From the source
Harvey's patent research agent navigates fragmented patent sources, deciding what to seek next and conducting focused research within a bounded budget.
- The company says a single patent index falls short because patent information is scattered across published patents, patent-office systems, indexes and web sources, each with its own boundaries.
- Traditional retrieval-augmented generation searches a fixed index and works when the information sits in one collection and the research path is predictable, but in patent research a result may reveal another record to inspect or another fact to verify.
- Each task starts with a research objective that preserves the user's full question, including patent numbers, claim numbers, timing and legal context, so the agent plans from the desired outcome rather than a reduced bag of keywords.
- For recurring patterns such as current claim status, art applied by an examiner, PTAB outcomes and prior-art research, Harvey gives the agent concise paths, which it describes as information requirements rather than hard-coded source assignments.
- The agent receives a routing table listing what data each source has, which information needs it serves best, where its boundaries lie and which alternative can be a fallback; it prioritizes the USPTO for U.S. patent text and names Google Patents as an alternative when the USPTO isn't available.
- The agent stops when it can return a cited answer, identify what remains unresolved, or when it reaches the run's research budget.






