nao Labs (YC X25)

Launching the first agentic analytics meetup in Paris 🇫🇷 👾 The goal: gather the data community, share experiments, learnings, and figure out together how to make agentic analytics work. The format: a roundtable with 4 data teams who setup their agent with different solutions (Snowflake Cortex, Hex, nao Labs (YC X25), Dust, Looker, in-house solution) Our speakers: Yochan Khoi (Gorgias), Anaïs Ghelfi (Malt), Benjamin Rouif (Getaround), Léon Stefani (Brigad) 31st March 6pm Paris 20 Wacano Drinks on us! 🥤 Register here https://luma.com/h7stn67w

nao is going live today! Join us for breakfast or tea 🥯 🍵, 6am PT / 5pm CET We'll discuss analytics agents, context engineering, show you cool nao features - all this in the beautiful world of open source 🕊️ https://luma.com/z87etlcx

Conversational analytics has been one of the most talked about use cases for GenAI. Lately, I've been testing nao, by nao Labs (YC X25), on the Indian capital markets database I had built for my hobby project — and I'm genuinely impressed. What I loved out of the box: ✅ Effortless setup ✅ Folder-based context management using .md files — elegant and effective What I added on top: 📊 Replaced Recharts library with Plotly for enhanced interactivity and unlocking all chart types 📈 Built a feedback loop where charting agent also calculates and return key metrics back to the analysis agent for grounded references and sharper analysis (Check the video to see it in action 👇) Using a similar setup, I am now experimenting on developing a conversational analytics agent for CxOs which sits on top of Financial and CRM data. Massive credit to nao Labs (YC X25) — especially Claire Gouze and Christophe Blefari — for building such a well-thought-out, extensible tool and making it open source👏. Link to the GitHub repo in comments. #GenerativeAI #DataAnalytics #OpenSource #FinanceAI #ConversationalAI

💥 We're launching the first Open Source Analytics Agent Builder 🤩 We want to bring a radically different approach to agentic analytics: ❌ No more black-box, one size fits all, vendor lock-in solutions. 🧱 An open framework, to let data teams build their context and agent the way they want 📂 A file-system approach, so you can put any context in it and your agent can retrieve it fast ⚙️ A context engineering tool: test different contexts to get the best agent performance 💬 A UI to deploy for anyone at the company to ask questions on data Check out our repo here: https://lnkd.in/eKqr9jXX We want nao to become a foundation for context engineering. A framework for data teams to discover and share how to create the best AI agents for analytics. We're excited to build this in the open with our data community!

wrapping up a 6mo project with a large client in the enterprise manufacturing space this week. we migrated materialized Snowflake views to a new dbt Labs project: - 322 staging files - 71 intermediate tables - 35 mart tables - 7 incremental tables I used the opportunity to lean into new AI code dev tools: - Anthropic's claude code within Cursor - nao Labs (YC X25) the client was ~18k person org. im proud of the rate at which we got things done despite the friction we faced in (2) areas. (1) our end product was affected by compromises on quality to appease the client who wanted things a certain way / didn't prioritize certain dev standards, in lieu of faster code deployments (lots of small things e.g. no lint checks in CI jobs, bypassed code approvals). a consensus on compromised quality is toxic to a project. It’s a silent agreement that discourages individual contributors from pushing a task closer to perfection, once they know their colleagues won’t be. It kills motivation. The collective end result is haphazard work and tech debt. (2) client-side analyst/engineers became defensive over recommendations and hard to work with. in these situations I try to stay firm on my position while being mindful / proactive addressing personal feelings at stake. work is emotional and people are sensitive. I think its better to have an uncomfy chat about feelings hurt than allow hidden resentments to fester eg 'im sorry you feel belittled by this choice....im pushing for X to achieve Y but can see how its causing Z and thats not cool'. vibes impact quality always learning. headed to asia for the next 2mo. stay tuned massive thanks to my consulting colleagues. (i wish you could add spotify songs to linkedin posts 😅)

🔥 💬 We’re launching Conversational Analytics in nao ! 🤖 ⚡️ We started nao with one simple goal: be the best tool to work on data with AI. Data teams spend a lot of time preparing data, but create value analyzing data and cracking business questions. Now with nao, they can do both in the same tool, with the same context and AI power: 💬 answer simple business requests 🕵️ deep-dive complex analysis 🚨 debug a data quality issue 📊 draw charts to share results visually If you want to give it a try for your data team, come say hi! 👋