Sahana Sreeram
Hi! I'm Sahana, a senior at Duke University studying computer science and statistics. I'm a former Red Hat intern and just completed my third internship with Red Hat this past August. I'm passionate about data and security as they relate to AI, and am involved with research at Duke on studying and evaluating ML model homogeneity. Excited to be a part of DevConf this year.
Session
As AI development moves toward agents that operate on real systems, data context becomes critical. Agents need to understand how data moves, recognize incorrect pipeline results, and take trusted action.
In this session, I will show how I built a data agent on Red Hat OpenShift AI using Apache Spark through the Kubeflow Spark Operator. An enriched context layer and MCP tools connect the agent to the data pipeline and its runtime.
The demo shows the agent detecting a broken Spark pipeline and using a diagnose-repair-validate loop to prepare a verified fix for human review. The goal is to show how users can build and scale their own in-house data agents on RHOAI and bring the agentic development lifecycle to enterprise data pipelines.