Unsiloed AI has raised $7.5 million in seed funding led by Felicis to make business documents easier for AI systems to understand. The round also saw participation from Y Combinator, Orange Collective and Uncorrelated Ventures, along with angel investors Aarthi Ramamurthy and Beth Turner.
Unsiloed aims to address a common problem businesses encounter when using AI: AI systems often struggle to interpret business documents containing tables, charts and complex layouts. The company tackles this challenge with software that breaks down complex documents, extracts information from tables, charts and other elements, and converts it into structured data that AI agents can use. The technology also traces extracted information back to its source in the original document, allowing users to verify the results.
READ: Former TikTok employees launch AI app to help users pose for better photos (September 15, 2026)
“The problem with LLMs is they’re inherently probabilistic,” said Unsiloed co-founder and CEO Aman Mishra (pictured above, right) in an interview. “There is going to be some deviation induced. There is going to be some hallucination involved, and that has a massive negative impact downstream.”
Mishra co-founded Unsiloed with Adnan Abbas, his former classmate at the Indian Institute of Technology (IIT) Kharagpur. The two joined Y Combinator’s Fall 2025 batch after spending time developing the technology.
Mishra told TechCrunch that Unsiloed is already working with customers in finance, legal services and healthcare. One bank is using its technology to process documents, while a law firm has deployed it on its own servers to handle contracts and archived case files, he said, without identifying either customer. Mishra also named voice AI startup Bolna AI as a customer, saying it uses Unsiloed to ingest knowledge bases for building voice agents.
Mishra told TechCrunch that Unsiloed’s competitive advantage lies in how it processes complex documents. The company uses what it calls “dual-stream” vision models, which process text and image data separately, along with a technique called “heat map-based chunking” to identify the most important parts of a document.
“In one of the streams you have the text tokens, in the other stream you have the exact image tokens,” Mishra said. “This is something that we have spent a lot of time architecting.”
Unsiloed’s technology directs more computing power toward areas such as figures, numbers and charts. The startup also uses a specialized decoder that accounts for industry-specific terminology, helping it distinguish between terms that can have different meanings in different business contexts.
READ: Former TikTok employees launch AI app to help users pose for better photos (September 15, 2026)
Mishra pointed to a test involving 542 financial documents supplied by an enterprise customer. Unsiloed achieved 99.78% accuracy across roughly 84,000 extracted data points, according to a technical brief shared by the startup. The test compared Unsiloed with major AI models, Microsoft’s Azure Document Intelligence and the customer’s in-house extraction tool. However, the results have not been independently verified.
Mishra said Unsiloed’s pricing starts at one cent per page. He added that the startup’s approach helps keep costs down by directing computing power toward the parts of a document that require the most attention, rather than processing every section in the same way.


