ASK.
Generative AI.
Role: IC Lead Product Designer
Cross-Functional Team: Product, Engineering, Data science, Executive team, Quality Assurance.
Problem: Data is growing exponentially and legal teams need efficient, simplified search to reduce evidence loss and cost escalation.
Solution: Improve user search and review with generative AI-driven tools.
Result: Ask AI streamlines legal review with natural language search and transparent citations, delivering dramatic efficiency gains.
To manage exponential data growth, legal teams need efficient, simplified search to reduce evidence loss and cost escalation.
Overwhelming Data Volume:
-
The sheer volume of electronically stored information (ESI) is exponentially increasing, creating an overwhelming challenge for legal professionals.
-
In today's litigious environment, the ability to quickly and accurately find relevant information is no longer a luxury, it's a necessity, and current search methods are failing to meet this critical need.
Complex existing Search methods:
-
Keyword and Boolean search methods are inadequate for the complexity of legal language and large datasets.
-
These methods are time-consuming and require specialised knowledge of search syntax.
-
Legal professionals can sometimes struggle to craft effective queries, often with limited success.
Nuances of Legal Language:
-
Traditional search methods can fail to grasp the nuances of legal language, including complex terminology, subtle distinctions, and implied meanings.
-
Keyword searches can miss crucial information if a document lacks the precise keywords used.
-
Failure to identify relationships or interpret intent results in missed evidence.
Missed Evidence and higher costs:
-
Missed evidence can negatively impact case outcomes, leading to unfavourable judgments or settlements.
-
Time-consuming manual review drives up costs, placing a significant burden on legal teams.
-
The inability to quickly and accurately find information is a critical failing in today's legal environment.
Contextual background
I joined Reveal following its acquisition of Logikcull in the summer of 2023. At Logikcull, I and a small team of data scientists began exploring the potential of generative AI in e-discovery. This involved user interviews, research, and collaboration with internal data scientists and industry experts.

After joining Reveal, I was tasked with leading the design of "Ask," their innovative generative AI project. While some initial concept work had been done for a BETA, significant improvements were needed to make Ask practical for real-world discovery cases, which is where my contribution began.
Comprehensive research identified key user needs, driving ASK's strategic improvements.
Start with the WHY?
To inform the development and strategy of ASK, a comprehensive user research initiative was undertaken, focusing on understanding the needs and pain points of our users. This research was conducted through a multi-faceted approach:

Targeted User Interviews: Working with the VP of Product and Customer Success Managers, key global accounts were selected for initial user research. To empower users to schedule a 1:1 research session at their convenience, I created a public calendar link which was circulated via email. I then conducted interviews with users across these accounts, gathering direct feedback on their experiences and requirements.

Collaboration with Stakeholders and Experts: Internal stakeholders and industry experts were consulted to gain a deeper understanding of current use cases and potential areas for improvement. This collaborative approach ensured a holistic view of the product's application within the market. Insights from other internal customer-facing teams such as customer success, support and sales were also gathered during this period.

