How might Harvey (Business/Productivity Software) enhance its AI-powered legal research assistant to provide more targeted case law recommendations?

Introduction

To enhance Harvey's AI-powered legal research assistant for more targeted case law recommendations, we need to dive deep into user needs, current pain points, and potential technological advancements. I'll outline a strategic approach to improve this critical feature, focusing on user experience, accuracy, and efficiency.

Step 1

Clarifying Questions (5 mins)

• Looking at the product context, I'm thinking Harvey might be targeting a specific subset of legal professionals. Could you help me understand who our primary users are and their key use cases for the AI-powered legal research assistant?

Why it matters: Determines the depth and breadth of case law coverage needed Expected answer: Primarily used by associates at large law firms for complex litigation research Impact on approach: Would focus on depth in specific practice areas rather than broad coverage

• Considering user behavior, I'm curious about how lawyers typically interact with the AI assistant. Could you share insights on the most common query patterns and how users refine their searches?

Why it matters: Informs the design of the recommendation algorithm and user interface Expected answer: Users often start broad and iteratively refine based on initial results Impact on approach: Would prioritize features that support iterative search and learning from user interactions

• Examining pain points, I'm wondering about the current accuracy and relevance of case law recommendations. What feedback have we received from users about the quality of results, and how does it compare to traditional legal research methods?

Why it matters: Identifies key areas for improvement in the AI model and recommendation system Expected answer: Generally positive, but users sometimes miss important cases or receive irrelevant recommendations Impact on approach: Would focus on improving precision and recall of the AI model

• Considering the product lifecycle, where does Harvey stand in terms of market adoption, and what are the key metrics driving this improvement initiative?

Why it matters: Helps prioritize between user acquisition and retention strategies Expected answer: Growing user base, but facing increased competition; focus on improving user retention and engagement Impact on approach: Would emphasize features that increase daily active users and time spent on the platform