to go. But, also, if there's a lot of fines in this too and there's not a lot of room for error with compliance either, automation helps a lot with that. The third is consistency. 72 of the organizations we surveyed manage more than 3,000 endpoints, and you're not going to get the same result on 3,000 machines if you're if you're doing it by hand. And one customer told us their IT manager went from thirty hours a week on patching, to to about an hour, which is a pretty big drop, and we love to see that with our customers also. So where should you start? It's always a hard place. It's like, okay. I need automation. I need to implement this. Like, where do I start? There's so many problems at hand. So, you don't need to automate everything, and I like using the… Personally, I like using the I hate doing this test. So ask your team which repetitive tasks waste the most time or create the most risk or that they absolutely hate doing, and, some good targets for automation will start to fall out of that. Another approach is to map one workflow from end to end starting, just example, starting the moment a CVE drops and kind of mark every spot where a person has to wait or step in. Those spots are also great candidates. Usually, that means starting, also with, excuse me. Usually, that means also starting kind of with the higher volume tasks that eat up your wheat. So patching, alert triage, and keeping your asset list currently. After that comes compliance heavy work, reporting, audit trails, those are great candidates for automation also. Anything that needs to be identical and ran hundreds of… Or thousands or more times, that's a great a great candidate for for automation. I'd also like to add one more category is the tasks that you'd only do every couple months, maybe every six months or a year. Those are the ones where you always wish you'd taken better notes or the… It's like, I do this once every six months. I forget how to do it every time. So setting up those automations and kind of that… Making sure that that is documented well also so that next time it comes up, it is just taken care of automatically, and you don't have to take the the time or cognitive load to go back and figure out how you did it last time also. Let's see. So the other thing… There's one more category I wanna spend a little time on, because it's grown a lot this year also, and that's vulnerabilities that you can't patch yet. So looking back just at this year, dirty frag is is a good example. So in May, a researcher published a working exploit code for a Linux kernel bug, that takes an unprivileged user to root on every major distribution. One of the two CVEs had no patch anywhere yet, but the mitigation, a lot of teams had already put in… Oh, I'm gonna start over again. Pause. Cut. Dirty frag is a good example of this one, I think. And so it happened in May of this year. A researcher published a working exploit for a Linux kernel bug chain that takes an unprivileged user to root on every major distribution. One of the two CVEs that were released had no patch for it yet, and the mitigation that a lot of teams had already put in place for copy failed didn't cover it. So what do you do when there's there's no patch? You close the doors until there is a patch, which is which is what mitigation means. So for dirty frag, that meant blocking the affected kernel modules until the patch landed. We shipped to worklet did did exactly that and put it on on GitHub for free for anyone, whether they're a customer or not. If they're a customer, obviously, it's just a couple of clicks in the Automox console, but, and you can get all the benefits of automation. But doing that by hand usually means that someone has to read the advisory, write a script, test it, push it, and then try to prove it ran. And that can take hours or or days. And it also happens… It's also happening a lot more that… Than it used to. So mitigation can't be the 11PM execution exception anymore. It really needs to be its own process and its own owner. So that's why in September, we launched what we're calling here at at Automox Mitigation Worklet. So, if you're new to Worklets, their automation is written in bash or PowerShell that run on Windows, Mac, and Linux endpoints. Now when a vulnerability is disclosed, we have our team, draft up a mitigation workload within hours. They're using AI to help draft it, help prove it out, and test it. Goes through validation, security checks, and human review before it ever reaches the Automox console in the worklet catalog. And then from there, it's your call. You can search the catalog by CVE number, review the worklet, and pick which endpoints get it and when. If it can't wait for the next scheduled run, we have what we call fix now or run now, which pushes it right away. You can select which endpoint you wanna run it on right away from the console, and the activity log and policy results show whether it actually ran. That takes you from disclosure to mitigation in in minutes or hours and instead of days or weeks. So step three, is where automation turns into results that you can prove, and it's where the blueprint and turnkey method that that I mentioned earlier comes in. The whole point is to decide things ahead of time so that nobody's making it up in the middle of an incident. So in the in the report, there's a quote in there that says speed is a governance problem before it's a technical one. The technology can already patch quickly, and what slows teams down is everything around it. So can you roll back? And do you know when you would roll back? Who owns the exceptions, and who decides which systems can change without an approval? If you're answering those questions in the middle of an incident, you're already too late. I think of every CVE kind of as a fire drill. You plan the exits before the alarm goes off. You improve the plan a little time… A little bit after each one. And so that means deciding upfront where automation can act right away, like low risk patches, standard configurations, and known mitigations, which… In which systems, need someone to sign off on. So, I