Genie Code for intelligent document processing

Genie Code builds end-to-end document processing pipelines that parse, classify, extract and validate unstructured files such as PDFs, contracts and invoices, using ai_parse_document, ai_classify and ai_extract. Given labeled data, it scores extraction quality field by field and iterates on the pipeline, re-running the evaluation after each accepted fix.

Statuses and dates come from public Databricks sources only. We do not see the private roadmap Databricks shares with customers. If something looks wrong, report a correction.