Sourav Nandy's profile on Product Hunt

About

Sourav Nandy is an entrepreneurial technology leader with 25+ years of experience in software engineering and product management. He builds enterprise-grade software driving measurable outcomes for Fortune 100 companies. Bridging corporate scale with startup agility, Sourav has spearheaded multiple ventures alongside U.S. co-founders and researchers. His portfolio includes an education startup ($100K raised) and an IoT hydroponics platform ($50K funded). An inventor with multiple U.S. patents, he actively contributes to the global AI community with work featured in ICML, DZone, HackerNoon, and Swiss Cognitive. Sourav holds an M.S. in Technology Commercialization and a postgraduate degree in AI/ML from UT Austin, alongside a B.Eng. in Computer Science.

Badges

Veteran

Gone streaking

Gone streaking 5

Maker History

Agent-EvalStatistical regression testing for LLM agents
Aug 2026

🎉

Joined Product HuntOctober 9th, 2019

Forums

p/agent-eval-measure-llm-drift

•

1d ago

agent-eval: Statistical regression testing for LLM agents

Hi Everyone!

@rudrendu_paul_ai and I are officially soft-launching a new OSS solution, agent-eval, today.

•

1d ago

agent-eval: Statistical regression testing for LLM agents

Hi Everyone!

@rudrendu_paul_ai and I are officially soft-launching a new OSS solution, agent-eval, today.

•

5h ago

Agent-Eval - Statistical regression testing for LLM agents

Statistical regression testing for LLM agents. Run versions A and B 50 times to get a p-value, Cohen's d, and a 95% CI proving whether behavior actually shifted. While DeepEval, Braintrust, and Promptfoo test single responses against a threshold, none measure distribution drift. It is completely self-hostable under an Apache 2.0 license and requires no SaaS subscriptions. Works natively with LangGraph, OpenAI Agents SDK, CrewAI, and LangChain LCEL. Start testing: `pip install agent-regress-cli`.