Unsiloed AI raised a $7.5 million seed round led by Felicis, with Y Combinator, Orange Collective, Uncorrelated Ventures and two angel investors participating. Its software converts complex documents, including tables, charts and intricate layouts, into structured data for AI agents while indicating where each extracted item came from, according to the company. Unsiloed also reported customer use in finance, legal services, healthcare and voice-agent development.
What problem it solves
Organizations need to aggregate, store, and query logs without operating a complex full-text indexing system. Loki addresses this with compressed, unstructured logs and metadata-based indexing using labels that can also be used to switch between metrics and logs.
Key features
Label-based log indexing — Loki stores compressed log content and indexes labels associated with eac…
What problem it solves
Website owners and SEO teams need to identify technical, content, structured-data, AI-search, local, e-commerce, and international SEO issues and turn the findings into an actionable plan. Audits must also explain why each issue matters and how to verify that a fix worked.
Key features
Parallel website audits — Specialist agents audit technical SEO, content, schema, speed, A…
What problem it solves
Teams building retrieval-augmented AI systems need to extract useful knowledge from complex, heterogeneous documents and ground generated answers in traceable evidence. They also need an orchestrated workflow that can combine document understanding, chunking, retrieval, reasoning, and citations.
Key features
Deep document understanding — Extract knowledge from unstructured d…