In the last month, Sensible updated an Anthropic model version for LLM-based methods, released UX improvements for authoring SenseML, and switched our default OCR provider for scans and images from Microsoft to Amazon.
In the last month, Sensible released advanced configuration options for layout-based extraction methods and added support for extracting from XLSM files.
In the last month, Sensible introduced a new visual editor that displays LLM-based extraction configurations as simple cards instead of as JSON code. A key usability feature is that new users can now modify the extraction configurations using plain English descriptions like "update the field that extracts the customer's phone number to strip dashes and parentheses" rather than writing JSON syntax.
In the last month, Sensible significantly improved LLM accuracy for long documents with a new document-outlining feature and added several advanced configuration options for layout-based methods.
In the last month, Sensible released several major new features. We introduced email-driven document extraction for automated processing of email attachments, significantly expanded our auto-generated extraction schemas to handle larger and more complex documents, and added new troubleshooting capabilities for multimodal extractions. We also added several advanced configuration options and deprecated some older LLM configuration options.
In the last month, Sensible removed a visual tool for authoring large language model (LLM) prompts. Stay tuned for new authoring features. We added advanced functionality for layout-based methods, enabled stricter criteria for LLM output, and introduced new features for advanced output schema manipulation.
In the last month, Sensible released features for advanced output schema manipulation and types configuration.
In the last month, we released UX improvements for the Sensible app and advanced output schema manipulation features.
In the last month, Sensible released a powerful new feature for conditionally executing extraction fields. For very large spreadsheets, Sensible introduced a speedy cell-extraction method. For research papers and other multi-column document layouts, Sensible introduced a new Multicolumn preprocessor. Sensible also released a new confidence signal, inferred_answer, for qualifying LLM accuracy; enabled combining single-document and portfolio extractions into a single Excel file, and released advanced output schema manipulation features.
In the last month, Sensible released support for chaining large language model (LLM) prompts for the List method, Anthropic support for the List and NLP Table methods, UX improvements to the Sensible app, configurability for classifying documents by type, and advanced output schema manipulation features.
