Project Description

authorDOCS is part of the author product suite by software developer McCarthyFinch/Onit. It’s an advanced legal AI Word Add-in that reads, writes and reasons like a lawyer.

Industry: Legal Software Development
Product team:  Myself on UX/UI + Graphic Design, 1 x Legal Tech, 1 x Product Owner, 1x Product Designer

What was developed

authorDOCS is a Microsoft Word Add-in that was developed to assist lawyers with reading legal contracts. Allowing lawyers to quickly and efficiently identify key commercial issues, search for clauses and legal details and easily draft from their Clause Library.

Over the course of the app’s development, I was responsible in tandem with our product team for identifying key user concerns, workflows, and personas. I was also responsible for wireframing, prototyping, user testing, and taking the app to the final product. Inclusive of this was the development of a full support portal with documentation and user tutorials.

The problem being solved

In-house legal teams and law firms face increasing pressure to take on more work while reducing legal spending. A big part of this is reducing financial risk across low-end contracts that never even make it to the legal team’s desk and increasing productivity and efficiency around contract reviews that are on the legal team’s agenda.

In-house and legal counsel usually have a ‘playbook’ of legal issues they look for in particular legal documents. If shared across a team these playbooks usually reside in spreadsheets, word documents, emails or worst-case scenario in the lawyer’s head.

Traditional methods of reviewing legal documents involve having the document open on the screen, with a second copy printed on paper and a copy of the playbook close by. Highlighter in hand, the lawyer will then laboriously read through the contract highlighting sections of concern.

Traditional processes are slow and cautious. Our challenge was to simplify the document review process in a way that didn’t ask users to change their usual workflow. Allowed them and their team to access their playbook within Word. And reduced workload while engaging trust in the product’s legal accuracy.

UX research + artifacts

UX was an extremely important part of the development process in order to ensure adoption of the product.

To aid this the product team and I:

  • Interviewed lawyers across firms and in-house to understand common practices and workflows.
  • Developed user personas and use cases
  • Performed competitive analysis of other products in the market.
  • User tested and iterated with clickable prototypes developed in InVision.

As the product went live we performed:

  • User testing
  • User interviews
  • Journey mapping
  • Studies to gauge the effectiveness of time saved and productivity increases
  • Implemented iterative improvements and updates to the product over time.

Designing for trust

In the legal industry adoption of technology has been slow. The legal ramifications of providing incorrect advice are huge. Trust thresholds that legal technology will provide the correct advice, in an open and easy to explain fashion is low.

This means that any technology needs to be an open box with easy to explain reasoning. It also means that most users do not have a high comfort level with software usage.

With authorDOCS we allowed legal teams to build the rules for their document reviews in an online console. Allowing them full control over what was looked for and why, and what advice was offered in any type of document review.

We also worked to make AI corrections simple and easy to perform. Mindful that incorrectly identified or missing document content must be as easy to correct as tagging a friend in Facebook. Anything more than one or two clicks to correct, removes user willingness to participate, and negatively impacts the user’s perception of the product’s accuracy.

Follow Up Study

We performed a number of follow-up studies to confirm ease of use and productivity gains. In our final study, six lawyers were asked to install, learn and use authorDOCS, then immediately perform day-to-day activities, such as compliance checking, standard reviews, and contract drafting. While a control team was asked to perform the same tasks using traditional methods. The participants increased output by 50.1% and achieved a 33% efficiency gain. 

Conclusion

In conclusion, we identified that authorDOCS is a tool for proficient mid and senior-level lawyers and business users. However, we found we had low adoption with more junior legal users and less experienced business users. This lead to the development of an automated review product called authorAPPROVE for business users. And the development of a new product offering called Precedent ReviewAI that helps legal users build out checklists with advice for teams of varying skill range.