I co-lead UX for Appian's intelligent document processing platform -- making it possible for users of all technical backgrounds to build, test, and refine AI models for classifying and extracting data from complex documents.
Role
UX Design Co-Lead
Timeline
Sept 2025 - Present
Team
Product, Engineering, AI
Scope
End-to-end Design
DocCenter is Appian's platform for intelligent document processing. Think of it as the tool that lets organizations teach AI how to read their documents -- classifying them by type and pulling out the data that matters. As one of the two UX leads, my job is making that process feel manageable for everyone, not just ML engineers.
Build AI models that automatically classify documents by type, with built-in testing to ensure accuracy.
Create and configure AI models to extract data from complex documents with varied layouts.
Track accuracy of classification and extraction models across development, testing, and production.
Rapidly iterate on models by testing directly in the app, reconciling results, and viewing performance metrics.
Deep dives into some of my favorite design challenges I tackled and the solutions I crafted for DocCenter.
Classification is usually just one step in a bigger process. After a model classifies a batch of documents, teams often need to kick off something else -- like extracting data from invoices or routing purchase orders to the right department.
Before triggers existed, users had to manually start downstream processes after classification was complete -- or build custom integrations outside of DocCenter to connect the dots. The goal was to give users a simple way to say: "When this classification activity finishes, automatically start this process." No code, no workarounds.
Users can create triggers from the Triggers tab within any classification model. The setup is intentionally minimal -- just three decisions:
Timing
Choose whether the triggered process runs synchronously (waits for it to finish) or asynchronously (kicks it off and moves on).
Process Model
Select the process model to start when the activity completes. This is where users connect classification to their existing workflows.
Activity Type
Choose which classification activity should trigger the process. Currently supports Reconciliation, with more types planned.
One trigger per model
I kept the interaction model simple: one trigger per classification model. If users need to trigger multiple processes, they create a wrapper process model. This avoids complex ordering logic in the UI and keeps the mental model straightforward.
Guardrails for reliability
Triggered processes need to meet specific requirements -- like having the right permissions and a parameterized instance variable. I surfaced these requirements clearly in the UI so users don't hit confusing errors at runtime.
Edit and delete in context
Users can update or remove triggers directly from the Triggers tab without navigating away. Small detail, but it keeps the workflow tight and reduces the chance of accidental misconfiguration.
Since going generally available, DocCenter has seen strong and steady adoption across enterprise customers and government agencies. Here's a snapshot of where things stand:
123
Active customers in production
~20K
Instances run per month
75K+
Documents processed in 2025
1,008
Cumulative installs by Dec 2025
208
Models created (72% extraction, 28% classification)
60K
Documents processed
45 days to 1 day
Reduced audit backlog from 45 days to 1 day for a large mortgage company
75% faster review time
Faster review time on Attending Physician Statements for a large insurance company in North America
95% automation
Of order management automated at a healthcare company
36% reduced time to invoice
Faster invoicing turnaround through automated document processing
I'd love to walk you through how I approached this product and the decisions behind it.
Get in Touch