mean, you're gonna patch your employee laptops different than you are your your production servers. So you write those decisions into into the policies within Automox. Let the policy apply them the same way every time on every endpoint and keep checking what ran matches what you agreed on. And before you let automation take on more, you need four things in place, really. So clear boundaries, predictable execution, and visibility so every automation can be automate… Every action can be automated and then a way to roll back too. That last one means knowing how you'd uninstall a patch if you need to or revert a setting before you, after you you push it. So settle who has the authority and how much risk is acceptable before the emergency, not during it. So what separates automation that looks good on paper from automation that actually gets results? A lot of it comes down to what you measure. It's easy to count how many patches went out, but that can often be a vanity metric. Plenty of tools will tell you a patch deployed. Plenty of tools will tell you that there's a problem out there. But when you can confirm that it landed on the endpoints and that it's working and patched, that's that's where you can add value. So a better question is whether your risk is actually going down, how many endpoints still have a known exploited vulnerability open, and for how many days, how many patches have been verified on the endpoint, not just sent. If those numbers improve over time, your your automation is doing its job. So plan on changing things also. So best practices change. We're in a time where best practices are changing quite frequently, and your environment's also gonna change. So what you set up six months ago is maybe not gonna be the the environment that you have today. What worked last quarter might not work now. So be willing to be proven wrong. And every time someone proves you wrong, the setup gets gets better. So that's the tour. That's what we have for today. Thank you guys so much for joining. And if you're interested in that state of endpoint… The 2027 state of endpoint management report, you can get it from automox.com or the resources section of this webinar. Mitigation worklets are in the workbook catalog on automox.com if you wanna see them. And thank you so much for spending the twenty minutes with me, and we'll see you next time. Scott Bekker Alright. Thanks, Landon. Fantastic presentation there. And a a reminder that the, the poll question is up, just about, you know, any any information that, that you'd like, additional information from, from Automox about their solution, options in their data sheet, technical white paper, customer case study, and a bunch more. You can click as many as you like, and they'll get all of those to you afterward. I'd also like to remind you all just about the the handouts each, each presenting. Each presenter has a has a handout today. Automox has a, a 2027 state of endpoint management report there. It's a nice, it's a nice it's a nice read. It's it's long enough to have some depth, but not too long to, you know, not too long. So it's like… It's a 10 pager, so you can you can dip in there and get get a lot of detail. So be sure to, take advantage of of that, resource over there. Now it looks like we had a lot of questions we can't get to right here, but, but Landon and the, the Automox team will do their best to respond to you. So, thanks thanks for, sending in those questions, and, thanks again to Landon. Great presentation, and thanks for educating us on Automox. Alright. And it is time for our next prize drawing. And, the winner of… Well, I should say… I said our our next, but it's our first. The winner of our first $300 Amazon gift card of the day is Abdul Kadir from California. So congratulations to Abdul. We'll be in touch about claiming your prize. Alright. And it is time for our next presentation in the solutions and tools that use AI to get more from your existing data, Glean. And this session comes from Glean, and presenting for Glean is, the senior solutions engineer, Justin Swadling. And let me bring Justin on stage with me here. Oops. I think I moved him off. Justin Swadling Yeah. Scott Bekker Hey, Justin. Justin Swadling Fabulous. to be here. Scott Bekker I'm glad you could make it. Alright. Let us, stop sharing the slides so you can do your, your screen share and, and take it away. And I'll just… I'll stay on stage with you here until you get your your screen share up if you'd like just so I can report Justin Swadling doesn't Scott Bekker I. see it. K? Justin Swadling But it's terrific to meet everybody. My name is Justin Swadling. I'm an engineer here at Glean. And so, we are in the business of making all the data in your business findable, searchable, usable, and it's, one of the most fun, tools I have ever used and I enjoy every day. I will pull up, just, like, two, three slides. I wanna just introduce, like, what it is we do here and why it's awesome, and then I'm gonna show you. As a part of, like, some of the data and other other, topics we're covering today, I'm gonna focus my, let me go find the magic demo button. Why can't I move this? Demo. The stage bit is… There it is. Entire screen. Share. We're off to the races. Welcome. Alright. What do we do here at Glean? As you guys have already experienced, I'm sure. Right? You're using… Maybe you have Glean. Maybe you have Claude. Maybe you have Cursor. Who knows? And you can ask cool questions to get information about data usage, things that you're measuring at work. Right? Whether it's financial or user based or whatever the situation is. How do we mix that though with the documents that are trapped in SharePoint, the discussions in teams in Slack, Google Drive, Confluence, Jira, code bases? How do we mix all this text data that's hard to search through and actually combine that with relevant, like, actual calculations and other charting and information. Well, this is my specialty. Everybody's doing all these different agents across all these different things, but the same issue on… Is underneath those. How do I find documents? How