--- title: "Context Engineering Studio Demo" url: "https://atlan.com/context-engineering-studio-demo/" description: "Watch a product demo of Atlan's Context Engineering Studio, and see how enterprises build AI agents that are ready to ship." --- > Atlan is hosting Context Conference, bringing together the leaders and builders at the frontier of giving AI the context it needs to understand their business. It runs online on October 28, 2026, from 11:00 AM to 2:00 PM ET. Atlan co-founder Prukalpa Sankar opens and closes the day. Leaders from AstraZeneca, BNY and Verizon share why they invest in context and what they get from it. Registrants get early access to The AI Context Gap, a new study from MIT Technology Review Insights. Register: https://atlan.com/context-conference/ # See how an AI agent is built from scratch with context Demos / On demand / Recorded May 1, 2026 / 19:06 / 8 chapters Watch: https://atlan.com/context-engineering-studio-demo/ Anirudh Agarwal builds a contact center agent in Cursor from Atlan's context, then versions, simulates and observes it in Context Engineering Studio. Elastic's Jessie Buelteman on shipping semantic models. ## What you'll see ### 01 / An agent built from the context you already have Watch 0:00-4:50: https://atlan.com/context-engineering-studio-demo/?t=0 In Cursor, with Atlan's MCP server and Claude Managed Agents, one prompt builds Maya, a contact center agent: Atlan finds the right tables, SOPs and business concepts, writes her skills and semantic models, and deploys her. Side by side, Maya on Atlan's context gets the child's name, the refund and the tone right where the raw-table agent misses. ### 02 / Context Engineering Studio: repos, simulations, observability Watch 4:50-9:15: https://atlan.com/context-engineering-studio-demo/?t=290 The same build inside Atlan, as a context repository holding semantic models, skills and a SOUL.md file. Simulations run mock calls before launch, the context moves to Snowflake Cortex Analyst or Databricks Unity Catalog, and observability flags patterns in agent traces, such as a wrong customer tier, to fix in the context. ### 03 / How Elastic builds talk-to-your-data for finance Watch 10:16-19:06: https://atlan.com/context-engineering-studio-demo/?t=616 Jessie tells Prukalpa why Elastic starts in the data layer: build semantic models from all the context, validate accuracy before shipping, govern them through the same GitHub and dbt review as SQL, and keep them refreshed. His goal for every team and tool is the same answer. ## Speakers - Anirudh Agarwal, Staff Engineer, Atlan (host) - Varun Banka, Co-Founder, Atlan - Prukalpa Sankar, Co-Founder, Atlan - Jessie Buelteman, Senior Manager, Enterprise Data Governance, Elastic ## Chapters 1. [0:00 Building an Agent in Cursor](https://atlan.com/context-engineering-studio-demo/?t=0) 2. [3:38 How Context Improves AI](https://atlan.com/context-engineering-studio-demo/?t=218) 3. [4:50 Context Repositories](https://atlan.com/context-engineering-studio-demo/?t=290) 4. [6:26 Simulations & Testing](https://atlan.com/context-engineering-studio-demo/?t=386) 5. [7:04 Portability](https://atlan.com/context-engineering-studio-demo/?t=424) 6. [7:47 Observability](https://atlan.com/context-engineering-studio-demo/?t=467) 7. [9:15 Recap](https://atlan.com/context-engineering-studio-demo/?t=555) 8. [10:16 Customer Story: Elastic](https://atlan.com/context-engineering-studio-demo/?t=616) ## Related videos - [Context Agents demo](https://atlan.com/context-agents-demo/) (13 min) - [The context layer, live (product demos)](https://atlan.com/context-layer-demo/) (62 min) - [Bootstrap, test, ship: versioning context like code](https://atlan.com/know/enterprise-context-layer/videos/versioning-context-like-code/) (5 min) - [The missing infrastructure for production agents](https://atlan.com/know/the-missing-infrastructure-for-production-agents/) (21 min) ## Transcript ### 0:00 Building an Agent in Cursor **Anirudh Agarwal** [0:00] So what we're gonna do today as the first part of this demo is actually show you how you can leverage the Atlan context layer to build an agent in an IDE like Cursor. So let me share my screen. So what you see here is my Cursor workspace. In my Cursor workspace, we basically, I have integrated two MCP servers. The first MCP server is Atlan's MCP server, and the second MCP server is the agent framework that I'm using here, which is Claude Managed Agents. Now, all I need to do is paste in the prompt that I want to build. [0:33] Now, what immediately starts happening is that because of all your enterprise context that lives in Atlan, all of that can be leveraged to now build this contact center agent that we are building called Maya. It understands and it knows that it needs