Unsiloed AI 获 750 万美元融资 让文档可被 AI 查询

原标题:A great launch for the document layer of AI, built for finance, law and healthcare, where the record...
62AI 研判分

7 人初创公司 Unsiloed AI 完成由 Felicis 领投的 750 万美元种子轮融资,目标是构建面向 AI 智能体的“文档可计算层”。其双流视觉模型并行读取文档内容与版面布局,并通过热力图分块把额外算力集中在图表与数字上,每个抽取字段都可回溯到页面原始位置,且支持在客户自有服务器上离线部署。

报道正文

Rohan Paul (@rohanpaul_ai) · 2026-11-18 14

A great launch for the document layer of AI, built for finance, law and healthcare, where the record still lives in PDFs, scans and spreadsheets.

Unsiloed AI, a 7-person startup, raised $7.5M in a Felicis-led seed to make documents queryable for AI agents.

Finance, law and healthcare run on PDFs and scans, which LLMs read probabilistically, so a single misread table cell can poison downstream analysis.

Unsiloed’s dual-stream vision models read content and layout in parallel, while heat-map chunking spends extra compute on figures, numbers and charts.

Each extracted field links back to its spot on the page, and the system can run air-gapped on a customer’s own servers.

↳ 引用 @aman_unsiloed (Aman): 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:

推文配图