The Querri Library is where your data gets organized around the questions your business asks, so every answer comes from the same trusted, shared foundation.. The library learns your definitions, business context, and past analysis, so its answers are grounded in how your business actually works. And when it doesn’t know, it says so, instead of making things up.
Congratulations on the launch! Excited to see more work in the space of empowering the rest of the org. How do you account for the onerous nature of keeping AI in sync with business context? Data owners aren’t always in calls to receive the context real time. It’s unlikely leaders who are on calls have time to update context. And in my experience, how operations define it verbally to data teams rarely aligns perfectly with how it actually has to be coded, making them a less than ideal fit to maintain definitions of tables they didn’t create.
Hey @daveaingram and @amy_ingram - Congratulations on your launch. Very interesting concept. Are there any data limits so Querri can handle and return answers with out any latency issues?
Also, Can we limit the access to answers by team or by data sets?
Congrats on the launch! Really like that it says what's missing instead of giving a confident wrong number.
Shared business definitions are a smart focus, seem pretty relevant to me! Curious how the library handles conflicting definitions across teams, and whether users can trace each answer back to its sources/authors, congratulations on your launch! 🚀
Dave and the team have been amazing to work with as I've looked to roll out better visibility across a number of systems across multiple companies in our portfolio. There has been no system they've been unwilling to try and build connectors for which has been a huge time benefit for me in a job where time is a premium.
How do you handle when the underlying data changes, business definitions evolve or 2 equally valid interpretations exist? Who ultimately owns the truth; the data, semantic layer or the person asking ques?
Congrats Dave, Amy and the Querri team. The point about the same question getting a different answer tomorrow is the real problem with AI on top of data. When two teams define "active customer" differently, does the Library force one definition, or can both live side by side?
Building Querri has been quite a journey!
Our mission, from the very beginning, has been to make working with data accessible to everyone. In a world where businesses collect more data than ever, understanding that data is no longer just a nice-to-have. It can make or break important business decisions.
But getting data together from dozens of different systems is hard enough. Getting AI to give you reliable answers based on your business's definitions of revenue, churn, or other important metrics is another challenge entirely.
We've spent thousands of hours tackling this problem. Because it matters.
AI is an incredibly powerful tool, but it needs to understand your business context. We're also huge believers in keeping humans in the loop. Data has so much nuance, and it would be naive to assume AI automatically knows how your business defines everything or how you want to handle every inconsistency.
That's why we've built so many ways for people to guide the AI, teach it their business context, and stay in control of how their data is cleaned, analyzed, and understood.
And security isn't an afterthought. Querri has completed a SOC 2 Type II audit, is ISO 27001:2022 certified, supports HIPAA compliance, and never uses customer data to train AI models.
I'm incredibly proud of our team and what we've built together.
We're excited to share it with the Product Hunt community, and we'd genuinely love your feedback, questions, and ideas. That's how we learn, grow, and keep getting better!
Hi team, congrats on the launch. Isn't it same thing those big data warehouse players are building? like Cortex from snowflake and Geni from databricks? and I think the challenge for the data query using nlp is governance and how to make sure you answer is correct
Really like this approach. Building AI around a business’s actual context rather than just giving it access to data feels like a meaningful step forward. Good stuff!
congrats team! rebuilding an old dashboard from just a screenshot sounds kinda wild what happens if the numbers don't match the original, does it tell you why?
Saving what the team means by “sales” is the detail that stood out. It gives people something concrete to check when two reports disagree.
Hi Product Hunt! Dave here, founder and CEO of Querri.
Today we’re launching the Querri Library and the Librarian, the biggest release in Querri’s history. Querri is the question-first data platform: you start with the questions your business asks, and Querri builds what’s needed to answer them, then keeps learning your business.
The problem → solution
AI made asking your data a question easy. It didn’t make the answer yours. Point a general-purpose AI at real company data, with hundreds of tables and five definitions of “active customer,” and it picks one. Ask again tomorrow and it may pick another.
So we stopped trying to make the AI a better guesser and changed what it’s standing on. The Library is a map of your business: the questions your team keeps asking, the KPIs that answer them, the definitions behind those numbers, and the data they’re computed from. The Librarian is the agent that builds it with you, in plain English, and answers from it.
What makes it different?
A chatbot on top of your data is easy to build. I can say that with some authority, because that’s roughly where Querri started. What’s hard is making the answers right, and yours. Every answer in Querri shows the rows, the calculation and the sources it read. Every piece of data loaded gets 180+ quality checks. When a question has more than one reasonable reading, Querri tells you. In our benchmarking, Querri flagged the other defensible answer on 73% of its responses, versus 12% for a leading general-purpose AI agent given the same data. And when the data is too messy or isn’t there, it tells you what’s missing instead of handing you a confident number that happens to be wrong.
And all of this feeds into chat, dashboards, MCP for Claude, ChatGPT and the like, and APIs and CLI for further extension.
Key features & use cases:
Start from your questions before you connect a single file
125+ connectors, plus spreadsheets and files
KPIs defined once and tied to Revenue, Cost, Efficiency, Quality or Risk
Business rules you settle in chat (“sales means paid orders only”) saved as facts
Paste a screenshot or sketch of an old dashboard and it rebuilds it, calculations included
Monitors that watch a KPI by region, store or rep and tell you which one moved (set up with an agent but run without every time the data updates)
Share a cleaned view with another team instead of the raw tables via access controlled workspaces .. we’re talking real life data work here after all.
While you sleep, Querri “dreams” about your business and suggests new questions and KPIs. Nothing changes without your OK.
Who is it for?
Ops, customer success and revenue teams whose answers live across several systems. Small business owners doing the data work themselves. Consultants who want each client’s definitions to live somewhere. Data teams who want give the business an easy, accurate and reliable front door and free their issue queue. And software companies that want to white-label it for their own customers.
It learns your business, and it never trains a model on your data. We’re SOC 2 Type II, HIPAA and ISO 27001:2022 certified.
My ask: bring the question that tripped up the last AI you tried, and tell us what Querri does with it. I’ll be here all day reading and answering every comment.
P.S., want to really put it through the paces? Sign up for a trial with HUNTER1000 promo code and you'll get a 1000 bonus credits to get some serious value out of your data.
About The Library on Product Hunt
“Your business context organized by queries”
The Library launched on Product Hunt on October 21st, 2026 and earned 174 upvotes and 25 comments, placing #4 on the daily leaderboard. The Querri Library is where your data gets organized around the questions your business asks, so every answer comes from the same trusted, shared foundation.. The library learns your definitions, business context, and past analysis, so its answers are grounded in how your business actually works. And when it doesn’t know, it says so, instead of making things up.
The Library was featured in Analytics (174.2k followers) and Tech (635k followers) on Product Hunt. Together, these topics include over 188.2k products, making this a competitive space to launch in.
Who hunted The Library?
The Library was hunted by Neelam Chakrabarty. 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 The Library stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Neelam Chakrabarty