to go and look at all of our tables. It helps you search for that. It helps you search for all of your knowledge files, which are all your SOPs. It teaches the agent what to do and in what situation. It also can build all of your skills. Think of skills as mental models or capabilities that you need your agent to have to be able to do any operation. [1:07] It builds things like semantic models. So sem-semantic models are essentially files that allow your agent to understand your database. It allows your agent to understand your tables. It does simulations. It runs an evaluation to identify how good the context that you're building for your agent is. And then finally, it builds a soul file, which gives your agent an identity, and then it also goes ahead and deploys it to your agent framework. Now what's happening here is that we're now searching through all of the different assets. It's found something like Customer 360, which could be super useful for a customer support use case. [1:43] It found something called contact center interactions, that it can historically go back and look at all of the different interactions that that user might have had, had had with that customer support agent. It also found all of our business concepts. It understood things like service reliability. It understood things like carrier interaction. All of that automatically gets bootstrapped and leveraged, making my life as a builder really, really easy. Let me show you what I did backstage right before the de-demo, is actually build an agent completely through it. So as you can see, what we are doing, what the agent is automatically doing is that it's finding all of our business concepts. [2:22] It's finding all of our SOPs that we've defined and stored in Atlan. Atlan, also, what it's doing is it's actually generating us all of the skill files that we need. So think about skill files such as the voice and tone of the agent. How do we route escalations? How do we manage refunds? All of them get automatically created from the context that we have in Atlan, as well as all of our semantic models also automatically get defined and created. And what this leads to is a completely deployed agent. So let's show you what the deployed agent actually looks like. [2:55] What we've used here is Claude Managed Agents to actually do the deployment, but you can also use any other agent framework, whether it's Google's ADK, whether it's LangGraph. You can easily build on top of them through all of these different tools that Atlan has. So as you can see here, our agent has a system prompt that was generated through the context that Atlan already creates in the context layer. We created all the tools that the agent needs, as well as all the skills that the agent needs to be able to complete this operation. [3:23] Now, before we even go into our demo further, the second thing that we wanted to show was, okay, we showed you how you can actually leverage Atlan to build an agent. But what also really matters is how the quality of that agent is. ### 3:38 How Context Improves AI **Anirudh Agarwal** [3:38] So what we have here on the left is an agent that's powered primarily on the raw context, in the raw files, the raw SQL tables. And on the right, something that's powered by Atlan's context layer. So you can see what the agent's trying to do. First, whenever a question is asked, similar to, you know, my son's burger had cheese despite his da-dairy allergies and the kids' meals were missing. What the agent immediately starts doing is it starts looking at the ontology. It identifies the right tables. It also identifies the severity of what has happened, tags the right ID to it, and then uses that to trigger the right SOP and the right response to it. [4:18] So when you compare these two responses side by side, what you realize is that the Atlan's context agent actually gives much more contextual answers. The first thing, it actually got the purse - the the, the son's name right. It also found the correct amount that it needed to refund. Also, it also follows the tone of the business. For Mech Context, we want to make sure that, you know, we follow up. We we say that we wanna text you back in two weeks or in two hours, and all of that comes because this is powered by Atlan's context layer. ### 4:50 Context Repositories **Anirudh Agarwal** [4:51] Now let's jump into the product and show you a little bit about how Atlan's Context Engineering Studio works. Now, if you're, if you're someone who doesn't like using IDEs or doesn't like using CLIs, we also offer you to do the same workflow within Atlan itself. So you can define the same natural language prompt, and we can build this agent through a context repository. Now, you might be wondering, what's