Hasura

PromptQL is live on Product Hunt! Tanmai Gopal, Rajoshi Ghosh, Tirumarai Selvan, Anushrut Gupta, and the rest of the team is hanging out in the comments, ready to chat! Drop by, check out PromptQL, ask questions, and share your feedback. We can't wait to hear what you think! 🔗 https://lnkd.in/gAqHfQnJ

We built an AI assistant for our customer support team with #PromptQL. It's connected to our ticket & user data across ZenDesk, Postgres, and BigQuery. Watch #PromptQL as it: - Creates an agentic query plan for your natural langauge questions - Stores retrieved data as memory artifacts (doesn't clog up the context windows) that can be referenced - Has a human-in-the-loop model for permanent changes - like making refunds Demo ⤵️

Ready to future-proof your cloud solutions? Join Rahul Agarwal for a deep dive into the Data Delivery Network (DDN) at @apiworld! This is going to be a hands-on workshop covering: 🔀 Creating a unified, flexible data access layer that seamlessly integrates with your data sources/services 📈 Building scalable, adaptable workflows that evolve alongside your app and data requirements 🔗 More about the workshop ➡️ https://bit.ly/3A6Zrj0

Bonjour from the future! See how we are reshaping the way #AI will interact with your data. 👀 https://lnkd.in/g-__Yski

Hot take but AI Assistants aren’t living up to the hype Despite the buzz, closed-domain AI assistants are falling short. Without reliable, context-aware responses, they’re not ready for serious business use. Where AI Assistants Fail Here’s a scenario from a well known sales assistant that’s out there today: 📊 User Query: “What’s the length of my average sales cycle?” ➡️ Assistant Response: “I calculated the average sales cycle length for your opportunities, but there are no results to show.” The assistant can’t perform a computation. Why? Let’s break it down. 🛑 The Issue: Closed-domain AI assistants rely heavily on search-first algorithms, making them unsuitable for high-trust applications. Consider a task like “Find all emails from last week that need follow-ups.” A search-based AI might skip important messages if they lack specific keywords, leaving critical follow-ups unnoticed. When this incomplete data is passed to the language model, the result is unreliable, making these assistants ill-suited for nuanced business queries. ✅ The Solution: Agentic query planning. Instead of rigid keyword search, assistants should gather all relevant emails and then use an LLM to classify follow-ups—just as a person would—ensuring accuracy. That’s why our AI lab built PromptQL - An agentic, data access API for your AI! PromptQL is available now in Alpha ➡️ https://bit.ly/4f1z25j We’re also releasing the Agentic Data Access Benchmark. We built a dataset across 5️⃣ closed domains and put popular assistants to the test: 💡They could only handle the simplest questions.  ⚠️ ~ 80% of real-world, medium-to-high complexity questions performed poorly. Here's the full Agentic Data Access Benchmark ➡️ https://lnkd.in/gr_4iKr2

🚀 Happening tomorrow...our most exciting product launch to date! Our #AI lab has been hard at work, figuring out how to make data access for AI truly intelligent, accurate, and effective. We can't wait to show off what we've built. Plus catch an exclusive keynote from CEO Tanmai Gopal detailing how truly agentic data access will transform the AI landscape. 📅 Save the date and elevate your AI game! https://lnkd.in/g6DyEN6j

Would you give LLMs access to your private data? Here's what folks at GitHub Universe had to say about that question.

🌟 Exciting news from GitHub Universe 2024! 🌟 Hasura is here at the Gateway Pavilion, ready to showcase our latest product release! Stop by our booth to meet our team, learn how Hasura can transform your data strategies, and take home some exclusive swag. Let’s connect and explore the future of data together! #Hasura #GitHubUniverse #Innovation #DataSolutions #ConnectWithUs

We're showing off our new AI data access tool online during Dev Day on 31st Oct! See how you can use it to build your own intelligent Customer Support Assistant that can ✅ Increases productivity ✅ Find answers and close tickets faster ✅ Provide insights into the team’s performance ✅ Eliminate repetitive questioning ✅ Unify customer data for a comprehensive view ✅ Leverage product usage data and telemetry for proactive support Register ➡️ https://bit.ly/3Yn35gW

Learn how to get your API RAG ready! Don't miss Anushrut Gupta's talk at API World on 7th Nov. He's gonna cover: - Why API based retrieval doesn’t work well for RAG - What RAGs need from APIs - Making existing APIs RAG-ready without full rebuilds Check out the talk ➡️ https://bit.ly/3AjtHay