llm-extraction
(2)
Sensible
Sensible is a developer-first platform that turns any document - PDFs, scans, emails, images - into structured, verifiable JSON. It pairs LLM-based extraction with deterministic, layout-based rules written in its own configuration language, SenseML, and ships 150+ prebuilt parsers plus confidence scores, source coordinates, and human-review workflows. Founded in 2020 and backed by Craft Ventures, Sensible is used by companies across insurance, proptech, financial services, logistics, and healthcare to automate document-heavy operations.
Jason Auh
Jason Auh is Head of Sales and Customer Success at Sensible, the San Francisco developer platform that turns messy documents into structured, schema-validated data through its SenseML configuration language. A Dartmouth graduate who came up through enterprise sales at NetBase Quid, Jason sits at the seam between the engineering that builds Sensible and the customers who bet their workflows on it - and he writes candidly about where document AI actually breaks in production, not just in the demo.