PromptQL is a data access agent to build AI assistants on ANY data (structured, unstructured or APIs). It gives your AI agentic data access so it can create complex query plans, run computations, retry on failures, modify query plans, and reduce hallucinations
Hi PH,
After months of hard work, trying to understand the challenges and issues around AI and data, we're excited to share PromptQL, a new data access agent from Hasura for building AI assistants to talk to your data.
You can try it out by building a GitHub issues assistant in 5 minutes here.
Although this assistant is quick to build, it is remarkably more powerful than any other assistant out there. Why? Because we have used numerous techniques to combine the power of querying structured as well as unstructured data together. Moreover, we compose data access with numeric as well as LLM computations to generate a flexible query plan to achieve complex user goals.
How much can PromptQL do? We've put together the Agentic Data Access & Computation benchmark to illustrate the various kinds of goals that users would want to achieve in their assistants and to help compare solutions.
The current way of building assistants rely on canned RAG pipelines which perform quite poorly on this benchmark, and have limited use in real-world business critical scenarios. We built PromptQL as a way to give LLMs agentic access to data so that you can build flexible and reliable assistants.
As we have been building APIs for many years now, starting as "the GraphQL on Postgres" tool and having since generalized to various data sources in our latest product, Hasura DDN, we've realized that we have the perfect foundation for crafting something optimized for AI. On top of this, we have done a lot of incredible AI research and engineering to make PromptQL.
We’d love it if you tried it out and let us know what you think!
Also, a huge thank you to @kevin for hunting us!
Great job on launching PromptQL! Can you tell us more about its capabilities for unstructured data?
Congrats on the launch! This looks like it takes a lot of work out of building a custom agent with RAG. It also avoiding the need for complex routers in the pipeline to direct queries to specialized agents. Nice list of datasource integrations too!
The flexibility here excites me, being able to work with any kind of data could make my AI projects much more efficient.
As the kids say: I did a thing with this! 🤗
https://www.linkedin.com/posts/r...PromptQL has been a lot of fun to explore. The biggest blocker I've had in working with AI is it's inability to accurately traverse complex queries or structures like a human would. PromptQL solves that and gives me an assistant that "thinks" like me (or better).
Congrats on the launch! PromptQL sounds like a game-changer for AI assistants and data access. How does it handle different data formats like CSV, SQL, and APIs? Can't wait to try it out!
Congratulations on your launch, @tirumarai! PromptQL seems so useful and will surely ease a lot of operations.
About PromptQL on Product Hunt
“Moving from RAG to agentic data access”
PromptQL launched on Product Hunt on November 7th, 2024 and earned 219 upvotes and 6 comments, placing #9 on the daily leaderboard. PromptQL is a data access agent to build AI assistants on ANY data (structured, unstructured or APIs). It gives your AI agentic data access so it can create complex query plans, run computations, retry on failures, modify query plans, and reduce hallucinations
PromptQL was featured in API (98.1k followers), Developer Tools (511.2k followers) and Artificial Intelligence (466.5k followers) on Product Hunt. Together, these topics include over 163.3k products, making this a competitive space to launch in.
Who hunted PromptQL?
PromptQL was hunted by Kevin William David. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how PromptQL stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Kevin William David