Sensible.so
LLM-first document processing platform with visual editing, multimodal extraction, and email-driven workflows for finance, legal, and real estate applications.
Overview
Sensible provides a document processing API combining LLM parsing with visual layout rules for extracting data from PDFs, emails, and spreadsheets. Founded in San Francisco in 2020 with $8M in funding led by Craft Ventures, the company has evolved from a developer-focused extraction tool into a comprehensive LLM-first platform.
In 2026, Sensible launched Visual Document Extraction with natural language editing, allowing users to create parsers using plain English descriptions like "capture middle names." The platform introduced email-driven processing workflows that process attachments by forwarding emails to Sensible, and a Multimodal Engine for extracting data from embedded images, charts, and handwriting.
The company's hybrid approach combines traditional layout-based methods with LLM capabilities, targeting a PDF data extraction market projected to reach $2.0 billion in 2025 at 13.6% CAGR. Third-party integrations including a Raycast extension and Zapier connector indicate growing developer ecosystem adoption.
Key Features
- Visual Document Extraction: Automatic LLM-powered parser creation with natural language editing and visual cards interface
- Multimodal Engine: LLM-powered extraction from images, charts, graphs, and handwriting embedded in documents
- Email Data Extraction: Email-driven document processing with attachment handling via forwarding workflows
- Agentic AI Workflows: Enhanced document extraction capabilities with agentic LLM workflows for complex processing
- Batch Extract: Process up to 5,000 documents concurrently through bulk upload capabilities
- Pre-Configured Parsers: 150+ ready-to-use parsers for common document types
- Human Review: Manual oversight feature for document extraction validation
- Version Control: Document parser versioning for configuration management
Use Cases
Financial Document Processing
Fintech companies integrate Sensible's API to extract data from bank statements, tax forms, and financial reports. The Visual Document Extraction feature allows finance teams to create custom parsers using natural language, while the Multimodal Engine processes embedded charts and signatures in financial documents.
Legal Document Analysis
Law firms use Sensible's email-driven processing to automatically extract data from contract attachments and legal filings. The platform's agentic AI workflows handle complex legal document structures, with HIPAA compliance for sensitive legal data.
Real Estate Automation
Real estate applications leverage Batch Extract to process thousands of property documents concurrently. The Zapier integration enables automated workflows connecting extracted property data to Salesforce and databases.
Technical Specifications
| Feature | Specification |
|---|---|
| Core Products | Extract API, Classification API, Visual Editor |
| Parsing Methods | LLM parsing, visual layout rules, multimodal extraction |
| Document Types | PDF, email, Excel, TIFF, JPEG, PNG, Word |
| LLM Integration | gpt-3.5-turbo-0613, agentic workflows |
| Batch Processing | Up to 5,000 documents concurrently |
| SDKs | JavaScript, Python, Node SDK |
| Integration | REST API, webhooks, Zapier connector |
| Infrastructure | AWS, multi-region deployment |
| Compliance | SOC 2, HIPAA |
| Target Verticals | Finance, legal, real estate |
Resources
Company Information
Headquarters: San Francisco, California, United States
Founded: 2020
Employees: 11
Funding: $8M (Seed round led by Craft Ventures, with Engineering Capital and Clocktower Technology Ventures)