DocCenter Design Considerations

Every DocCenter project involves balancing three factors: extraction accuracy, processing speed, and AI action consumption. Understanding how your DocCenter model configuration choices affect each factor helps you design a solution that meets your business requirements while staying within your AI action allocation.

AI actions in DocCenter

AI actions are the unit of measurement for AI-powered feature usage in Appian. Each time DocCenter processes a document—whether classifying, extracting, or reviewing—it consumes AI actions. Your environment receives an allocation of AI actions based on your Appian license tier, and you can purchase additional bundles as needed.

DocCenter usage groups for AI action attribution

A usage group is an Appian group that DocCenter attaches to its AI calls so that the resulting AI action consumption is recorded against that group. Usage groups change how AI action consumption is reported, not how much a model consumes. To reduce consumption rather than attribute it, see Factors that affect DocCenter AI action consumption.

Organizations that run DocCenter across several independent business units—for example, separate claims, underwriting, and compliance teams—can use usage groups for cost allocation, attributing AI action consumption to the team that generated it.

DocCenter attaches two kinds of usage groups:

• AIA All Users: DocCenter adds this group to every AI call automatically, which separates DocCenter consumption from other AI activity in your environment.
• Groups you specify: A calling process model passes these groups for a single execution, alongside AIA All Users rather than replacing it. Requires DocCenter 4.4 with Appian 26.6, and the groups must exist before you configure the process model.

Usage groups govern reporting only. Usage groups do not:

• Cap or throttle consumption: Usage groups record consumption after processing completes. Usage groups do not block processing when a business unit approaches a budget.
• Support agentic capabilities: Verification models and AI-Suggested Improvements do not support usage groups in DocCenter 4.4, because both run through the Appian agent engine.

Where DocCenter records usage groups

DocCenter records usage groups in two locations:

Location	What it shows
The AI Usage tab of an extraction or classification instance	Usage groups as tags beside the name of each AI call, such as Text Bounding Boxes or Extraction.
The artificial_intelligence.csv AI audit log	Usage groups for each AI call, for reporting outside DocCenter.

Factors that affect DocCenter AI action consumption

Not all DocCenter model configurations consume AI actions equally. The following table summarizes the configurations that increase consumption and when to use them:

Configuration	Consumption impact	When to use
Advanced Layout	High—scales with page count, even blank pages.	As a last resort when Visual extraction alone does not achieve desired accuracy. See Choose between Visual extraction and Advanced Layout.
Mixed Vision + Text fields	High—makes multiple AI calls with the same document, doubling consumption.	Avoid this configuration. If your document has even one visual field, use Vision for all fields. If no fields need visual processing, use all text fields.
AI-Suggested Improvements	High—runs an AI agent that makes multiple calls per instance.	When you need AI-generated suggestions for improving model accuracy and accept the additional AI action cost.
AI Review	Moderate—runs a second model pass on every instance.	When straight-through processing (STP) is desired and you want automated verification before reconciliation.
Visual extraction	Moderate—processes page images in addition to text. Recommended configuration for documents with any visual elements.	For fields containing visual elements (checkboxes, signatures) or where spatial layout is important (complex tables, nonstandard layouts). Use Visual for all fields if any field requires it.
Bounding boxes	Low—makes an additional AI call to merge bounding box coordinates with extracted text.	When you need to highlight extracted values in the original document for reconciliation or audit purposes.
Field instructions	Low—adds context to the prompt for each field.	When the default extraction is not accurate enough and additional context improves results. Add only where they measurably help.
Describe Validations	Low—additional AI call per validation.	When you need AI-generated validation conditions rather than rule-based validations.
Text extraction	Low—processes only the text layer of each page.	For documents where all fields are standard text values (names, dates, amounts) and no visual elements need interpretation. This is the lowest-consumption configuration and the recommended starting point.
Number of fields	Cumulative—each field adds to the prompt size and response.	Extract only the fields your business process needs. Remove unused fields from the model.
Document page count	Cumulative—more pages means more content to process.	Use sections to limit what the model reads for long documents.

