AI legal assistant (YC S23)
Sahil Dave
Designed the MVP for an AI-based legal assistant (B2B) for Atla. Helped founders strategies with clarity.
atla uses AI safety techniques to make sense of the dense legal language, serving as a reliable ally in high-stakes legal decision-making. atla searches through millions of legal docs, then uses machine learning to extract key information from each source. This process-based reasoning leads to reliable answers. I worked with the founders to refine their vision into an actionable, iterative product roadmap. Interviewing real users and doing usability testing helped us leapfrog with the iterations. I was able to come up with solutions that'd solve users' problems while keeping the MVP scope small.
Contribution
atla uses AI safety techniques to make sense of the dense legal language, serving as a reliable ally in high-stakes legal decision-making. atla searches through millions of legal docs, then uses machine learning to extract key information from each source. This process-based reasoning leads to reliable answers. I worked with the founders to refine their vision into an actionable, iterative product roadmap. Interviewing real users and doing usability testing helped us leapfrog with the iterations. I was able to come up with solutions that'd solve users' problems while keeping the MVP scope small.
Lawyers can start searching like Google or jump into their autosaved past searches
The "Summary" screen presents the AI-generated answer to the legal question and relevant sources.
Context
The current users, the legal teams at Volkswagen and N26, ask a legal question, and the AI assistant generates a reliable answer alongside the legal sources, documents and court decisions. The tool also lets them ask follow-up questions, and dig deeper to find the 'whole' answer.
The generated summary is always linked to the sources on the right. On hover, the user can copy, view the sources and rate.
A context menu is available when the user selects a part of the text
Dig Deeper
On interviewing the lawyers, the biggest hurdle in adopting the software came to light. Lawyers needed to reduce liability, and a one-shot AI-generated summary did not cut it for them. They needed a way to go deeper into their research and find answers from different angles. After testing a few prototypes, we went with a threaded way of asking for follow-ups - Dig deeper.
The Dig Deeper helps lawyers reduce liability by helping them go further in their research
The questions can be threaded and collapsed. Reducing clutter was a big challenge, solved by adding buttons in the hover state.
Lawyers can also view full sources and jump to highlights relevant to the question
The lawyers can also view full sources and jump to highlights relevant to the question
I always give clear handover documentation to enable smooth development
Outcome
Roman and Maurice did a successful YC launch in July '23 and the MVP is being used by the legal team of N26 and Volkswagen.
Like this project
Posted Dec 1, 2023
Designed the MVP for an AI-based legal assistant (B2B) for Atla. Helped founders strategise with clarity.
Likes
0
Views
11
