Praneeth Paikray

Praneeth Paikray

Solutions Architect - AI

About

Praneeth Paikray is a AI Solutions Architect at Databricks and an AI practitioner with 9 years of experience building applied Data Science & AI systems across financial services, enterprise technology, and workforce solutions. He is interested in practical AI systems that can be deployed in the real world, from generative AI workflows to agentic architectures and optimization techniques.

Improving AI systems is still a largely manual process. Teams review bad outputs, adjust instructions, test a few examples, and repeat. That process is slow, hard to scale, and often fragile in real enterprise workflows, where errors vary across steps and small changes can create new failures elsewhere.
 
In this session, we will build a practical enterprise AI workflow and show how it can improve from failure using GEPA. Rather than treating optimization as prompt trial and error, we will use execution traces and textual feedback to refine the system in a more structured way. The session will walk through the baseline workflow, common failure modes, feedback design, and the optimization loop that helps the system perform better over time.
 
This is a session about building better improvement loops, not just better prompts. Attendees will leave with a practical understanding of where GEPA fits, how to evaluate progress, and how to apply this pattern to real enterprise tasks without the overhead of reinforcement learning.
Read More →
View All Speakers

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details