[Improved] Custom date range filter on the usage pageThe usage page now lets you filter by a custom date range instead of a fixed year, giving more precise control over billing and usage reports.[Fixed] Reverting to the original value marks fields as verifiedEditing a field value back to its originally extracted value now correctly marks it as human-verified rather than human-edited.
[Improved] Better OCR accuracyUpgraded text recognition with better support for Latin languages.[Improved] LLM cost tracking in billingBilling transactions now include per-extraction LLM token counts and costs for full cost transparency.[Improved] More accurate table extractionImproved accuracy when extracting data from tables with closely spaced rows or surrounding text.[Improved] Faster processing during peak usageExtraction now scales to handle high volumes, reducing wait times during busy periods.[New] Sample workflows on new accountsNew accounts are now prepopulated with sample workflows and documents for a guided onboarding experience.[Fixed] Smart-lookup crash on empty corpusSmart lookup no longer crashes when the search corpus is empty.[Improved] Faster extraction callbacks and field-list endpointsPerformance improvements on extraction callbacks and field-list endpoints.[Fixed] Readable file download filenamesFile download filenames are now readable by the frontend.
[Improved] Visual grounding 2.0Completely revamped evidence highlighting with block-level and element-level precision, making it easier to trace extracted values back to their exact location in the source document.[New] Billing dashboardNew usage dashboard with remaining credits, weekly summaries, per-workflow usage breakdown, and CSV export.[Improved] Advanced document layout analysis enabled in productionThe advanced document segmentation pipeline is now enabled in production for improved table and section detection.[Fixed] Bounding-box highlights no longer stuck after navigating fieldsHighlights are now cleared correctly when you move between fields.[Fixed] Confidence calibrationFixed calibration configuration for confidence scoring.
[New] Redesigned home pageA personalized home with recent workflows, at-a-glance file-status indicators, and a streamlined workflow creation experience with templates.[New] Redesigned schema builderA new two-step Define & Refine flow with AI-powered field suggestions, inline file previews, and drag-and-drop uploads.[Improved] Faster page rotationAbout 2× faster page-orientation detection per page.[Improved] More reliable AI field suggestionsField suggestions now use an upgraded model for higher reliability.[Fixed] Smart-lookup settings saved on publishSmart-lookup settings are now correctly saved when publishing a workflow version.[Fixed] Workflow studio sidebar overflowFixed sidebar overflow in the workflow studio.
[Improved] New dashboard visual designRefreshed visual design across the platform with updated components, colors, and layout.[Improved] Faster, more reliable evidence highlightingEvidence highlighting now uses an event-driven architecture, making interactions faster and more reliable across all views.[Improved] Files and organization logos served securely through the backendFiles and organization logos are now served securely through the backend, improving security and simplifying local development.[New] AI workflow-name suggestionsNew AI-powered workflow-name suggestions based on your description and uploaded files.[Improved] File status counts in workflow listingsWorkflow listings now show at-a-glance counts of files by processing status.[Fixed] Document-element classificationFixed a classification regression that could cause incorrect layout detection in some documents.
[New] Smart LookupNew feature to enrich extracted data with external reference files using AI-powered matching.[Improved] Field source trackingFields now track their source (extraction vs. smart lookup) for better traceability.[Fixed] Manual field creation processingField data processing now correctly handles manually created fields.
