Rill Data

📣 Introducing AI Agents for Rill 📣 Building on our existing MCP server integration, we're excited to share project-wide chat in Rill, which is our first interactive agent of many to come. 🚀 It's not just a chatbot—you always have a dashboard ready to back up any responses from the AI! 🤯

In 2014, The Economist ran a special report on how real-time programmatic bidding was revolutionizing advertising. Now, AI is doing it again, and at a faster pace. Analytics played a critical role in that last revolution, and will be an even bigger part of this one. Agents need insights to drive decisions, and are voracious consumers of analytics. We have a front-row seat to this: Agentic queries are beginning to eclipse dashboard clicks across Rill Data's business intelligence customers. Yesterday I spoke with @tipsheetai about how agents are transforming analytics and decision-making in every industry, especially in media and advertising. Agents provide their highest leverage at decision points like routing and pricing, which in programmatic advertising are already online and fully digitized. There is now a global race to unlock the value of intelligence in every vertical, and as usual, media and advertising are at the tip of the spear. Partners like @CloudX and @tv_scientific understand this and are putting agentic analytics and workflows at the core of their platforms. To paraphrase what William Gibson said about the future: agentic analytics is already here— it's just not evenly distributed.

Today's tipsheet interview for Thursday, March 19... Rill Data CEO Michael Driscoll spoke to tipsheet yesterday about AI and his agentic analytics company. Topics included: * Mr. Driscoll spoke to tipsheet about Rill Data yesterday, including: * Rill Data’s origin story at Snap * What Rill can do for advertising and marketing * The transition to solutions for humans and agents * Plugging into large language models (LLMs). * Observability’s role in advertising today * What is Conversational BI? * MCP for Conversational BI * Are APIs going away? * The reasoning behind ‘local-first’ analytics * AI and ‘local versus cloud’ * The state of mediation in today’s ad ecosystem * Agent-to-agent future at scale — when? Read: tipsheet.ai/technology/ril…

In this article, @sspaeti looks at how we build agentic-friendly and local-first analytic stacks with @motherduck, Rill, and agents. The convergence of embedded analytics engines (DuckDB/MotherDuck), declarative BI-as-code (Rill), and AI agent protocols (MCP) is creating a new architecture for business intelligence, one where dashboards become code and analysts shift from clicking to prompting. rilldata.com/blog/building-…

Why do we use MotherDuck and Rill for agentic-first data tasks? Ghanshyam Chodavadiya from SWYM says "Rill lets us encode business context directly into our BI layer. Combined with MotherDuck and the Rill MCP client, it gives us flexible data control while powering automatically generated client dashboards and AI-driven insights."

In the latest Rill 0.83 release, now you can generate a full Canvas dashboard directly from an existing metrics view. We also added a new connector for @supabase and updated the project status pages making it easier to start exploring your data in Rill. docs.rilldata.com/notes/0.83

"AI-native business intelligence firm Rill Data has added Devan (Fearman) Kane as CMO, Jay Stevens as CRO, among others." We are excited to expand our commercial team as we build the fastest business intelligence tool. Watch the video to see to how you can build fast agentic analytics with Claude Code and Rill. rilldata.com/blog/building-…

Guess who loves local-first, code-first analytics tools? 🤖 Agents. Claude Code + Rill can now build a full data stack in seconds – pipelines, database, and dashboards visualizing millions of records – with BI-as-code, on a single machine.

Rill is at #MarketectureLive! If you want to get personal demo of Rill's AI-native BI tool from Jay Stevens or Farris Jallad, let’s meet up! With thousands of users at Comcast/FreeWheel, InMobi, and MNTN, Rill is the leading BI tool for ad tech platforms with use cases in revenue monitoring, partner reporting, yield optimization, discrepancy troubleshooting, and more.

Times are shifting rapidly toward CLI-first development. You know that's true when even email and calendar get their own Google CLIs. So why not bring that same CLI-first, developer-friendly approach to your business metrics? If you're a data engineer or analytics engineer building with agents, this one's for you. With the stack of DuckDB+MotherDuck and Rill as an agent-friendly, local-first frontend, that's exactly what's needed these days to work with agents. Especially to retrieve context from local specification of metrics and dashboard definition - getting exact context through SQL and YAML. Focusing on developer workflow with the use of Claude Code, Codex, and Cursor that can instantly update your dashboard, update metrics in the unified layer for all visualizations to pick up, or just adding new columns to the database with the DuckDB CLI, whether the data is locally or in the cloud with serverless MotherDuck. To any data engineer, this is a joy to work in, and the iteration cycles from `ambiguous prompts -> verifiable configs -> shipping visualizations` is so fast. Increasing quality by allowing domain-experts who know the business best to own more of the data stack, while everything is still versioned in git, automatable, and easy to work with. In this new essay about «Building an Agent-Friendly, Local-First Analytics Stack», we look into general data engineering workflows and working with new agent tooling, why you'd use MotherDuck, and how Rill can help you in this stack. We look at Conversational BI, where Rill turns dashboards into code (and code into agent-readable context), serving as the code abstraction layer in most cases. What I explore more: →We discuss what's next with agentic coding, no more dashboards needed? →We analyze natural language interfaces as they are convenient, but inaccurate? →Does self-serve with BI-as-Code providing the context we need? →How the language we choose matters. Looking at SQL, YAML, and how people choose languages based on Agent use (not human familiarity). And we check limitations the future holds due to the imprecise way of natural language, e.g., "give me the analytics for this week?" Did you mean "from today until last week"? Or how data workloads need to be deterministic and reproducible to backfill faulty data, but AI agents aren't that. We explore three open-source examples in the article: 1. Stack Overflow Developer Survey with zero-pipeline analytics 2. Updated Multi-Cloud Cost Analyzer to add MotherDuck with `DLT_DESTINATION=motherduck` 3. Including a real-world setup from Salomon Vaisberg from Drio Tech, how he uses Airbyte/dlt + BigQuery/MotherDuck/dbt + Rill. If you like this, read the full article at: rilldata.com/blog/building-…. What do you think, and which agent-friendly, local-first analytics stack do you prefer these days?

