DocCenter

About DocCenter

As you see the power of AI in processes involving documents, you may want to know how to expand these capabilities across your organization.

Introducing DocCenter, your comprehensive application for enterprise-grade intelligent document processing. Quickly define your document types or fields to extract in one intuitive workflow. DocCenter is up to the challenge of handling your business's highly complex documents with varied formatting and layouts, resulting in higher classification and extraction accuracy.

Scroll or drag to pan · ⌘+/⌘− to zoom · Esc to close

DocCenter allows users of all technical skill levels to create and refine AI models for both document classification and extraction. It supports versioning of models and has a robust reconciliation and accuracy metrics framework that provides your users the tools they need to take full advantage of advances in AI capabilities.

What's included?

DocCenter provides a comprehensive set of tools to help you easily create, manage, and monitor your classification and extraction AI models. This application includes:

• Classification: Build AI models that automatically classify documents by type, with built-in testing to ensure they meet your requirements.
• Extraction: Quickly create and configure AI models to extract data from complex documents with varied layouts, and test the models to verify they meet your needs.
• Verification: Define rules and verify documents against those rules using an AI-powered agent, connecting classification, extraction, and verification into a unified document processing workflow.
• Monitoring: Monitor the accuracy of your classification and extraction models in development, testing, and production environments. Track AI action usage per model and per instance to stay within any usage limits you're subject to. To attribute AI action consumption to specific business units, pass usage groups when a process model runs a DocCenter model.
• Testing and versioning: Rapidly iterate on classification, extraction, and verification models by testing directly in the app, reconciling results, and viewing metrics on performance. If you see a chance to improve, you can create a new version of the model to further refine the prompt and other model configurations.
• Deployment: Easily deploy your models and configurations to higher environments.

DocCenter is designed to help you get the most out of Appian's generative AI capabilities, with a focus on transparency, monitoring, and continuous improvement. Whether you're extracting data from documents or classifying content, this application provides the tools you need to succeed in one streamlined workflow.

Getting started with extraction

Before you put in the work to create your own extraction process, think about what you want to do. For example:

• What kind of documents will you process?
• Who is responsible for reconciling and correcting results?
• Where do you want to display the data after?

If you want the ability to customize these aspects of the document extraction process, like how the data moves post-extraction or who corrects results, you can build your own document extraction process using the extraction models in DocCenter.

To take advantage of Appian's full-stack automation features, consider pairing your document extraction process with other AI-powered features and robotic process automation (RPA).

Access DocCenter

Customers can get access to DocCenter in a few ways:

• New Appian customers will have DocCenter enabled by default on their Appian environment.
• Existing Appian customers can create a Support case or download DocCenter on MyAppian. On MyAppian, click SUPPORT > DOWNLOADS > SOLUTIONS and search for DocCenter.

Usage limits

DocCenter is powered by Appian's AI features, which are subject to environment's usage of AI actions. Check with your system administrator to understand and anticipate your environment's usage of AI actions.

Version compatibility

Refer to the Support and Release History table to see which versions of DocCenter are supported on your Appian version.

Feedback