June 2025 Summaries

The company behind a large outpatient diagnostic imaging provider in the U.S. modernized its critical scheduling process for diagnostic tests, including mammograms, by accelerating to an AI-driven solution called PromptQL. The traditional UI modernization was deemed insufficient due to the complexity of scheduling, which required a scheduler to manually navigate across dozens of tabs and memorize business rules to select the correct procedure code from over 300 options. This task alone could take up to 12 minutes per appointment, resulting in costly mistakes such as incorrect codes, canceled appointments, lost revenue, and patient dissatisfaction. PromptQL created an AI-powered scheduling co-pilot that improves operational efficiency, enables faster and more accurate scheduling, and supports better patient outcomes. With the expected productivity gains of up to $50 million once fully rolled out across hundreds of locations in North America, the customer now has a scalable, explainable, and efficient workflow that reduces friction for patients, schedulers, and developers alike, and is preparing to expand the model to other diagnostic imaging workflows.

The company, one of the world's largest restaurant chains, faced a challenge in getting insights from its vast data warehouse and operational systems. Business teams had limited access to accurate answers due to the complexity of querying the data and the lack of expertise among analysts and data experts. However, by layering PromptQL on top of their data, they were able to transform how they engage with data, gather insights, and make decisions. With PromptQL, business users can ask real questions in plain English, such as "Why are delivery sales down in Munich?" and receive accurate answers with full reasoning and explainability. The solution introduces three major innovations: understanding the business context, self-correcting and resilient querying, and transparent and explainable results. These innovations enable PromptQL to provide reliable insights, build trust among users, and unlock revenue growth without overhauling the existing data stack. The company is now expanding PromptQL access to more teams and use cases, integrating operational actions directly into the AI loop, and building reusable programs to power repeatable workflows.

Hasura has released PromptQL, a new data access product that is the spiritual successor to GraphQL for the age of AI. `PromptQL takes the magical CRUD APIs offered by Hasura's existing products and adds business logic capabilities, allowing developers to write complex logic entirely in natural language. `The platform creates PromptQL programs on the fly, subsuming CRUD use cases while enabling users to interact with data using natural language. `This allows for a world where GenAI systems can be used to help users make decisions or execute workflows, and provides a new way for developers to build AI-powered applications.