The Challenge: Fund legal teams spend significant time manually comparing and noting differences in clauses negotiated by individual investors using side letters.

Solution: Develop a tool that automates clause labelling, identifies common variations, and enables easy comparison of clause changes.

‍

Understanding the Pain Points

Through extensive research, the following user pain points were identified:

1. Time-Consuming Comparison: Legal professionals spend excessive hours comparing clauses and tracking changes, leading to high legal fees.
2. Manual Reporting: Creating comparison reports in different formats (CSV, Word) is a labour-intensive task that increases the risk of errors.
3. Redline Analysis: Users struggle to visualize added or removed content in clauses, resorting to manual redlining in applications like Microsoft Word.
4. Standardization: Users need a suggested standard clause iteration based on frequency but lack an automated method to determine it.

Design Exploration

To address these pain points, a series of "How Might We" questions were developed:

1. How might we enhance contract sorting and navigation?
2. How might we differentiate contracts more effectively?
3. How might we simplify contract search and retrieval?

Solution Approach

Comparing existing tools and services, we identified that the core functionality of scanning text/documents for differences or similarities was already present. However, many tools were limited to single-document comparisons. Our solution aimed to offer multiple-text/string/document comparisons, delivering enhanced efficiency.

Design Implementation

1. User Interface (UI): A clean and intuitive dashboard was designed to allow users to upload documents and initiate comparison tasks easily.
2. Automated Labeling: Utilizing machine learning, key clauses within side letters were automatically labelled, saving time on manual tagging.
3. Visual Comparison: A redline analysis feature was implemented, enabling users to visualize changes between iterations, eliminating the need for manual redlining.
4. Frequency Analysis: A list of each clause iteration and its occurrence frequency was provided. The most common iteration was highlighted as a suggested standard.

Impact

The solution drastically improved the efficiency of legal teams:

• Time Savings: The automated process reduced comparison time by up to 80%, leading to significant cost savings for clients.
• Error Reduction: Manual errors associated with clause comparison were minimized, enhancing accuracy.
• Enhanced Reporting: Users could generate comparison reports in various formats swiftly, enhancing productivity.

‍

Conclusion

Robin AI's product successfully tackled the challenge of simplifying clause comparison for legal professionals. By leveraging machine learning and an intuitive user interface, the tool enabled users to automate clause labelling, visualize changes, and determine suggested standards based on frequency. The solution not only streamlined the legal workflow but also contributed to cost savings and improved accuracy. As a product designer, I am proud to have been a part of this project that enhances efficiency within the legal domain through innovative design and technology integration.

‍