Our database captures real-world business entity formation scenarios, starting with a seed scenario provided by a local business. Through conversations with the business owner, a lawyer initiates the legal process, meticulously documenting and taking notes of each step—from initial discussions to formal filings. The process culminates in a finalized agreement document, serving as the definitive legal outcome.
This data collection tool enables us to study not just what decisions are made while drafting by law students, but also how they adapt, iterate, and navigate ambiguity across the full drafting workflow.
Our data collection tool is rooted in a visual, expert-informed task plan that maps out the full legal drafting workflow—from initial client intake to final agreement. 🎯 This task plan supports flexible navigation across subtasks in the data collection tool, while maintaining a clear structure rooted in real-world practice.
The workflow is organized across three levels of detail:
This multi-layered structure allows us to capture the dynamic, non-linear nature of legal work—supporting both detailed analysis and AI tools that align with how real practitioners think and operate.
For example, the entity formation workflow includes five key stages:
Together, these levels form a flexible yet robust blueprint for capturing and analyzing legal workflows in real-world scenarios.
We gathered data from law students working through real-world business formation scenarios—an example is shown below under the 'Human' tab. Using the same task plan, we also had LLMs like DeepSeek R1 and OpenAI O1 generate workflows for these scenarios. Switch to the LLM tab to see a sample output from the O1 model.
We plan to scale up our data collection and develop innovative legal reasoning benchmarks for evaluating long-range, multi-turn, deep legal reasoning tasks. We welcome collaborators, funders, and researchers interested in exploring AI for knowledge intensive tasks, such as legal processing. If you’d like to try our tool or contribute to our dataset, please get in touch! Contact us at dongyeop@umn.edu