AI-powered financial contract data processing platform

Bringing AI automation power to everyday work for advanced contract review and process productivity.

Project Type

B2B SaaS Platform,

ML & AI Integrated.

Business Goal

Deliver MVP to 1st users for a long-term contract with Google.

My Contribution

UX research, Prototyping,

UI design,

Design Iteration


Jan 2023 - Jun 2023


Project Brief

Google financial specialists spend much time reviewing contracts and extracting data manually.

Our client is working on a web-based AI-powered document automation product to improve document handling productivity for non-tech background enterprise users, Google Financial Outsourcing team.


Financial Operation Specialist

"I support the finance team by performing clerical duties to review and file reports efficiently and accurately."


Design Scope

How might we build the users’ trust and reduce the friction in AI suggestion and validation user flows?

The more users are hindered by wrong results and frictional experiences at the earlier stage, the less trust they will show for AI tools. Ensuring a smooth experience is the highest priority:

  • Streamline the document review process

  • Reducing the time spent on manual tasks

  • Enhancing the accuracy of entity extraction



We aligned the client team to follow an iterative design process in which designers focus on the users' needs in each phase. The design teams met and aligned with the stakeholders throughout the design process.


User Journey Map

Insight 01


Provide the users with more valid info and help them establish work priorities to increase efficiency.

Insight 02


Need a clearer navigation pattern between a key term checklist, original document and extracted document

Insight 03


Prioritize building user trust to help the user gain usage of the Orby system.



How might we encourage users to finish the training process?
How might we help users build trust in the AI process?

Chatbot UI - AI Training Phase

A chatbot has been designed as an entry point for users to start interacting with Orby during the daily workflow.

How might we streamline the validation flows?

Page Layout - Validation Process

The two-column layout provides more space for contract display and follows the Z-readable pattern for easy entity review.

Navigation - Validation Process

Our aim is to direct the user toward examining the terms attentively using a tabbed filter, thereby enhancing precision.

How to assist users in identifying different tasks when there are lots of files with abundant information?
How can we display as much information as the users need within a regulated area?
How to add tasks that are not recognized by Orby AI?

Suggestion Panel Layout

A chatbot has been designed as an entry point for users to start interacting with Orby during the daily workflow.


Hi-Fi Prototype

01 Orby AI Onboarding

Orby Onboarding helps users minimize their effort of learning how to work with Orby by providing easy tips about key concepts and features.

02 Get started and check work orders

Orby notifies users when new tasks come. The AI suggestion panel helps users prioritize their tasks.

03 Add new tasks

Orby auto-syncs task files and allows users to add new tasks manually.

04 Result validation

Streamlined classifications into "All", "Low confidence", and "Not in doc" to minimize unnecessary data and error frequency. Tabbed filtering supports users precisely verifying terms.

05 Optimize and export tasks

The Orby score increases as the user corrects the terms that establish confidence between users and the Orby. Uses can export the results to other apps.



Domain knowledge is essential to B2B projects

As a designer focusing on productivity, I learned about the financial / contract processing domain. It would make the design process more efficient if we brought this in earlier to align the user's mental model in the early stage.

Define success metrics on the business side

Orby AI is a 2B product serving professional teams. Thinking about the product on the business side would help define success metrics to evaluate design impacts in a more convincing way.



Our AI-integrated service led to an 80%+ reduction in the time per task for contract extraction and processing, resulting in a decrease from 60 min to 5 min per task.

Google confirmed the long-term cooperation on AI automated invoice processing and business data comparison.