A place for AI forward engineers and leaders
Watch sessions on building AI agents grounded in your governed data.
Watch now
Snowflake and Domo Agents: One Governed Answer | Domo BUILD 2026
Try Domo for yourself.
Free Trial
Video transcript
Mayur: So I have this Snowflake agent over here, which is essentially working off a set of clinical studies. These are all clinical studies that exist in Snowflake, and I have built an agent on top of it. Now, if I ask this agent any question, I do get a response, right? For example: "How many studies are in Phase Two?" Let's see
It returns the number of studies which are in Phase Two. This is good. But what if I want the same response when I query it from Domo using the same user persona? I have the role set as a Domo role, and I have this clinical agent in Snowflake. Whenever I use this agent, I want to ask: "How many studies are in Phase Two?" I want this agent to offload the task to the Snowflake agent. As you can see, it is delegating the operation to the Snowflake agent we have defined in Snowflake. This is our Snowflake agent doing the work. While it is returning the result, you can check the query that Snowflake ran to get the result; the query is available here. Now, let's go back to Domo and see if we have the same results.
As you can see, we have the same thirteen studies currently in Phase Two. The answer is consistent whether I query it from Snowflake or whether I execute it from Domo. That's the sort of consistency I am looking for
Speakers
Mayur Mahadeshwar
Partner Sales Engineer, Snowflake
Mayur Mahadeshwar
Snowflake
Partner Sales Engineer, Snowflake
Mayur Mahadeshwar is a Partner Engineer at Snowflake with more than a decade of experience helping enterprises modernize their use of data and AI. His career spans SAS, Pivotal, Confluent, and Snowflake, giving him a front-row view into the evolution of data science, cloud platforms, and now agentic AI. He works with customers on how to design practical AI systems by combining the right data foundations, platforms, and tools across their ecosystem. A proud Aggie with a Master’s degree from Texas A&M University, Mayur also holds a Bachelor’s degree in Computer Science.
Ask a Snowflake agent how many clinical studies are in phase two, and it returns 13. Ask the same question in Domo, and the answer holds: 13.
In this mini demo from Domo BUILD 2026, watch a Domo agent delegate the query to a Snowflake agent built on clinical studies data, run the work, and hand back a consistent answer, with the same role and user persona carried across both platforms. You can inspect the exact SQL the Snowflake agent ran, so the result is one you can trust and verify. This is agent delegation and interoperability in action, where governance follows the data through every AI agent instead of breaking between systems. It's built for data professionals, BI and analytics leaders, and IT teams evaluating governed AI agents on real data.
Domo transforms the way these companies manage business.