a context repository? Let me show you one. So a context repository is nothing... Is similar to how a, you have a GitHub repository for code. A context repository is a repository for context. [5:28] Now, what a context repository has is everything that your agent needs to be able to do its task. Like we just saw, it has all of your semantic models. It has all of your skills that you need to do an operation. It And it has something called a SOUL.md file. So let's see what a SOUL.md file is. It's what gives Maya the unique identity of a Mech Context context center agent. W-what's a skill here? We have something called a loop closing skill. [5:56] A loop closing skill is what allowed it to do the follow-up in the first place, even after the issue was resolved, because that's what's unique about our contact our contact center and how we run our customer operations. It has all of our semantic models, which allow the agent to understand which columns to query, which tables to query. Now, all of this comes into a context layer. Finally, imagine Maya when she joined a new job. She was not first put into doing all of these calls. ### 6:26 Simulations & Testing **Anirudh Agarwal** [6:26] What Atlan offers is a way to simulate. Just like Maya would go through training, she would go through mock calls with her seniors, with her managers, Atlan runs simulations of different scenarios so that you know how your agent is performing even before you deploy it to end customers. This gives builders a sense of confidence of how the agents are performing in, in a synthetic simulated environment. The reason we are able to do this so well is because Atlan has a deep contextual understanding of both your data and business graph, and all of that is leveraged to be able to create all of these scenarios for simulations. ### 7:04 Portability **Anirudh Agarwal** [7:05] One of the core beliefs that we have in Atlan is of openness, interoperability, and that's where a context repo becomes super useful. We have something called a lake house, which Varun will talk further about. We also have our Atlan MCP, which we showed you, which is compatible with with ChatGPT, with Claude, with Gemini, with any of your coding tools. Also with all of the major AI frameworks. We also can help you deploy your semantic models to things like Snowflake Cortex Analyst or to a Databricks Unity Catalog. And we're building support for you to be able to sync these files to GitHub and your S3 lo-locations as well. ### 7:47 Observability **Anirudh Agarwal** [7:46] Now, for any agent operating in the real world, the, the learning does not stop at them, you know, doing their job. It comes through daily feedback that comes through their managers, through their peers. That's why Atlan has observability. What we do in observability is that every single trace that the agent is actually performing is captured here. And once it's captured, it creates a feedback loop for you to continue to improve your context layer. What we also offer is a way for you to deep dive into the trace to understand what the agent was doing, what parts of the context layer it's touching, what tools it's using. [8:26] And for anyone debugging an agent, it can also look at and understand what the reasoning trace was. Now, looking at hundreds of thousands of traces is really, really hard. What Atlan does is that it actually watches over every single one of your traces and identifies patterns that you can easily go and fix to improve your context. [8:46] So, for example, just like Maya would have sometimes associated the wrong tier to a customer and leading to a bad refund, similarly, if your agent does the same operation, Atlan's observability identifies them and gives you a way to improve that improve the context so that it doesn't repeat, building a self-improvement flow that can help you improve the quality of your context as more interactions happen. So that was all for the demo. ### 9:15 Recap **Anirudh Agarwal** [9:15] I'll throw it back to Varun for the next bit. Thank you. **Varun Banka** [9:18] Thank you for doing this. So what Anirudh talked about was how do we use the context layer to accelerate and build trusted agents. And we realize there are people in both spectrums, right? There are people who are building these agents in GitHub repos, so they need, they need - or in their own IDs or in cloud code, they need just extensibility, portability. You brought You saw connecting to Atlan's MCP to actually drive that. So if you're a builder, you love that, you can do that. If you're someone who likes more of the cloud cowork world, you can also take in the Atlan's experience what you saw, to actually help you build those trusted agents. [9:55] Now, not only that, we help you