Unsiloed 融资 750 万美元,为 AI 智能体打造文档基础设施
刚拿了 Felicis 领投的 750 万美元种子轮,做的是让智能体能像查数据库一样查 PDF 这类文档。用视觉加双流模型把 messy 文档转成 LLM 能推理的结构。做企业智能体、RAG 或者文档处理的开发者值得看看这个方向。
文档处理初创公司 Unsiloed 宣布完成 750 万美元种子轮融资,由 Felicis 领投。公司的核心判断是:金融、法律、医疗等行业以文档而非数据库为核心数据载体,AI 智能体需要像软件查询数据表一样查询这些文档。
技术上,Unsiloed 使用计算机视觉与双流(dual-stream)模型,把复杂的多模态文档转换成 LLM 和智能体可理解、可推理的格式,构建一层"可计算"的文档基础设施。团队汇集了来自 Google DeepMind、Cognition 和量化交易公司的机器学习研究者与工程师。
随着智能体处理和写入的文档数量预计超过人类,这层"文档即数据表"的能力可能成为企业落地智能体的关键依赖,类似于数据库之于传统软件。
We need good workspace and document infrastructure for agents. Finance, law, and healthcare run on documents. Agents need to query those documents the way software queries tables. @UnsiloedHQ is building that layer with computer vision and dual-stream models. Aman @aman_unsiloed We’ve raised a $7.5M seed round led by Felicis so AI can read documents as easily as it reads databases. Finance, law and healthcare run on documents, and not databases like any other industry. Soon AI agents will read and write more documents than humans, and they’ll need to query them the way software queries tables. We’re building the computable layer that makes this possible. To do this at scale, we've brought together ML researchers and engineers from Google DeepMind, Cognition, and quant trading firms. We use computer vision and dual-stream models to turn complex multimodal documents into formats LLMs and AI agents can understand and reason over. If your team wants to turn messy documents into reliable, AI-ready data, book a demo: unsiloed.ai/book-demo
This report is categorized under AITOP's "Industry" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Unsiloed, Felicis, agents, RAG.
Source attribution: curated from elvis (@omarsar0).