# AI x Data Published articles for AI x Data. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Why we moved our growth analytics back into Tinybird DevFeed: [Why we moved our growth analytics back into Tinybird]() Original publisher: [Read original article]() Author: Pablo Abella Published: 2026-06-01T10:00:00Z Content type: article Language: en Sources: [Tinybird]() Topics: [data]() Tags: [ai-x-data](), [analytics](), [analytics-stack](), [data](), [growth](), [scalable-analytics-architecture]() ### AI overview Tinybird describes Birdwatcher, its internal growth analytics stack, and explains why it moved more of its analytics workflow onto its own data and platform. ### Source excerpt The story of Birdwatcher, Tinybird's internal growth analytics stack, and why we moved more of our analytics loop onto our own data. ## Tinybird Best Practices for AI Agents DevFeed: [Tinybird Best Practices for AI Agents]() Original publisher: [Read original article]() Author: Rafa Moreno, Gonzalo Gómez Published: 2026-01-27T00:00:00Z Content type: article Language: en Sources: [Tinybird]() Topics: [ai-coding](), [coding](), [Testing](), [Deployment](), [Structured-data]() Tags: [agents](), [ai](), [ai-agents](), [ai-coding](), [ai-x-data](), [best-practices](), [coding](), [deployment](), [schema-design](), [testing]() ### AI overview The article presents 20 best-practice rules for using AI coding agents with Tinybird, covering schema design, endpoints, materialized views, testing, and deployment. ### Source excerpt Turn any AI coding agent into a Tinybird expert. 20 rules covering schema design, endpoints, materialized views, testing, and deployment. ## OpenAI agent builder + Tinybird MCP: a data-driven agent workflow DevFeed: [OpenAI agent builder + Tinybird MCP: a data-driven agent workflow]() Original publisher: [Read original article]() Author: Cameron Archer Published: 2025-10-09T10:00:00Z Content type: tutorial Language: en Sources: [Tinybird]() Topics: [OpenAI](), [MCP](), [data]() Tags: [agent](), [ai-x-data](), [data](), [how-to](), [mcp](), [openai]() ### AI overview A step-by-step tutorial on building a data-driven agent workflow using OpenAI Agent Builder and Tinybird MCP. ### Source excerpt OpenAI Agent Builder plus Tinybird MCP creates data-driven agent workflows that actually scale. Here's how to build one step by step. ## Don't trust the prompt: use RLAC to secure LLM database access DevFeed: [Don't trust the prompt: use RLAC to secure LLM database access]() Original publisher: [Read original article]() Author: Jorge Sancha Published: 2025-08-22T10:00:00Z Content type: article Language: en Sources: [Tinybird]() Topics: [Large Language Model](), [Database](), [Artificial Intelligence]() Tags: [ai](), [ai-x-data](), [database](), [llm]() ### AI overview The article discusses using RLAC to prevent AI systems from querying database data they should not access. ### Source excerpt RLAC for LLM database access prevents AI from querying data it shouldn't see. Secure your analytics before exposing them to agents. ## How we built our own Claude Code DevFeed: [How we built our own Claude Code]() Original publisher: [Read original article]() Author: Rafa Moreno Published: 2025-08-12T10:00:00Z Content type: opinion Language: en Sources: [Tinybird]() Topics: [Claude Code](), [Code](), [ai-coding](), [coding]() Tags: [ai](), [ai-coding](), [ai-x-data](), [claude-code](), [code](), [coding]() ### AI overview The article explains why Tinybird built its own Claude Code for internal workflows, arguing that off-the-shelf AI coding tools did not meet its needs and describing what the team learned. ### Source excerpt We built our own Claude Code for internal workflows. Here's why off-the-shelf AI coding tools weren't enough and what we learned. ## Why LLMs struggle with analytics DevFeed: [Why LLMs struggle with analytics]() Original publisher: [Read original article]() Author: Jorge Sancha, Rafa Moreno Published: 2025-07-21T10:00:00Z Content type: article Language: en Sources: [Tinybird]() Topics: [Large Language Model](), [data](), [Query (disambiguation)]() Tags: [ai](), [ai-x-data](), [analytics](), [data](), [llms]() ### AI overview The article discusses why LLMs struggle with analytics and presents an approach that it says enables accurate data querying. ### Source excerpt Why LLMs struggle with analytics and how we fixed that. AI can finally query data accurately. Here's the approach that works. ## How to Create Analytics Agents with Tinybird's Built-in MCP Server DevFeed: [How to Create Analytics Agents with Tinybird's Built-in MCP Server]() Original publisher: [Read