DEV Community

Rudrendu Paul profile picture

Rudrendu Paul

AI/ML Builder | Agentic AI | Fortune 50 Scale | Multi-LLM Orchestration | Causal Inference | Published Researcher (ICML 2026) | OSS: Hugging Face, Scikit-learn, Anthropic Cookbook, Google ADK

Location San Francisco, CA Joined Joined on  Personal website https://www.linkedin.com/in/rudrendupaul/ github website
Threshold testing is blind to agent regression; we built the statistical alternative, validated against 29 PRs

Threshold testing is blind to agent regression; we built the statistical alternative, validated against 29 PRs

Comments
15 min read

Want to connect with Rudrendu Paul?

Create an account to connect with Rudrendu Paul. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
How We Built a Way to Replay AI Agent Failures Without Paying to Reproduce Them

How We Built a Way to Replay AI Agent Failures Without Paying to Reproduce Them

Comments
16 min read
Giving an AI Agent a Benchmark Tool It Can Install and Actually Trust

Giving an AI Agent a Benchmark Tool It Can Install and Actually Trust

Comments
16 min read
Would Your AI Benchmark Survive Being Audited Like the Vendors It Judges? Ours Didn't, at First

Would Your AI Benchmark Survive Being Audited Like the Vendors It Judges? Ours Didn't, at First

Comments
16 min read
How to Check If AI Systems Can Find and Cite Your Site (in 5 Minutes)

How to Check If AI Systems Can Find and Cite Your Site (in 5 Minutes)

Comments 2
5 min read
loading...