Competitive and Market Research: In addition to user research, ongoing competitive and market research was conducted to provide context and identify industry trends, informing product strategy and development. The generative AI landscape is evolving rapidly which requires constant tracking in order to inform product decisions.
Beyond informing design and product decisions, effectively communicating the research findings and the "why" behind features was crucial. To achieve this, I created knowledge-sharing documentation and utilised AI-powered Zoom and Gong summaries and repositories. I also presented my findings to the entire product team, fostering broad understanding and alignment.
User Stories:
Answer Verification: As a user, I want to see a list of references for each answer provided by Ask, so I can verify the information.
Cited Documents in Response: As a user, I want cited documents incorporated into Ask's responses, so I can understand the basis of its conclusions.
Document Set Selection: As a user, I want to select the document set my questions relate to (e.g., all documents, current search), so Ask can provide more relevant answers.
Document Set Summarization/Timeline-Based Answers: As a user, I want Ask to generate a summary of a document set or provide answers based on a timeline, so I can quickly grasp key information.
Easy Document Viewer Access: As a user, I want to easily open cited documents in the document viewer, so I can review them in detail.
Fullscreen Ask Window: As a user, I want to expand the Ask window to full screen, so I can view more content.
Admin - Session Log Access: As an admin, I want to view and download session logs for chat conversations in Ask, so I can monitor usage and troubleshoot issues.
Chat History: As a user, I want to view my chat history and resume previous conversations, so I can easily track and continue my research.
Download Conversation: As a user, I want to download a conversation with Ask, so I can keep a record of the interaction.
Share Conversation/Document Set: As a user, I want to share a chat conversation or a resulting document set with a colleague, so I can collaborate effectively.
Feedback on Response: As a user, I want to provide feedback on a response from Ask, so I can help improve its accuracy and usefulness.
Prompt Suggestions: As a user, I want access to initial prompt ideas or suggestions, so I can more easily formulate effective queries.
We improved the user experience and flow by incorporating chat history, document citations, and chat downloads.
To improve the user experience, we looked to add several features to the Ask interface. Users should now be able to ask new questions and view their chat history. After a conversation or review, users have several exit options: open cited documents, download the chat, or simply close and exit Ask.
A user-centred redesign of "Ask" prioritizes clarity, control, and legal defensibility through improved search, instructions, chat, and citations.
I initially tackled two key design and user experience challenges: search scope and additional instructions. Users needed to refine their "ask" queries to specific document subsets, such as the results of a previous search. I addressed this by adding a simple radio button, allowing users to toggle between "Current Results" and "All Docs" for their search scope.
The second challenge involved the "additional instructions" input. This feature lets users refine their questions (e.g., requesting a list-formatted response), but isn't always needed. Since technical limitations require separate input fields for the initial question and additional instructions, I wanted to avoid cluttering the interface with two permanent inputs. Therefore, I nested the "additional instructions" field under a "More Details" link, keeping the interface clean while still offering the advanced functionality.
Ask now offers persistent chat history with a user-controlled, expandable panel.
Users strongly requested the ability to resume previous conversations. Thanks to recent technical advancements, we are now able to offer this feature, displaying previously saved chat sessions within the interface.
Recognizing the potential for Ask to evolve into a highly powerful and complex interface, I prioritized a design and user experience that would allow users to manage the visibility of their chat history. To achieve this, I introduced a collapsible left panel within the modal. This panel provides a dedicated space for displaying the chat history, ensuring it's readily accessible while also allowing users to hide it when not needed. Furthermore, this design choice offers the flexibility to incorporate additional menu items into this panel in the future, as Ask's functionality expands.
Citation iterations:
Legal AI defensibility with citations and source document access.
Defensibility is the paramount concern for legal professionals using generative AI. They need to understand and justify the AI's output. Ask addresses this by providing citations for its responses. Users receive citation numbers and a sample of the source documents, which can be reviewed individually or as a batch in the document viewer. This feature connects generative AI with established assisted review workflows.
We collaborated with internal and external industry experts to iteratively design and refine our citation format. This process addressed challenges such as citation length, the number of citations, handling multiple references within a single cited document, and ensuring accurate citation matching.
Prompt libraries simplify AI use for legal professionals in "Ask".
Conversations with users and trainers of Ask revealed an opportunity to enhance the initial user experience. Despite general awareness of generative AI, many legal professionals lack a clear understanding of its practical applications within their field. To address this, I began investigating the potential of "prompt libraries" and "suggested prompts." The goal is to enable account owners to import or create collections of valuable and relevant prompts, providing their users with a helpful starting point for discovery during litigation.
We explored integrating prompt recommendations into the "Ask" modal for first-time users. Upon loading, users would see general prompt ideas, and a "type" menu would allow them to filter for more specific categories, such as Subpoena, FOIA requests, or Employment disputes.
Adding downloadable session logs for improved AI defensibility.
To enhance user defensibility, we explored incorporating a session log. This feature would not only track Ask usage but also allow admins to view and download conversation session reports within a specified date range and/or for specific users. This would be invaluable for users or admins needing to support findings derived from generative AI-assisted review. I designed two versions: one as a dedicated, fixed session log screen, and another as a modal accessible from anywhere within the product (subject to user/admin permissions).
Ask AI streamlines legal review with natural language search and transparent citations, delivering dramatic efficiency gains.
Natural Language Search: Ask questions in everyday language, avoiding complex Boolean searches or keyword guessing.
​
AI-Powered Summaries: Get concise, human-readable summaries of relevant information, not just document lists.
​
Targeted Results: Receive precise answers tailored to specific questions.
​
Source Transparency: See a ranked list of source documents with snippets of text used to generate the answer, allowing for verification.
​
Data Control: Choose the data Ask uses, from an entire dataset to a single custodian.
​
Integration with Reveal: Seamlessly navigate between Ask and other Reveal features.
​
Result Saving: Save Ask results as a search for later use.
​
Downloadable Results: Download a complete list of questions, answers, sources, and more.
​
Efficient Matter Understanding: Rapidly learn more about a matter through concise summaries and deep dives.
Facing a one-week deadline for a multi-million dollar construction arbitration closing brief, K2 leveraged Reveal's ASK technology to efficiently process over 3,000 documents, resulting in a 65-page brief containing 250 precisely integrated citations.
Utilising Ask and a streamlined approach, K2 yielded a 360% increase in time savings efficiency, completing the brief in days rather than weeks, and significantly reduced review costs.
The firm praised the streamlined process, the accuracy of ASK in identifying key documents, and the comprehensive handling of evidence, ultimately delivering a persuasive and well-supported brief within the tight deadline.
Ask will evolve with user feedback, focusing on transparency and defensibility in AI-powered legal search
The expanding capabilities of generative AI offer exciting possibilities for Ask's growth. User feedback and ongoing research by our data science team will drive a continuous cycle of new features and improvements.

A key focus will remain on refining the user experience, particularly how we connect users with relevant documents. Our goal is to make natural language search easy, fast, and efficient. While AI won't replace legal professionals, this assistive technology can be incredibly powerful. We've heard firsthand from users that building confidence in the technology, and specifically in Ask, hinges on defensibility. Users need to understand how certain documents, decisions, and outcomes were derived.

Generative AI in legal tech cannot be a "black box." Therefore, we need to empower users to understand and audit the information Ask produces.