Why you should never trust your inference layer to enforce security policies and always enforce row-level access control (RLAC) for LLM database access.| www.tinybird.co
Or, rather, how we built Tinybird Code, a command line agent inspired by Claude Code, but optimized for complex real-time data engineering problems with ClickHouse.| Tinybird Blog
LLMs are trained to interpret language, not data. Bridging the gap between AI and data means obsessing over context, semantics, and performance.| Tinybird Blog
Learn how to use Tinybird’s built-in MCP server to create LLM based analytics agents that autonomously explore and report on your data| Tinybird Blog
Learn how to build an agent that can explore your data, generate SQL queries, and run comprehensive data analysis over large-scale datasets.| Tinybird Blog
I built Birdwatcher, an analytics agent that connects to your Tinybird Workspace. You can add it to your Slack workspace to start talking to your data.| Tinybird Blog
Here's how I build Birdwatcher, an autonomous AI agent that uses the Tinybird MCP Server to explore data in Tinybird and accomplish any mission you give it.| Tinybird Blog
MCP enforces consistency that HTTP APIs lack, which is essential for LLMs' autonomous tool selection and agent autonomy. This post breaks down real-world trade-offs of using MCPs and/or APIs| Tinybird Blog
We benchmarked 19 LLMs on analytical SQL and the internet had thoughts. Here's a breakdown of your feedback, what we got wrong, what we got right (but didn’t explain), and how we’re improving the benchmark for round two.| Tinybird Blog
Can natural language replace SQL? We benchmarked the SQL-writing ability of the top 19 LLMs to find out.| Tinybird Blog
UIs are changing. Here's how to use LLMs and real-time analytics APIs to build allow your users to generate their own data visualizations.| Tinybird Blog
Click-to-filter is out. Prompt-to-filter is in. Learn how to ditch the filter sidebars and dropdowns and replace them with a single user text input and an LLM.| Tinybird Blog
It's hard to sift through all the AI hype. Here are 5 AI features you can build that add immediate value to your app.| Tinybird Blog
If you're building AI features, make sure to instrument your LLM calls so you can analyze costs, usage, and adoption. Here are a few examples in Python and TypeScript.| Tinybird Blog
This is the full, unedited transcript of our conversation with Claude, whose context-awareness is provided by a v0 Tinybird MCP Server.| Tinybird Blog