What is FormX.ai?

FormX.ai is an AI-powered platform designed to automate data extraction and processing from a wide range of documents. It offers intelligent document processing, optical character recognition, and streamlined workflows to enhance business efficiency.

The platform utilizes advanced AI, including LLM technology, to improve data extraction accuracy. FormX.ai allows users to switch between vision and LLM models, features guardrails for model stability, provides optimized prompt engineering and supports fine-tuning of LLMs using real world feedback, and allows to mix multiple models for different document types.

Features

Intelligent Document Processing: Automate data extraction from any document.
Optical Character Recognition: Unlock the power of your PDFs with text extraction.
Custom Builders: Create custom extractors to fit specific document needs.
API Integration: Seamlessly connect FormX.ai to existing systems.
Production-Ready Data with LLMs: Guardrails ensure model stability and prevent hallucinations in production environments.
Optimized Prompt Engineering: Continuously improve accuracy with new prompting techniques and input data preprocessing.
Fine-Tune LLMs with Production Data: Continuously fine-tune LLMs using real-world feedback.

Use Cases

Streamline finance operations
Enhance HR operations
Drive operational excellence in retail
Simplify legal and business documentation
Elevate customer service

FAQs

What does "100 free pages" mean?

All document extractions via our web portal or through APIs are counted as 1 API call. On the free plan, your first 100 calls are on us for you to try out FormX.ai and feel free to contact us if you need help.
Do you save or encrypt any uploaded document?

We only save the master document uploaded to our web portal, or the documents you uploaded for training a custom models. Any images uploaded via API or web portal test are in-memory only and disposed once extraction is done. We will not use your document for optimizing our AI models or any other purposes unless you request us to do so.All API calls are encrypted with HTTPS.
Do you offer volume discount or private cloud deployment?

Yes, we work with enterprises to customize the plan that suits their needs. Please contact us!
What is the accuracy for receipt extractions?

Accuracy rate depends on a lot of factors, and it also depends on how accuracy are defined.As a reference, most of our previous clients would have at least 70% of accuracy by fields.If we limit to only images with good quality (no blur, no lighting problems), from our client’s feedback, general fields such as date, time & amount can have accuracies over 90%.You can contact us with around 100 receipts as sample, and we will share an accuracy report with you.
What are the latency for receipt processing?

Usually it is 4 - 8 seconds, excluding the image uploading time. (It is not a SLA commitment)Image uploading time will depend on the image file size and network speed, which we have no control on. We suggest you to resize the images to a smaller one to reduce the uploading time.If you need a better latency or a SLA commitment, please contact us for an Enterprise plan.