Legal Document Drafting

New document drafting feature for SimpleLegal using generative AI

Role: UX/UI Designer | Year: 2023


In today's fast-paced legal world, time is of the essence. Lawyers and legal professionals are constantly under pressure to deliver high-quality written content quickly and efficiently. The goal of this project is to empower in-house attorneys to draft, brainstorm, strategize, and generate content for any type of legal document more efficiently.

The Problem:
1. Time-Consuming and Error-Prone Process:Traditional legal document drafting involves extensive cutting, pasting, checking, and updating from existing documents. This process is not only time-consuming but also prone to errors
2. Tedious Proofreading: Lawyers often spend a significant amount of time proofreading documents to ensure accuracy. Despite careful checks, there's no guarantee that errors won't slip through, leading to potential legal and financial consequences
3. Risk of Errors: A Thomson Reuters study highlights that manual drafting is associated with a higher risk of errors, which can be costly and damaging to a lawyer's reputation and client trust

The Goal:
To introduce a document drafting capability that utilizes generative AI in the application. Generative AI in legal document drafting refers to the application of advanced AI technologies, such as GPT (Generative Pre-Trained Transformer) models, to create, edit, and review legal documents. This will assist with:
1. Time Efficiency: Generative AI significantly reduces the time spent on drafting documents. For instance, AI-powered tools can produce accurate first drafts quickly, allowing lawyers to focus more on strategic activities rather than on time-consuming drafting tasks
2. Reduced Risk of Errors: By automating the drafting process, generative AI minimizes the risk of human errors, such as incorrect details or formatting issues, thereby enhancing the overall accuracy and reliability of documents
3. Enhanced Productivity: Lawyers using generative AI report increased efficiency in reviewing documents and mitigating the risk of errors. This technology enables them to use their time more effectively on high-value activities, rather than on repetitive and mundane tasks.

Responsive image


We conducted a survey through WalkMe and collected responses from Jan 26 - Feb 20. The purpose of the research is to:

survey design

Our results showed that the majority of respondants do not use a document creation tool as many are wary of the high cost of such a tool. We wanted to explore how we could offer a document creation tool inside of SimpleLegal, thus allowing our users to draft, brainstorm, strategize, and generate content for any type of legal document more efficiently.

survey design

Ideate & Define

This was the first generative AI feature for the product, and I took on the sole design responsibility for this project. I researched several different applications that had document generation capabilities, and brainstormed on ideas to implement this feature into the application.

One of the biggest challenges for me was testing out the prompts and designing the prompt inputs so that we could get closer to accurate and relevant results. We wanted flexibility with the prompts so that users can create first drafts of various legal documents, including contracts, memos, and legal briefs, based on learned patterns and data from existing content, but also give enough context to receive accurate results. After numerous testing, my project manager and I decided to provide these fields and supply the final prompt to generative AI:


I worked on several designs for giving the prompts and previewing the document, drawing inspiration from other applications and our other product lines. My initial design populated a modal, where users could input their prompts and select relevant fields for their draft. However, to avoid excess scroll and to maintain context for users, I landed on a new design. This design borrowed an existing component in the application in which users are already familiar with. In addition, this solves the problem of having enough real estate, and provides the user with additional context for what they are doing.