Confident AI

The LLM Eval and Observability Platform for AI Quality

Y CombinatorWinter 2025ActiveB2BEngineering, Product and DesignArtificial IntelligenceDeveloper ToolsGenerative AIOpen Source

What they do

Problem

Teams building LLM applications struggle to reliably evaluate, monitor, and safeguard model quality in production.

Solution

An LLM evaluation and observability platform that benchmarks, monitors, and applies guardrails using DeepEval-powered metrics and infrastructure.

Who it's for

Developers and AI/ML teams at companies of all sizes building and operating LLM-powered applications.

Founders

Jeffrey Ip

CEO & Cofounder

Creator of DeepEval, the open-source LLM evaluation framework. and grew it to over 400k monthly downloads and counting. Previously SWE @ Google, Microsoft.

LinkedIn · X

Kritin Vongthongsri

Co-Founder

Building the #1 LLM Evaluation Platform & empowering teams to red-team and safeguard LLM apps. AI Researcher and CHI-published author, previously built NLP pipelines for fintech startup and researched self-driving cars/HCI during @ Princeton (ORFE'24 + CS).