July 25, 2026

AI vision OCR fallback for scanned and image-only documents, and EVE-built automation flows now reliably fill their structured-output fields.

Developer highlights. This section tracks API, MCP, SDK, automation, and Taskade Genesis platform changes for developers. For the full product changelog see taskade.com/changelog; for release newsletters see taskade.com/blog/updates.

What's New:

Document OCR Fallback for Scanned & Image-Only Files

Convert File to Text and Genesis document extraction now fall back to AI vision OCR when a document has no embedded text layer — scanned PDFs, image-only PDFs, and photo formats like HEIC now extract text instead of failing. The fallback only engages when standard text extraction finds nothing, bills a flat AI-credit fee per document, and respects your plan's AI usage limits; documents with a normal text layer are processed exactly as before. See Automation Actions.

---

Fix: EVE-Built Flows Fill Every Field They Promise

Automation flows authored by Taskade EVE that use AI structured-output steps (reports, analyses, custom-field fills) now reliably fill every field they promise — previously, some generated flows could run successfully yet leave their target fields empty. See the Workflow Generator.