FAQ
What is ObjectiveAI?
ObjectiveAI is an AI platform built around our primary product, the ObjectiveAI Score Completion.
What is a Score Completion?
A Score Completion is a new way of using large language models (LLMs). Instead of asking one LLM for one answer, you provide the choices, and a Score Model evaluates them. The system returns:
- multiple independent votes from diverse LLMs
- a unified Confidence Score for each choice
- an ordered ranking of all choices (derived from the Confidence Scores)
Are you asking the LLMs to provide a Confidence Score?
No.
LLMs are not good at self-assessing their own reliability, and they're especially not good at quantifying it. Neither are most people, for that matter.
We take a different approach that minimizes prompt engineering. By minimizing prompt engineering, we've created a flexible system that can handle any prompt, works with almost any LLM, and minimizes waste, making our system quite affordable.
What is a Score Model?
A Score Model is a collection of LLMs, each with a weight and optional parameters, including optional personality configuration.
- You provide the choices. A Score Model never creates choices; it only evaluates them.
- The Score Model evaluates each choice by having each LLM vote for the best one.
- Every vote increases that choice's Weight. Some LLMs may have a lower weight, making their vote less important. They may vote probabilistically for multiple choices if configured with
top_logprobs. - Even low weight LLMs may profoundly influence which choice wins. Take a look at our benchmarks to see that Score Models can be more correct than any individual LLM in the model.
What is a Confidence Score?
A Confidence Score can be thought of as a ranking for a response, or as measured reliability. We've found that responses with higher Confidence Scores are more likely to be correct, as opposed to responses with lower Confidence Scores. It's an excellent way to deal with ambiguity, which the world is full of.
What is weight?
Each LLM in a Score Model has a weight, which may either be Static (a single number) or use Training Tables.
What are Training Tables?
Training Tables mode is intended for Developers, and is a way to make the weight for each LLM dynamic, based on the input prompt and choices.
Users can train their own Training Tables mode Score Model by marking the Correct Vote for completions. This data influences the per-LLM weights for future completions. Training Table data is separate for each user.
Training Tables mode is an important way to hone a Score Model to your own use case, and to improve the model over time.
How many Score Models are there?
Each Score Model is user-defined.
What LLMs are supported?
ObjectiveAI uses OpenRouter as our upstream LLM provider. A Score Model may contain any LLM supported by OpenRouter. To see the full list, check out OpenRouter's models.
How much does ObjectiveAI cost?
ObjectiveAI, like many AI services, uses credits, which may be purchased. The number of credits used for each request depends on the LLMs used, and the number of tokens processed. We charge a 5.5% ($0.80 minimum) fee when purchasing credits, to cover payment processing fees. Credit usage is the same as charged by OpenRouter, plus a 10% service fee.
If you are an Enterprise customer, or are otherwise interested in custom pricing, please contact us.