do I get pages? How do I get policies? How do I get meeting recordings and discussions with my coworkers on chat? How do how do I make those available and quick and easy so that whether I'm doing an agent in Snowflake or BQ or Claude or wherever I'm doing my dreams, I can bring that context in and have that available at all times. So we've been building this for years now. I think the company… How old's it going? Seven or eight years? It's been awesome. We build this… And we build this structure, this layer of context here in the highlighted blue where we will go out and scrape for you your SharePoint, Google Drive, Slack, Teams, meeting recordings, whatever you got, and go get all the text out for you. Actually, use machine learning to understand it, and then be able to find it and use it. So whenever you're an eight… Whether it's you asking a question or an agent asking a question or you asking Glean to make a dashboard for this, help me visualize this for my boss, we can very easily combine those queries to Snowflake and Excel and Salesforce or whatever with our detailed context and understanding of your business. This means that everything you do with AI, robots, agents is dramatically better, easier, and more fun to do every day. To show you this… And I'm gonna make sure I set a timer for myself so I don't run too long because I certainly can chat. And then I'll take a second too. I'll be able to come back, different parts and try to come back to the q and a. If you guys have questions in the chat or questions in the q and a, I can come back to you and take a look. So let's pop me out of this, and let me take you to Glean. Hello. Welcome to Glean. I'll make it bigger for everybody on the on the bit. For most people using Glean, they just have it set to whatever model is the best possible model for the task. You ask questions, help me build the spreadsheet, help me make a PowerPoint. I'm looking for this document that, you know, Clarisse sent me on Tuesday. I'm looking for something Josh was talking about, and Glean will automatically be able to find all those things regardless of the LLM or model you're using. How do we do that? We have this powerful search engine that we build for each company. This allows us to do questions like snowflake, policy. And I… And instantaneously with no LLM, there's no, like, tokens where… No tokens were used here. Glean is able to create this giant rank search that looks like a real Google search, but for your company. I'm ranking all of the data in your business, documents, messages, policies, documentation, code, anything I can get my hands on that's loaded with text, written text, and I'm creating this powerful search engine so that you can search, I can instantaneously find 18,000 records related to policy documents related to Snowflake that are in my corporate business, that are in my… At my work. Furthermore, I could do this for every single employee. So for me, these are the documents I get to look at every day. Right? These are all the things I have access to. If you were to come in for your work, whether that's recruiting or fin… You know, financial ops or sales or whatever, you know, procurement, you come in, you'll have access to all your tools right here where we are making everything super searchable. So when you ask even just a simple question, like, build me a to do list or transferring to marketing. Because, you know, I don't know. I love marketing. It's a fun role. Ads are complicated. I think it's interesting. One of the first things this is gonna do, one, the auto routing switched models for me to use the most effective model for building something beautiful, and then look what it does right here. Here it is. It pulled 30 documents across one, two, three, four, five, or six different underlying sources instantly. So instead of asking your agent or your tool, like Claude or whatever, to search Gmail, then SharePoint, then Jira, then your code base, you just… It just goes clean. Get me everything about internal transfer process and everything else about internal mobility policy. The agent just uses Glean like a Google search in your company to get all the things that you have access to to give you a great answer. And this, what the way you see it here is just in Glean.com for everybody to just… This is what most people do every day, but you can plug it into anything. Plug it into cursor. Plug it into Devon. Plug it into your custom agent building, Google ADP or Microsoft Foundry. Right? Plug it into anything you want and get this… Get yours… Get your company knowledge piped in to any tool you could need. A lot of us are experiencing this now. We're building agents internally in our business. And then on the backside, you're like, yes. But where are we gonna get the policy documents from? Where are we gonna get the financial data points from? And maybe you've even hooked it up to Snowflake already. So data's coming in from Snowflake tables and agents. That's fantastic. Still probably going to need to actually pull from real documented information. Here's a here's a real practical example I do all the time. For the tenant… For one of my customers, Support Lab, this is an internal one. This is not client. Please, plot me usage, wow, mow, and MCP usage in line. So do it in the chat, then define for me how we do those KPIs internally. Prefer definitions from, from experts. So one of the things I can do at Glean is I know… So while this is running, we'll wait for this to we'll wait for this to catch up here. Not only do I have a search engine of all the data, I know who everyone is. So I know me. I know all the different emails and user IDs behind the scenes that log me into all my systems, and I know where I am in the org chart. Like, this is in Glean. I know the org chart of the business. So that means my… The search results are extremely personalized to you, your role, the coworkers you work with, the department you're a part of, as well as just the documents that are most popular, the documents that are clicked on the most, the documents that are the most useful. It's like a