create... Help you version this, understand how each of your context is upgrading so that you know how your skills are evolving. What was it before that? What did the agent right now talk to? So this is context. Context Studio is our IDE for both builders and both for operators. ### 10:16 Customer Story: Elastic **Varun Banka** [10:16] Now, as part of the next step, I have Jessie, who've joined us, who've been using - with Elastic, has been using similar extensibility capabilities to drive use cases at Elastic. And I'm gonna pass on to Prukalpa back to have this amazing conversation with Jessie. Jessie, welcome aboard at Activate. **Jessie Buelteman** [10:33] Thanks, Varun. Thanks, Prukalpa. **Prukalpa Sankar** [10:35] Hi, Jessie. Thank you so much for joining us today. I just wanna start by saying thank you. Context Engineering Studio was built as a labor of love, but it was honestly built because of partners like you that allowed us to experiment and work with you. These are hard problems. How do we take skills and tacit knowledge and expertise that humans have inside their organizations, and how do we, how do we actually translate it into a way that AI understands? And so really, really grateful for the partnership. Welcome to Atlan. Jessie, I had a couple of questions that I wanted to walk you through. Set the scene for us, right? [11:10] Like, tell us a little bit about the problem that you're trying to solve at Elastic. **Jessie Buelteman** [11:15] Yeah. First, thanks for having me, Prukalpa, and working with the team has been, been a great partnership as we continue to evolve and try to drive these capabilities. So appreciate the team support there. So what, what we're trying to do at Elastic is enable talk to your data use cases specifically in our finance organization. Right? Just given the nature of, of the data, the accurate - the responses need to be very accurate to, to make sure that we're able to provide good responses and not have that come back to the data teams to, to self-resolve or, or tell them why it's not accurate. So that's a key component. [11:52] And then additionally, like, reporting at Elastic is democratized across analytics teams. So any approach we build kinda has to be repeatable and extensible across the broader organization. And as we look at that, right, we, we firmly believe that we need to start in the data layer. The data layer is like the context foundation that's gonna make these raw facts really interpretable and usable by any machine without any human intuition. So we have a focused effort to get our data layer kind of up to par so we can move on and build out robust semantic models. [12:34] And that, that's just work that we're doing retroactively to get that up to speed, and then moving forward, kind of how do we... Like, we want to define those standards for what good context is, and then afford, and enforce that before promotion to production. So moving forward, right, we have that ability to, to kind of streamline our process and go build semantics without going back constantly and build out our context, context layer. So all that, you know, that, that will give us the, the foundation for the semantic layer, and then that's helpful because all that context now lives in the data layer where it belongs. So we're no longer hard coding prompts or instructions. [13:18] Those become... Are brittle, they're hard to maintain, they're siloed, so you could create the same instruction and prompt. So really we want to make sure that's available so when we build the semantic models, it, it's, it's across that level. **Prukalpa Sankar** [13:31] Got it. **Jessie Buelteman** [13:33] So as we do that, right, all that information gets there. So how do we think about creating the remas - robust semantic model, and, and what do we need to achieve that? Then it comes into we need a solution that's open and interoperable, right? Our assets, they, they live across multiple tools. We don't want to necessarily have a lock-in. So we need a solution that can kind of work with us and, and scale as technology evolves use cases pivot. And so that's kind of our approach and where we're, where we're tackling this. **Prukalpa Sankar** [14:06] Awesome. Okay. So it sounds like how do I create... How do I drive accuracy is one problem. The other is how do I make it open and portable, and how do I make sure it's, it's built for change in this world that's evolving a lot? How are you thinking about this framework internally? Like, what is... Like, what does the framework look like for building this at, at Elastic? **Jessie Buelteman** [14:30] Yeah. It's... So first context engineering, like that... I would say that's our prerequisite, so we kind of talked about that. That would be the