Automating Customer Inquiry Translation to PostgreSQL Queries Using LLMs

The goal of this project is to develop a system that utilizes large language models (LLMs), such as ChatGPT, to accurately translate customer inquiries into PostgreSQL queries. This system aims to streamline data retrieval and analysis processes, reducing the time and effort required by staff to interpret and respond to customer requests.

Landing Page Design

To create landing pages for different segments of the market and optimize the content on G2 and Capterra.

Digital Marketing

To create digital assets that align with our product and to design and execute marketing campaigns (e.g., LinkedIn and Instagram ads).

Improved constraint satisfaction problem formulation

Improving CSP problem formulation for physician/resident call scheduling is the main activity to be undertaken. This will have a large impact on the healthcare systems currently served with Mesh AI. On the algorithm side, better solutions will be reached at smaller time and computation resource levels. This will reduce engine costs, power consumption, and most importantly will lead to better allocation of ever-shrinking human resources to healthcare tasks and needs. Not only highly qualified healthcare leaders and administrators will spend less time in the setup and customization steps but also every single instance of generating a ‘call schedule’ will be done with smaller time investments by an already over-burdened HCP (health care providers) community.