powerful, legitimate, like, SEO search engine on top of the business. And that allows us to combine, in my case, querying BigQuery, which is Google's, SQL database setup, and combine that with relevant documents and information from people. In this case, it's picking through my chat and Slack and looking for information, and it's gonna be able to do everything all at once. Build the dashboard, the visualization. Tell me what it means. Prepare… Like, define what those KPIs mean inside my business because it knows who I am. It knows my coworkers. It knows who the smart people are at work that define these business metrics for me all day, all the time. This, you know, this this, how we manage this is… Makes every single person at work a butt… A ton more productive. And when we go to build cool agents that actually automate some of the stuff we don't wanna do at work, we can… We know that we're… You… While we're using Glean to pipe in the best possible information about people, documents, code, etcetera, and pulling all that stuff in alongside queries to SQL databases, queries to other agents and other systems that we may need to pull from. Since this is still designing the world's most beautiful chart, I guess, I'm gonna check… I'm gonna pop over. Sorry. It's… It feels like a million million. How does Glean know what I have access to in the q and a? So I can come back and I can talk to that. So permissions are also… We build connectors to all the different data sources like SharePoint, Teams, Google Drive, Gmail, etcetera. We build them ourself. We do that because the permission… We have to we have to intake the permissions information from every single system we connect to. We have to get not only the docs, but we also have to pull in the permissions. So when you come to Glean, we can reinforce, like, yes. This document was shared with you in SharePoint. You have access to this Confluence page or these Jira tickets or these Salesforce objects, and we're gonna be able to pull that data for you and make it super searchable. So behind the scenes, we have all the data in the business and what… We have all the document data of the business in one place so that we can understand it and make it searchable for you. So when you find it, you click on it, takes you right to SharePoint, takes you right to the SharePoint folder you have access to, takes you right to the page and code you have access to, and allows you to, hey. There we go. That's exactly what I wanted. So this is all based on information I have access to. So I have access to BigQuery, so I'm allowed to query the data at at run time in real time. And I also have access to chat messages, documents in Google Drive, etcetera that are… That have been used on the right hand side to define these KPIs and explain them to me. So I'm able to combine… And, again, this is just a very… I wanted to do a fun just in the chat thing I could screen cap for my boss, but I can also make this a full blown, like, interactive artifact or HTML to show the team and review with the team on a schedule. And all the numbers here are sourced and decided by. So how do we define these KPIs? Well, it's based on this document from Bekker about defining how we do active users. It's about how we measure these different, documentation types. You can see different internal information is being cited and defining this information for me. One of the things that's really, really fun about using this and getting to have this every day at work is, like, changing projects or ramping up into new things is effortless. When it's easy to find all the facts about a new project, find all the right smart people that already work on it, and be able to read and learn about their work right away and combine that with, like, live customer data, live advertising data, finance data, and understand how you can participate in it as fast as possible. It's a a really, really fun and, delightful setup I enjoy doing. Let me pull back. Let me, let me pull back to the q and a, make sure I don't miss anything. Should be accountable. Recommendation. Those are the old ones for the other one. Hi from Puerto Rico. It's great to hear from you. Tucson. I don't see any more immediate items we need to go over, but, we can definitely talk about this a bit more. So let me… Let's let's do a… Let's go to the next level with this by making this little chart into a full blown page. Why would I do that? Because another thing we do here at Glean is we're trying to we're trying to make AI at work work for people. So making a dashboard, sharing it with my boss, sharing it with my team, and setting it on a Friday schedule to update itself every Friday morning at 8AM is gonna save me a lot of time. A lot of of the the two big things I do with Glean whether I'm in Glean.com or I'm in Claude or Cursor or some other tool is I'm either learning something or I'm making something. And because all my documents and data are here for me or, like, findable for me and for the robots automatically, it's very easy for me to build this stuff out. In this case, it's gonna make a full blown… It'll it'll make a more permanent visualization for this that makes it trivial for me to share this with my coworkers, like, provide this as an ongoing document. I was transitioning projects recently, and I just had to make a document with… I just had Glean build me a giant document with with ludicrous amount of detail of all my experiences, my meeting notes, my handwritten notes, my chats, and everything about what I had worked on and was able to create a 10 page slide from… 10 page PowerPoint for me that I I provided to the team directly through Glean so that they could have all this detail from my personal access and my own documents and my own meeting notes and other things, you know, package it up for them so that they could transition this work. And then I'm just going to do a quick… Give myself a quick time check. I don't wanna be like, oh, perfect. We have plenty of time. The other thing we support that I wanna… That I would bring up for this is that a lot of the team members, especially those around data