Event Recap

On October 23, CADS hosted Agentic AI in Action: From Idea to Production, a hands-on workshop led by Naveen Ramakrishna, Senior Principal Software Engineer at Dell Technologies.

The session was built around one idea: autonomy is a budget. Use an AI model where the work needs language or judgment, use code where there is a correct answer, and require a human wherever something becomes official.

Working in a shared notebook, participants engineered a “DataCard agent” that documents research datasets. Over five labs they:

  • decided when a problem needs an agent, a workflow or a simple script, and watched a small agent choose its own steps;
  • compared AI models on quality, speed and cost, and saw that output can pass every format check and still be wrong;
  • built rule-based evaluation with a capped AI judge and a bounded fix loop;
  • ran a batch under real rate limits, timeouts and failures, and diagnosed them from a trace;
  • carried out a prompt-injection attack hidden inside the data, then defended against it with layered guardrails and a human approval step.

The slides and notebook are available below.

stock image
Friday, October 23 | 11-12:30PM | ALK 440

Agentic AI in Action: From Idea to Production

A Hands-on Technical Workshop on Production Agentic AI

Building an agent is easy. Deciding whether you need one, designing it to be trusted, and running it at enterprise scale is where most efforts succeed or stall. 

Led by Naveen Ramakrishna, Senior Principal Software Engineer at Dell Technologies, this workshop walks through how production agentic systems are decided on, architected, deployed, governed and evolved; the engineering strategy and trade-offs behind real systems, not a tool demo.

Key Learning Objectives

  • Agent vs. Workflow vs. Script
  • Architecting Agents for Scale
  • Model Choice, Cost & Evaluation
  • Trust, Guardrails & Human Oversight