original article]() Author: Alberto Romeu Published: 2025-07-07T16:00:00Z Content type: tutorial Language: en Sources: [Tinybird]() Topics: [data](), [MCP Server](), [Large Language Model]() Tags: [agents](), [ai-x-data](), [data](), [examples](), [how-to](), [llm](), [mcp-server]() ### AI overview A tutorial on using Tinybird's built-in MCP server to create LLM-based analytics agents that explore and report on data. ### Source excerpt Learn how to use Tinybird's built-in MCP server to create LLM based analytics agents that autonomously explore and report on your data ## How to build an analytics agent with Agno and Tinybird DevFeed: [How to build an analytics agent with Agno and Tinybird]() Original publisher: [Read original article]() Author: Cameron Archer Published: 2025-07-02T10:00:00Z Content type: tutorial Language: en Sources: [Tinybird]() Topics: [data](), [Artificial Intelligence](), [real-time]() Tags: [agent](), [ai](), [ai-x-data](), [analytics](), [data](), [how-to](), [real-time]() ### AI overview A step-by-step tutorial on building an analytics agent with Agno and Tinybird, including how to give AI safe access to real-time data. ### Source excerpt How to build an analytics agent with Agno and Tinybird step by step. Give AI access to your real-time data safely. ## Birdwatcher Slack app monitors Tinybird pipelines and alerts teams when they break DevFeed: [Birdwatcher Slack app monitors Tinybird pipelines and alerts teams when they break]() Original publisher: [Read original article]() Author: Alberto Romeu Published: 2025-06-23T09:01:00Z Content type: article Language: en Sources: [Tinybird]() Topics: [Slack](), [monitor](), [data](), [App]() Tags: [ai-x-data](), [app](), [chat](), [data](), [monitor](), [slack](), [team]() ### AI overview Birdwatcher is a Slack app that monitors Tinybird pipelines and alerts users when something breaks, allowing teams to receive pipeline notifications in chat. ### Source excerpt Birdwatcher Slack app alerts you when something breaks. Monitor your Tinybird pipelines without leaving your team's chat. ## Building an autonomous analytics agent with Agno and Tinybird DevFeed: [Building an autonomous analytics agent with Agno and Tinybird]() Original publisher: [Read original article]() Author: Alberto Romeu Published: 2025-06-23T09:00:00Z Content type: tutorial Language: en Sources: [Tinybird]() Topics: [data](), [Artificial Intelligence]() Tags: [agent](), [ai-x-data](), [analytics](), [autonomous](), [building]() ### AI overview A setup guide for building an autonomous analytics agent with Agno and Tinybird that uses AI to query data. ### Source excerpt Building an analytics agent with Agno and Tinybird creates AI that queries your data intelligently. Here's the complete setup guide. ## MCP vs APIs: When to Use Which for AI Agent Development DevFeed: [MCP vs APIs: When to Use Which for AI Agent Development]() Original publisher: [Read original article]() Author: Jorge Sancha Published: 2025-06-10T14:00:00Z Content type: comparison Language: en Sources: [Tinybird]() Topics: [AI Agent](), [MCP](), [Development]() Tags: [2026](), [ai-agent](), [ai-x-data](), [apis](), [development](), [mcp]() ### AI overview This comparison examines MCP and APIs for AI agent development, presenting them as different tools with different strengths and indicating when to use each in 2026. ### Source excerpt MCP vs APIs for AI agent development: different tools, different strengths. Here's when to use each in 2026. ## Updated results from testing 19 LLMs on SQL after methodology feedback DevFeed: [Updated results from testing 19 LLMs on SQL after methodology feedback]() Original publisher: [Read original article]() Author: Víctor Ramírez Published: 2025-05-16T00:00:00Z Content type: opinion Language: en Sources: [Tinybird]() Topics: [Large Language Model](), [SQL]() Tags: [ai-x-data](), [llms](), [sql]() ### AI overview The article presents updated results from testing 19 LLMs on SQL after readers challenged the testing methodology. The supplied evidence does not include the specific results or methodological changes. ### Source excerpt We tested 19 LLMs on SQL. The results surprised us. Then you challenged our methodology. Here's the updated truth. ## Which LLM writes the best analytical SQL? DevFeed: [Which LLM writes the best analytical SQL?]