and other types of, like, interesting live experiences, we also build and have a variety of agents. It's very easy to deploy your own agent on Glean. It's as simple as explaining what you want and allowing Glean to make the agent for you. Things like every time a document hits a folder, please make this change. Every every Monday at 6AM, please prepare a brief for the week for the team. Every time we get a new meeting, please review the meeting notes and update this Excel sheet. It's trivial to set these agents up, and they don't require any technical expertise to do. Our intention here is to be something we can all interact with and all take advantage of by having the benefit of having all this data and and access to your stuff at work easy and not, like, ask Claude, hey, Claude. Don't forget to check my email. Don't forget to read this 50 times. Don't forget to find the right skill file. Well, that's super easy. I'm already connected, and I'm able to find everything using this powerful search engine that Glean has built to make all those other fun downstream things more easy. Let me so something we hadn't talked about that I suppose I wanna highlight is that part of what we do is with this none of them… We do not have our own model. We have… We are we are not in the model making game. We are in the context game. I am not interested. So whatever model you… Whether the team has their own privately hosted stuff or the team uses open weight models from overseas or they use just Claude or ChatGPT like everybody else does. Doesn't matter to us, and we make it really easy to route to the best possible model to be the most efficient and reduce cost for the team. So just that whether… No matter what you're using, whether you're in Glean or you're in Claude or ChatGPT or whatever, that we are making it more efficient. But the… We… By efficiently using context and the right model, we can save cost and tokens for the business. My goodness. It's making the world's most incredible, HTML for me. I'll pull a I'll pull a separate one up. I want… Let me see what I can let me see what I can grab. No. I don't want this. Creator me. As you can see, I I store all my best stuff in here. It's an endless to do. There we go. Came up right as I was… I figured it would. It was kinda running there. So now I've now I've actually created my own detailed dashboard I can share with the team and literally share it with my team or my group or anyone, same as you would do in SharePoint or Google Drive and make it easy for us all to participate in. And once I've got… Once I have everybody on my team having access, it's easy to then set a formal schedule that this can… So this could be a simple dashboard for a use case where normally it would be rather tedious to work with, you know, work with the BI team internal to our company to prepare me a specialty view just for my project. It's now easy to get the exact view that I think is valuable for my team to work on and actually develop through. And this has been just enormously fun to do at work and makes my life a ton easier given that I'm I'm I'm in a client environment where I work with clients all day and so I'm on, like, 10 projects at a time and I can barely keep my head on straight. So this being able to build these visuals and these these scheduled items for me as my weeks go on is an absolute lifesaver. You saw that I have tons of this stuff prepared all the time just to get… Just to keep my head on straight and get this job done. And with that, I'm gonna pull back and stop sharing. I'm gonna hit any q and a. You can also hit me in the chat. I don't see any open items in the chat to review right this second. And I suppose since you guys welcome from different locations, I am in here from Denver. Blue skies today, and it's been fabulous. Without any without any, without any specific q and a, I'll just assume the basics. How do you secure this? How do you make this care… How do you make this safe? You, reach out to us, and I will speak with you directly or one of our other fabulous engineers will. We have lots of different ways of meeting whatever your business's difficult requirements are. Right? Whether you wanna host our Glean system on your side, you want us to do it, we have networking requirements, proxy requirements, you name it. We're happy to take care of it. And without any other meeting, how long does it take Glean to get set up? Fabulous question. You may you may not believe me, but I… This is… It's literally like a two week process, especially if I'm hosting it. Like, if I… If you allow Glean to host it like a SaaS product, I am happy to do it in a couple weeks. All of my connectors are set up to be out of the box. The most… The longest part of the setup is just having meetings with the smart… You know, your admins and your IT folks so that I can work with them to coordinate. Right? Plugging into these… Plugging into SharePoint, plugging into Jira, plugging into whatever, right, and getting security approvals for those. Actual setup is is days. Just turning it on and then allowing us to work our way over all that data and making this incredible context layer. With that, I think we're coming to time. Obviously, it's been fabulous to be on with you guys today. Again, I'm Justin Swadling at Glean. Please feel free to reach out to any of us. Hit me up on LinkedIn, whatever it is, and we're happy to get you connected in and hopefully meet with our great team. Scott Bekker Alright. Great. Thanks a lot, Justin. Really appreciate it. Justin Swadling Happy to, Scott. Scott Bekker Alright. Okay. And, and while we're here, we do have, I do wanna remind everybody just about the, the handout section. We've got, we've got a resource from, from Glean as well. It's a it's a Glean for data analysis PDF. And, it's it's right in that sweet spot of, you know, the the the length of, you know, where you can get a lot of information without it being overwhelming. So be sure to, to check out that PDF there, and, and get that tab open. Alright. And we do have the the poll open just about additional information that you would like, from