Industry

Unsiloed AI 融资 750 万美元,让 PDF 文档可被 AI 智能体查询

Why we picked it

一家只有 7 人的公司拿下了 Felicis 领投的 750 万美元种子轮,做的就是让智能体能可靠地读 PDF。双流视觉模型加逐字段溯源,还能完全离线部署,比一般纯云方案更适合金融和法律这种不能出错的场景。做文档处理或智能体落地的开发者值得看看它的技术拆解。

Unsiloed AI 是一家 7 人规模的初创公司,完成了由 Felicis 领投的 750 万美元种子轮融资,目标是把金融、法律、医疗行业中被锁在 PDF、扫描件和表格里的文档变成 AI 智能体可查询的数据。

Body

技术上,Unsiloed 采用双流视觉模型并行读取文档的内容与版式,配合热图分块机制,对图表、数字和表格投入更多算力,因为 LLM 是概率性读取,一个表格单元格误读就可能污染整个下游分析。每个提取出的字段都能回链到原页面上的具体位置,便于溯源核验。

此外系统支持在客户自有服务器上以 air-gapped 隔离方式部署,这对数据敏感的法律和医疗机构是关键卖点。同赛道竞品多依赖云端 API,本地化部署加逐字段溯源是它差异化的切入角度。

Original · rohanpaul_ai

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.

Industry Coordinates & Source Verification

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 and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Unsiloed AI, Felicis, agents, RAG.

Source attribution: curated from rohanpaul_ai (@rohanpaul_ai).