Problem Statement

The complexity of managing multiple systems is a challenge. Users often struggle with navigating ever-growing platforms, APIs, file formats, and data structures, leading to inefficiency and a steep learning curve.

Existing efforts with LLMs like ChatGPT will always be limited by their goal of ever larger models performing generally better at tasks. A classic Jack of all trades, master of none problem. This creates slower models, uneven performance, and a lack of trust that it can do any specific task well.

Cofounders

• Evan is a seasoned machine learning engineer who shipped high performing models at Meta and Apple.
• Quinton is a business and marketing specialist with experience building and scaling companies to millions in revenue.

Who We Are

We have spent the last several months speaking with industry leaders in hopitality, finance, and technology to understand their common pain points and have identified a clear path forward. Now we are building a team of researchers, engineers, and industry experts passionate about solving this problem.

Mission Statement

To train highly-accurate custom action LLMs and create a unified natural language interface for seamless, accurate interaction with diverse applications, encompassing APIs, file management, data handling, and code execution.

What are Actions?

Think of actions as API calls that perform specific online tasks. Anything from sending an email or retrieving information from your Google Drive to massive tasks like processing large datasets or managing global cloud infrastructure. Actions are specific tasks executed by our system in response to natural language commands. They range from simple file operations to complex data manipulations and API interactions. Each action is designed to understand and efficiently execute user requests, transforming the way you interact with your applications.

Impact and Benefits

Our system will allow users to interact with their applications using natural language, eliminating the need to learn and navigate multiple interfaces and APIs. Users will be able to perform complex tasks easily, and our system will be able to execute them with high accuracy and efficiency.

Seeking Cofounders

We are looking for an ML research cofounder as well as a ML engineer and full stack developer to join our team. If you are passionate about solving this problem, have experience in machine learning, training/finetuning LLMs and are interested in joining our team, please reach out below.