Glean that they can follow-up with. Again, it's a it's a multi select, so, you know, data sheets, pricing detail, personal demo, like, try it for yourself. And you can you can click as many there as, as you'd like. And I'll leave that that poll open here for a little bit. It is time for our next prize drawing. And, the winner of our second $300 Amazon gift card is Jackie Hagg from Michigan. So congratulations to Jackie. We will be in touch about claiming your prize. Okay. And with that, we are ready for our, next, and final presentation, in the EcoCash, believe it or not. So this session comes from Everpure. And presenting for Everpure are, Aaron Stevens, who's product market director for, AI at Everpure, and Austin Boone, who's AI solutions architect. So I'm gonna turn things over, to the team there to, to get us rolling with with that presentation. Video Alright. Before Austin starts building, let's spend just a couple minutes on why this matters. So what we see in the research, is a few different things. These stats come from our, our joint study that we did with IDC earlier this year, And there's a couple of things that that make this portion of getting data ready for AI so critical. First of all, 90% of enterprise data is unstructured, which means that when it comes to AI, if we are only giving AI structured data, then we're missing out on a a majority of the information, that we have available to feed AI and to get intelligence from. The second thing is that right now, most AI proof of concepts never reach production, which is… You know, that's what a proof of concept is for. Right? But there's a lot of investment going into AI that is never actually delivering value to the business. And a lot of that based on this, this research, the indication that we had is that a lot of that, that breakdown is from data. And, again, as anyone who's been in IT or ever tried to create an ATL process, build a database, or build an AI data pipeline today knows, it's not simple. Right? It takes, it takes a sophisticated sophisticated team of people, and these are folks who have, really high value skill sets like data engineers, data scientists, ML engineers, or ML ops developers. Right? It takes those teams months to create a… AI data pipelines today without some kind of assistance from from technology. And those folks could be building the next, AI application. Put it any better. That's fantastic. And, yeah, we we believe at Everpure that there is a better way to do this. Nvidia also, believes that, which is why they created the AI data platform reference design that this is built on top of. And, and, that's that's exactly what we're we're hoping to bring to life, for everyone listening and who, maybe is a little bit tired of of creating data pipelines. Alright. So with that, let's get to building. Justin, are you ready? I am. I am. Fantastic. This is the this is the fun part. Absolutely. Alright. Good stuff. So, what we have here is our user interface for Everpure DataStream. And just to orient everyone to the screen, what you'd see here in the middle is kinda like, a data catalog, data pipeline catalog, and what we're calling kinda like our streams catalog view, where you can see the streams, that are available here, the ones that are published, streams that are still in draft. You can see up at the top right hand corner, you can actually create a new stream. And then on the left hand side, what you can see here is there's the stream catalog. There's a built in semantic search capability that allows you to search across various streams inside of DataStream in order to test functionality. You could do the same thing with AgenTek chat. You can toggle between different, functionalities because DataStream actually does provide large language models, various versions of that that are optimized, inside of our platform based on your infrastructure. In addition to that, there's a functionality here that allows you to create users and provide fine grain access control. You can grant access. What we'll do here is we'll jump back into the streams. I've got a particular use case that I've been working, related to, legal. I've already created this stream. And once you go in here, you can see, there's a little bit of a description here. The stream was created for AI ready data supporting legal ops. You can see, that there's 590 documents there. You can see that was last updated, a day ago. You can see your owners here, who the readers are. Some of these entities could be individual people. Some of these could be, service level accounts that have access to read from this stream. And then we also give you the ability to manage users right here within the stream, and grant various levels of access. A little bit further, an individual stream is a collection of curated data sources. So, each stream is a pipeline, and what you'll see here, I I kinda show you here in real time. What you'll see here, towards the middle of the screen under data sources is I've got, four different data sources. I've got an NFS data source that's pulling in some legal documentation. I've got an s three, data source that is connecting to, an s three bucket that's been, generated for a specific type of legal data. I've got another s three bucket that we wanted to pull into this stream that's pulling in, some text files, some, some various, transcripts, etcetera, related to legal proceedings. And then, to simulate some file shares within the organization, pulling information from different products that are being developed, supporting legal ops. I've got another, NFS, ingest that I've done, into this stream. So what happens is as each one of these streams are run, there's an ingest pipeline that is designed to leverage certain rules. So, for the sake of this demo, we've got two models. We've got, a text embeddings model, and we've got, a vision language model here, that are supporting the embeddings for each one of those data sources that we configured on the previous screen. In addition to that, there's some curation rules that allow us to provide, you know, a level of, redaction or omission