Automated AI-answer verification

... just one API call away!

Account overview desktop

Sample question

Is UK a democratic country?

Correct answer

Yes, UK became democracy in 1832.

AI answer

Politics in UK functions within a constitutional monarchy where executive power is delegated by legislation and social conventions to a unitary parliamentary democracy.

Score: 100%

Lorem ipsum question

Lorem ipsum dolor?

Correct answer

Yes.

AI answer

Lorem ipsum dolor sit amet, consectetur adipiscing elit.

Score: 100%

Lorem ipsum question

Sit amet?

Correct answer

Yes.

AI answer

Lorem ipsum dolor sit amet, consectetur adipiscing elit.

Score: 0%

Automated RAG assessment

We understand the challenges of manually testing RAG applications. That's why we created evalmy.ai — a tool to streamline AI answer verification, allowing you to focus on more important tasks.

Get started

Accuracy

AI validation is tricky. Small details can flip meanings (e.g., "legal" vs. "illegal"). evalmy.ai prioritizes accuracy to address this challenge.

Configurability

evalmy.ai offers out-of-the-box validation and customizable Sem-Score parameters, allowing testers to adjust context based on risk profiles.

Scalability

A cloud-based SaaS, evalmy.ai scales up or down as needed, depending on the number of models, test frequency, and question set size.

Pluggability

evalmy.ai provides a user-friendly API that seamlessly integrates into CI/CD pipelines and supports popular ML tools like LangChain.


What is C3-Score?

C3-score is a unique and balanced qualitative metric designed for evaluating AI answers. The C3-score consists of three key components:

  1. Completeness:

    No facts are missing from the AI's answer.

  2. Correctness:

    The answer contains no extra or fabricated information (no hallucinations).

  3. Contradiction:

    There is no logical inconsistency within the answers.

Try it for free

Rest API integration

Rest API Integration allows your application to communicate and share data with EvalMy.AI and makes it a powerful tool for enabling seamless data exchange and monitoring.

from evalmyai import Evaluator

data = {
    "expected": "Jane is twelve.",
    "actual": "Jane is 12 yrs, 7 mths and 3 days old."
} 

evaluator = Evaluator(auth, token) 

result = evaluator.evaluate(data)
                

Tutorial

Explore our extensive tutorials and documentation on GitHub. Whether you're a beginner embarking on your first coding journey or an experienced developer seeking advanced techniques, our resources will assist you in achieving your goals.

See tutorial

Technical support

Experience seamless support with our dedicated technical customer service team. Whether you're a developer in need of guidance or encountering a technical challenge, we're here to help. We're just one call or email away!


Pricing

EvalMy.AI operates on a convenient pay‑as‑you‑go basis – $5 per million GPT tokens.

Begin with our Starter pack, which includes 1 million free tokens. You can easily recharge your balance anytime through your account.

Starter pack

2 million tokens

5 USD

Get started with Starter pack

Recharge pack

1 million tokens

5 USD

Get started with Recharge pack