Confident AI: Open-Source Evaluation Infrastructure For LLMs

0
823
ai

NAME OF STARTUP: Confident AI

FOUNDED IN (Year): 2023

FOUNDER’S NAME: Jeffrey Ip

THE IDEA: What is the problem being solved by your startup / business?:

We save AI engineers time by helping them detect breaking changes in their LLM applications. This means faster time to production, and the ability to iterate faster by pinpointing underperforming areas in production.

THE FOUNDER’S STORY: When and how did you come up with the idea for the business?:

Jeffrey Ip, ex-Googler built large-scale infrastructure for YouTube and ex-Microsoft engineer that built AI recommenders for Office365.

WHO IS THE CUSTOMER: What is the typical profile of your target customer? Where would they be located?:

AI engineers (user persona), or Heads of AI (buyer persona)

FEATURES TO SHARE: What 3 key features from your startup journey you’d like to share with AI entrepreneurs?:

Confident AI offers an open-source package called DeepEval that enables engineers to evaluate or “unit test” their LLM applications’ outputs.

Confident AI is our commercial offering and it allows you to log and share evaluation results within your org, centralize your datasets used for evaluation, debug unsatisfactory evaluation results, and run evaluations in production throughout the lifetime of your LLM application. We offer 10+ default metrics for engineers to plug and use.

HQ City: San Francisco

Website URL: https://confident-ai.com/

Number of Employees: 1-5