of certain types of data while, the index process is going on throughout the pipeline. That could be, either, based off of word count. It could be off of dirty words. In addition to that, we've got some classification capability, where we can identify different, tagging and labeling criteria for data as it's being processed throughout the pipeline. So going back to these data sources, what you'll see is each one of these data sources, becomes part of that collection. It is all, vectorized. All the embeddings are based off of the models that we've identified here in the configuration, and then all of the different curation and classification rules are applied to this data based off of our data strategy. This is really an initial, capability all within this user interface in order to provide, an orchestrated way to create, a pipeline of data that can be accessed by high level applications, whether they're agentic, systems, whether they're apps that you've built that are gonna consume this data. And then you can actually have lineage and understand exactly how and where that data is coming from. Very, very cool. So looking at this, I'm just thinking back to that that slide I had, you know, identify and discover one to two weeks, suggest two to four weeks, curate three to eight weeks, so on and so forth. What steps did you just cover in this? This was identify and discover and ingest. Is there a curation that happened here as well? Absolutely. Curation happened. And then, also, one thing we kinda, leave off is actually serving, right, and consuming, the data. I'll show you that here in a… In an application that I've built on top of DataStream that is actually gonna leverage, the large language model inside of DataStream, some of the semantic search capabilities, connecting all via API. So let's go over here. I basically built, an application as a proof of value for a customer. This application is uniquely focused on court's intelligence and, specifically traffic citations. So just to orient you to the app to kinda show for demo purposes, right here we've got, verification that we're connected to DataStream. We've got verification that we've connected to that court stream that I created a few moments ago, and that the connection to that court stream is live. If we were to go to… Go ahead. On this application, just if… You know, make sure I'm understanding, you're essentially building the… An application that can help, citizens self serve on understanding what is going on with their traffic citations. And all of that AI data pipeline that you built to power this took minutes to make. Is that right? Absolutely. Alright. So I just wanna show, the audience a few things here. So I… Obviously, we're all green here, but what you'll see in this DataStream platform connection, these are all the the standard, open API, calls going into, authentication. I've authenticated as a specific user with access to this stream. You can see here that, I'm connected to the models that are inside of DataStream right now, in our demo environment to support the the chat and conversation capability. You can also see the, the the streams API that provides the, the streams that I actually have access to. But because I'm leveraging this particular application, the stream that's, associated with this app is the court stream. And then we've got a search API that is providing semantic search capability for the app that we built. So just to jump in a little bit, let's just say I'm I'm… I've gotten a a speeding ticket. It's $35. But when I got to the clerk's office, they say I needed, $238. So what you see happening right here is the call went out to data stream over the API. Let's look at this. Went over the API. It's starting to retrieve directly from the stream. Right? So it's going back into, the index, and it's pulling this ground… These grounded answers back and providing, a rich set of insights for this user. So now they can see, leveraging the large language model and those grounded answers. Hey. Based on documentation, you have a 4.8 multiplier. Here's all the additional fees that are associated with that, and then here's the bottom line. You can also see here, we've actually been actually able to pull, via the NFS connection, an actual raw document. You can see some tags here that I wanted to pull in to just kinda show some of the power of the tagging and classification, some of the metadata that we're able to pull in. And then in addition to that, you could see a text view. This text is actually being pulled directly from the index, that was ingested from this raw PDF. So, depending on how you're building your application, you can use the organic capability within DataStream in order to optimize that experience, and then also manage the way that data are being presented back within, your customer environment. That is very cool. Alright. So, just to show you a little bit more power, if we, had a requirement to add an additional data source. Everybody loves the app. New features are are developed for the app, but it requires additional data, to be processed into the pipeline. So we can come back to this stream. We can add a data source. So let's just say, I'm just gonna create a test data source. I want it to be NFS. I'm gonna go ahead and connect to, a repository. It does not have to be, running on Everpure. This can be anywhere in your data estate that is accessible. I'm gonna go ahead and load those directories. I'm gonna select a directory. I've got an access. Right? An indicator that we've got a successful connection, and I'm gonna mount that directory. So what's happening now is it's going across the the environment, identifying, the areas that I have access to in the different mount points. I'm gonna mount a specific path. And now I see, hey. I need to add some additional information from, the DISC test database. Right? So I'm gonna select that. I can identify which types of documents I want to be included in the ingest. And then I also wanna say how often I want that to happen. This is also something that can be, tailored to your unique requirement. But right