Rill’s GTM team is growing! We are excited to welcome 4 new team members 🚀 Jay Stevens is our new CRO. Jay has earned a reputation as a commercial leader who transforms businesses of all sizes for growth. Jay brings 25 years of experience in the marketing and advertising technology industry, most recently as Chief Commercial Officer at Permutive. His previous positions include President at Hudson MX, Chief Revenue Officer at Adform, and General Manager, International at Rubicon Project (now Magnite). Devan Kane joins Rill as Fractional CMO, reuniting with Mike Driscoll to help spearhead the company’s growth strategy. A 20-year veteran of the marketing landscape, Devan brings a full stack leadership approach, one honed through leadership roles at Squarespace, Snapchat and Metamarkets. Devan has experience in the art of capturing high-velocity SMB customers while simultaneously navigating the high-touch demands of Enterprise accounts, making her the ideal fit for the next phase of growth for Rill. Rounding out our new hires are Farris Jallad (Head of Sales) formerly at Permutive and Madison Bledsoe Taylor (Account Manager) formerly at Hitachi Solutions. Farris and Madison will lead all account relationships to ensure our customer’s get the most value out of Rill. Welcome to the team, Jay, Devan, Farris, and Madison!

I spent years working with data warehouse automation tools before the modern data stack existed. The biggest lesson? There are two approaches to generating pipelines: Parametric - you define parameters, the tool generates SQL Template-based - you write SQL templates with variables Most modern tools like dbt took the template approach. It's more flexible but requires more SQL knowledge. The automation tools took the parametric approach. Less flexible but faster for common patterns. Neither is wrong - they optimize for different teams. ssp.sh/blog/designing…

The Rill GTM team got together in Park City to strategize for 2026! 🚀 We reviewed the product roadmap and had meaningful conversations on how Rill can really make an impact for our customers. And we had some fun too 🥳 PS - we’re hiring! Join us in building the world’s fastest AI-native BI tool!

Why are hyperscalers racing to offer managed Iceberg? Because whoever controls the catalog controls the ecosystem. If your tables are in a managed Iceberg service, you can query them from any engine - Spark, Trino, DuckDB, whatever. But your metadata stays with that provider. It's a smart strategy. Give away the format, keep the control plane. ssp.sh/blog/open-tabl…

PS - we added support if Gemini is you’re preferred AI provider. Create a Gemini connector, set up your API key and you are good to go! Check out the release notes to learn more: docs.rilldata.com/notes/0.82

Check out what's new in Rill 0.82: 👍👎 AI feedback - give thumbs up or thumbs down to score your conversations with Rill's AI agent ℹ️ New status project page - we overhauled the status page so you can easily search, filter & find resources 🎨 New in Canvas dashboards - AI functionality & scatter plots

In case you missed the latest Data Talks on the Rocks episode - @wesmckinn, creator of Pandas, explains his unexpected switch from Python to Go for new projects. His reason: AI coding agents fundamentally changed the trade-offs that made Python dominant for the last 15 years. Learn more: datatalks.rilldata.com

ICYMI - Simon Spati interviewed Coinbase and Fresha and shares a common pattern - choose @StarRocksLabs when joins are central to your analytics. If you’re looking for a real-time BI tool designed to benefit from StarRocks’ real-time query performance, check out our native StarRocks connector. Shout out to community member Byung Ju Kim for his contribution! rilldata.com/blog/why-coinb…

.@sspaeti's guide covering data modeling strategies and practical S3-to-dashboard examples was featured in ClickHouse’s February newsletter. Check out the guide below and how to build sub-second real-time analytics with ClickHouse. rilldata.com/blog/data-mode…

Our friends at Twing Data built a lightweight dashboard for AWS cost monitoring using Rill for AWS CUR data. A few core Rill features do most of the heavy lifting: 1. Automatic ingestion from S3: Point Rill at your CUR bucket and it handles loading new files as they arrive. 2. Partition-aware updates: New cost files are ingested incrementally on a schedule, so the dashboard stays current without reprocessing everything. 3. ClickHouse under the hood: This scales far beyond “toy demo” size. You can throw very large CUR datasets at it without worrying about performance. Rill also provides a nice way to test changes on “dev” before pushing them to production. Learn more: blog.twingdata.com/p/aws-cost-mon…

For anyone who wants to explore this data with AI, I enriched it and set up a public MCP server you can connect to from Claude, ChatGPT, Cursor, etc. I added: - Provider names and locations - Procedure descriptions and service categories - Flags for providers who have been excluded from federal healthcare programs for fraud MCP server URL: api.rilldata.com/v1/orgs/demo/p… If you want to click around or validate what your AI finds, here's the source of truth dashboard (better on desktop): ui.rilldata.com/demo/medicaid-… Here's the GitHub repo. There's plenty more ways to enrich this, so open to PRs and recommendations! github.com/rilldata/rill-… Disclaimer: I work at Rill and put this together this morning with Claude Code + Rill.