prerequisite to go into this. And then we'd probably break it down into, like, four different phases, starting with, with build. So we want one place that takes all of this context and it's not just one dimension. It's not just dbt or you're looking at your BI assets, right? You're able to scrape all that information and have all that underlying information to build that, that semantic layer. [14:57] 'Cause we want all of it to build these robust models that you don't have to keep reiterating and, and have multiple versions to maybe answer multiple use cases. So the build part is, is really having all that underlying information, and then the validation kind of as mentioned earlier, right? That, that's critical because when we, when we want to ship something, we want to ship it with confidence and know, "Hey, when we give this to our business users, if you ask this question, there's a very good accuracy response that, that you're gonna get." And it... Or let us know, "Hey, we built this model. We ask it this question. Here's the, here's the gap. [15:37] Here's how you address it to get to that, you know, that threshold that, that you're looking for." **Prukalpa Sankar** [15:43] Mm-hmm. **Jessie Buelteman** [15:44] And then finally on the governance side when... We want... We have a very good structure in place, and we don't want to build from scratch, so... Or reinvent the wheel. We already have our GitHub and dbt structured. This has code ownership, so when we ship, we want to follow that same review approval process, that it just naturally fits in what we're doing for SQL models. We want to kind of implement the same for semantic models. And then the, the last component would be, like, the automated refresh. Obviously things change daily. New assets come in. Questions might evolve. [16:21] So how do we get that prompt or that notification or just to automatically scrape additional information that would come in to keep that semantic model fresh? **Prukalpa Sankar** [16:30] Gotcha. That makes sense. Yeah, I always like to think of this, like, context as a living compounding system. Like, underlying systems change, business changes, everything changes, and so how do you keep it alive in this, in this new world? I have one last question for you, Jessie. What does getting this right unlock at Elastic? Why does this matter? **Jessie Buelteman** [16:49] Yeah. It... Kind of just hinging on the, on some of the points above, but again, the validation, right? So it is very critical because just the users across our organization that would be leveraging this semantic model, that it is accurate. So and maybe taking that a step further, right? We'd almost want to... We ship a solid semantic model, and then you get a response. Even in that response, if, you know, prompting it to say, what, what's the, the reasoning that the that the agent went through to derive that answer? Were there any assumptions that were made? What were the data quality signals, right? [17:29] All that information's available, so I want, one, I get the response and then tell me why I should trust it. So that's really important, and, and the reason for that is it provides the users with self-serve capabilities with confidence. So it's not like, "Hey, I asked it a question," and then it comes to the data teams to validate that. So that's one component that I think will just alleviate the work on, on the data teams to constantly and provide that self-serve capability. And then on the governance following that same infrastructure, right? The, the reason that's super important, we'll be able to ship faster. [18:03] You just think from a development standpoint, we have that structure in place. We want something that kind of will, will fit into that. And we're able to ship and move things quicker and open it up for more people to use. So the more people that can use it, they already have their own review. You know, a marketing model might be different than a sales model, so the the proper people that are reviewing that code approval just follow that same infrastructure. And it just will eliminate development time and be able to ship things faster. **Prukalpa Sankar** [18:32] Okay. **Jessie Buelteman** [18:32] And the, the last component, Prukalpa, real quick, would be on the consumption side. As we build these and then we want to make that available, right? Are we able to ship that into place that's generally available for all the users, whether it's our data warehouse or GitHub, right? We have multiple personas, so any team, any tool, same answer is what we want to try to drive. And that, that's really a component to unlock this. **Prukalpa Sankar** [18:55] Got it. I think that's a mic drop moment, Jessie. Any team, any tool, same answer.