here, we've got hourly, daily, weekly. So if you have, you know, kinda batch jobs that you are used to running, you can actually synchronize DataStream for whatever other processes you have going on, externally, to DataStream in order to consume that data once it's fresh. Right? And then you can go ahead and create that data source. Once that happens, it gets queued, and then the process starts again. And now when you go to your application, you have access to that data. Is that accurate? Absolutely. As soon as the process finishes queuing, in the the pipeline is complete, you can begin to access that data directly within whatever application, or enterprise system that you are making that data available to. Okay. There's two things that are really standing out to me watching that portion and and something you said said earlier too. It's the flexibility and the interoperability. Right? So there are other solutions out there that let you do a piece of this. Right? So maybe they let you do this, but only with the data that's on their system. Right? So we we actually allow you to, to reach out to systems that aren't on Glean platform. Right? So there's that that interoperability, accessing all of the date… Potentially accessing all of the data you have. Right? You have you have the ability to bring any of the data that's in your organization in here. And then the second thing is you don't actually have to ingest into our system. Right? Or or how do I put this? You don't have to move the source data. You can take… You can you can access the source data, just bring what you need to run as part of this, but you don't actually have to copy over the source data to get started, which, again, would be a month long, you know, month long project, that would require a lot of resources. And so so this is just something you can plug into your existing system, and it will operate within within those means. For the demo portion, Justin, is there anything you wanna bring us home with? Yeah. Key takeaways, you know, the app is kinda cool. It helped support, proof of value for customers. But what I really want you to see the value of is not only does DataStream provide the ability to have an orchestrated and automated data pipeline, from ingest all the way to serving, but it provides, key features in the form of integrated large language models that are that are optimized for, search and query, concurrency, etcetera, all within the platform. So DataStream is actually providing the pipeline and an actual AI capability out of the box. And then… So, essentially, this is Everpure DataStream. Right? It's a full stack, AI data solution that turns raw data into AI ready pipelines in a matter of minutes instead of months. Justin, from from your vantage point, everything you showed us, what do you think is the most powerful capability or or the one that shows the most promise for for really helping the customers that you've worked with? I would say, the simplicity of data stream Right? Because some solutions nowadays with AI trial to… Try to boil the ocean. Right? But the challenge that will address most of the concerns that our customers have is something that does what it's supposed to do, very well. Right? It does it very well, and it helps them ensure that they're meeting all of their their data and AI governance mandates. It's providing tools and capability that ease the burden from their teams that are only getting smaller, right, and having to do more work, providing this capability that is able to be integrated into their current development pipeline and integrate with majority of the tools that they are currently using, in a very simple, way. Tim for joining us today. It was an absolute delight. I would love to have you back on. I'm sure our audience feels the same as well. Alright. Thank you, Erin. It was a pleasure. Awesome. Thank you, Austin. And to our wonderful audience, thank you so much for joining today. We really hope that you learned something, and you got some value, out of the time. If you're interested in working with Austin on a proof of concept, or one of his fellow colleagues, you can reach out to your account manager at Everpure, or or go on everpure data dot com, and, let us know what what you're working with, and we can get you in contact with, this, incredible team of field solution architects, and, and get you going, on your project. Scott Bekker Alright. Well, fantastic, presentation there from, for… So thanks to Aaron and Austin. And, Rhonda, did I… I've put up a poll question, the same as as we've been doing all through the event. This is for, you know, for getting additional information from from Everpure. This is for, you know, data sheet or technical white paper or customer case study. Again, it's a multi select, so you can you can pick out as as many things as you'd like, and, and Everpure will be following up with you on those items. And meanwhile, while we're at it, also wanna point out that in the, doc section, there's also a link for more information from Everpure, that's kind of like a, an omnibus page. It's got a lot of a lot of stuff on there. So it's a it's a great supplement to, to what you've been hearing about. So be sure to, to open that that link and, and check that out. Alright. And now it's time for our final prize drawing of the day, the winner of the the last of our $300 Amazon gift cards, and that is Matthew Margato from Connecticut. Matthew Margato. So congratulations, Matthew. We in touch about claiming your prize. And that is a wrap for this event. I really hope that you've, you've enjoyed it. I know we have, we've… Oops. I took away the the, the, the slide there. I know we've, we've really had a good time, bringing this EcoCash to you, and, I hope you hope you enjoyed it too. It's been a pleasure to be your host for today. Can't wait to see you in the next event. And, and a big shout out to our sponsors too, Automox, Glean, and Everpure. And with that, folks, we are all done. Hope you have a great rest of your day.

Please provide citations & attributions for any information you generate from this content, thank you.