Vishal Motwani, Numbers Station AI, Founding Product Manager Amit Shah, JLL, Senior Director
Numbers Station Labs is excited to release Meadow, the first open source agentic framework built for data workflows. Data workflows are multi-step processes where an analyst first transforms, generates, and analyzes structured data to gain insights and take action. Mutli-AI-agent architectures are proving to be the key to solving highly complex tasks with AI that one model alone cannot solve, and are paving the way for end-to-end data workflow automation. None of the existing general-purpose agent frameworks are tailor-built for data analysts and lack support for sharing knowledge across a data layer, data-aware task deconstruction, and iterative data debugging. To address these concerns, we’ve built Meadow—the first multi-agentic framework for data tasks where all agents are data-aware and can communicate via shared data layer, hierarchically plan data tasks, and query the data interactively to debug. Early results show that Meadow, without any expensive labeled examples, is within 3.6 points of state-of-the-art on the Spider text-to-SQL benchmark and realizes lifts of up to 20 points over simple, zero-shot text-to-SQL prompts. Meadow is also capable of detecting data errors and uncovering incorrect benchmark queries that did not take into account extra white spaces in the data.
