Kashikoi

Simulation Engine for Benchmarking AI Products

Y CombinatorSpring 2025ActiveB2BDeveloper ToolsGenerative AIMachine LearningAI

What they do

Problem

AI teams lack a reliable, scalable way to benchmark and deeply assess the real-world behavior of AI agents before deployment.

Solution

Kashikoi provides a CPU-friendly simulation engine that generates world models to autonomously interview AI agents and produce deep behavioral benchmarking assessments.

Who it's for

Developers and enterprise AI product teams building and deploying AI agents.

Founders

Aaksha Meghawat

Founder

Founder, Kashikoi. Aaksha led the Simulation & Evaluation stack at Moveworks(ServiceNow) shipping 250+ customized enterprise ready agents to Fortune 500 and federal agencies. Aaksha has done award winning NSF sponsored research in Transformers at CMU (long before OpenAI made them cool). She shipped edge speech recognition models on 1bn+ iPhones (for the most esoteric dialects you can think of) at Apple. The innovation behind this was nominated for a Best Paper at Interspeech 2021.

LinkedIn · X