() Original publisher: [Read original article]() Author: Víctor Ramírez, Alberto Romeu Published: 2025-05-08T00:00:00Z Content type: comparison Language: en Sources: [Tinybird]() Topics: [Large Language Model](), [SQL]() Tags: [ai-x-data](), [llm](), [llms](), [sql](), [writing]() ### AI overview The article benchmarks the SQL-writing ability of 19 leading large language models to assess whether natural language can replace SQL. ### Source excerpt Can natural language replace SQL? We benchmarked the SQL-writing ability of the top 19 LLMs to find out. ## Using LLMs to generate real-time data visualizations DevFeed: [Using LLMs to generate real-time data visualizations]() Original publisher: [Read original article]() Author: Cameron Archer Published: 2025-04-17T00:00:00Z Content type: tutorial Language: en Sources: [Tinybird]() Topics: [data](), [Large Language Model](), [real-time]() Tags: [ai-x-data](), [data](), [generate](), [how-to](), [llms](), [real-time]() ### AI overview This tutorial explains how to use LLMs to generate user-defined real-time data visualizations, allowing users to create charts by asking questions. ### Source excerpt Using LLMs to generate user-defined real-time data visualizations lets users create charts by asking. Here's how to build it. ## Build natural language filters for real-time analytics dashboards DevFeed: [Build natural language filters for real-time analytics dashboards]() Original publisher: [Read original article]() Author: Cameron Archer Published: 2025-04-10T00:00:00Z Content type: tutorial Language: en Sources: [Tinybird]() Topics: [dashboards](), [real-time](), [Artificial Intelligence](), [data](), [Query (disambiguation)](), [SQL]() Tags: [ai](), [ai-x-data](), [analytics](), [dashboards](), [data](), [real-time](), [sql]() ### AI overview This tutorial describes natural-language filters for real-time analytics dashboards. Users can ask questions about data, while AI translates their requests so SQL knowledge is not required. ### Source excerpt Natural language dashboard filters let users query data by asking questions. No SQL knowledge required. AI handles the translation. ## Five AI Features for Production Apps DevFeed: [Five AI Features for Production Apps]() Original publisher: [Read original article]() Author: Alberto Romeu Published: 2025-04-02T00:00:00Z Content type: tutorial Language: en Sources: [Tinybird]() Topics: [Artificial Intelligence](), [App]() Tags: [ai](), [ai-x-data](), [app](), [production]() ### AI overview An article introducing five AI features that can be built to add immediate value to an app. ### Source excerpt 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. ## Instrument your LLM calls to analyze AI costs and usage DevFeed: [Instrument your LLM calls to analyze AI costs and usage]() Original publisher: [Read original article]() Author: Alberto Romeu, Rafa Moreno Published: 2025-03-27T00:00:00Z Content type: tutorial Language: en Sources: [Tinybird]() Topics: [Large Language Model](), [observability](), [Artificial Intelligence](), [Latency]() Tags: [ai](), [ai-x-data](), [latency](), [llm](), [observability]() ### AI overview A tutorial on instrumenting LLM calls to analyze AI costs, usage, and latency through an observability setup. ### Source excerpt Instrument your LLM calls or fly blind on costs and latency. This observability setup shows exactly what your AI is doing. ## Analyze Bluesky Data with Claude Using the Tinybird MCP Server DevFeed: [Analyze Bluesky Data with Claude Using the Tinybird MCP Server]() Original publisher: [Read original article]() Author: Claude, Tinybird MCP Server Published: 2024-11-27T00:00:00Z Content type: article Language: en Sources: [Tinybird]() Topics: [Claude](), [Bluesky](), [MCP Server]() Tags: [ai](), [ai-x-data](), [claude](), [data](), [mcp](), [mcp-server]() ### AI overview The article presents using Claude with the Tinybird MCP Server to analyze Bluesky data and find insights from connected social data. ### Source excerpt Claude can analyze Bluesky data with the Tinybird MCP Server. Connect your social data and let AI find the insights. ## Real-time anomaly detection: algorithms, use cases & SQL code DevFeed: [Real-time anomaly detection: algorithms, use cases & SQL code]() Original publisher: [Read original article]() Author: Jim Moffitt Published: 2024-04-01T00:00:00Z Content type: tutorial Language: en Sources: [Tinybird]() Topics: [real-time](), [Algorithms, Complexity](), [SQL](), [Code]() Tags: [ai-x-data](), [algorithms](), [anomaly-detection](), [code](), [examples](), [how-to](), [real-time](), [sql](), [systems](), [use-cases]() ### AI overview A tutorial on building real-time anomaly detection systems using SQL algorithms, with examples and use cases for detecting outliers. ### Source excerpt Learn how to build real-time anomaly detection systems. Explore SQL algorithms, examples, and use cases to detect outliers instantly.