Balance accuracy, speed, and consumption in DocCenter

Most teams prioritize accuracy first, then speed, then consumption. However, high consumption can become a blocker if it exhausts your AI action allocation before your DocCenter project delivers value. Discuss these tradeoffs with stakeholders early:

• Accuracy vs. consumption: Features like Advanced Layout improve accuracy but increase consumption. Start with the simplest DocCenter configuration that meets your accuracy target and enable additional features incrementally.
• Speed vs. accuracy: Fast large language models (LLMs) such as Haiku and Nova 2 Lite process documents quickly and consume fewer actions per document, but may produce lower accuracy on complex documents. Reasoning LLMs such as Sonnet provide higher accuracy for complex extractions but take longer and may consume more actions.
• Volume vs. cost: High-volume processing magnifies per-document consumption. A configuration that adds a small cost per document can become significant at scale. Model the total monthly consumption before deploying DocCenter to production.

Choose between Visual extraction and Advanced Layout

Both Visual extraction and Advanced Layout improve accuracy for complex documents in DocCenter, but they work differently and have different cost profiles. Use the following guidance to choose the right option for your extraction model.

Start with Visual extraction

Enable Visual at the field level for any field that involves:

• Checkboxes or radio buttons: Fields that require interpreting graphical selection indicators.
• Signatures or stamps: Fields that require interpreting handwritten or image-based content.
• Complex tables: Tables with merged cells or irregular column structures.
• Nonstandard layouts: Fields where spatial position on the page determines meaning.

Visual extraction uses the multimodal capabilities of the large language model (LLM) to interpret page images alongside text. Visual extraction supports up to 500 pages (with reconciliation) or 1,000 pages (without reconciliation) with the latest models (Sonnet 4+, Nova 2 Lite) and provides strong accuracy for most visual elements at a moderate consumption cost.

Use Advanced Layout only as a last resort

Enable Advanced Layout at the model level only when:

• Visual extraction is insufficient: Visual extraction does not achieve your desired accuracy after prompt iteration.
• Prompt refinements are exhausted: You have tested prompt refinements and LLM selection changes without sufficient improvement.
• Higher consumption is acceptable: You accept the higher consumption as a necessary tradeoff for additional accuracy.

Advanced Layout combines Advanced IDP and generative AI processing, which significantly increases consumption—scaling directly with the number of pages in the document, including blank pages. Because of this cost profile, treat Advanced Layout as a last resort rather than a default configuration.

Manage DocCenter AI action consumption

The following practices help you get the best extraction accuracy within your AI action budget:

• Use sections for long documents: Sections limit what the model processes, reducing both consumption and processing time while improving accuracy by focusing the LLM on relevant content.
• Choose the right LLM for the job: Use fast large language models (LLMs) such as Haiku for high-volume, structured documents. Reserve reasoning LLMs such as Sonnet for complex documents that require chain-of-thought reasoning. Review additional guidance on selecting the right LLM for your use case.
• Add field instructions only where they help: Each instruction adds to the prompt. Test with and without instructions to confirm they measurably improve accuracy before keeping them.
• Remove unused fields: Every field in the extraction model adds to consumption. If a field is not used downstream, remove it from the model.
• Enable AI Review for straight-through processing: AI Review adds a second model pass on every instance. Enable AI Review when you want automated verification to increase confidence before reconciliation and are targeting straight-through processing (STP).
• Test and iterate before scaling: Run test cases on representative documents and monitor accuracy metrics. Achieve your accuracy target in testing before processing production volumes.
• Scope verification test suites to reduce consumption: Creating a verification test case costs nothing extra. AI action consumption increases only when you run a verification test suite, because DocCenter re-runs the agent against every test case in the suite. Run only the subset of test cases relevant to the rules you changed rather than the full test set.
• Monitor consumption per instance: The Instances tab on extraction and classification models shows an Actions column with the AI actions consumed per instance. Use the AI ACTIONS filter to find instances above a specific threshold and investigate whether configuration changes—such as switching from Advanced Layout to Visual extraction—can reduce their cost.
• Monitor consumption over time: Use the DocCenter homepage to track AI action usage. Watch for unexpected spikes after model changes or volume increases. You can also monitor AI actions at an instance level by comparing consumption across different configurations and choosing the configuration that provides the best balance of actions, accuracy, and speed.

Feedback