> For the complete documentation index, see [llms.txt](https://docs.taskade.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.taskade.com/changelog/changelog-2026/july-2026/july-25-2026.md).

# 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.

{% hint style="info" %}
**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](https://www.taskade.com/changelog); for release newsletters see [taskade.com/blog/updates](https://www.taskade.com/blog/updates).
{% endhint %}

## 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](/automations/automation/actions.md).

***

### 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](/automations/automation/workflow-generator.md).