Compare / Harvey
Sandstone vs Harvey: Legal AI for Firms, or the System In-House Runs On?
Harvey is legal AI at enterprise scale — research, document analysis, drafting, diligence, and a workflow builder, used across most of the Am Law 100 and by hundreds of in-house teams. Sandstone is built for a narrower job: supporting an in-house legal team day to day. Intake from wherever requests arrive, workflows built step by step, permissions mapped across your systems, and a record of each request from arrival to resolution.
Sandstone vs Harvey
| Capability | Sandstone |  Harvey |
|---|---|---|
| Primary focus | AI-native operating system for in-house legal work | Enterprise legal AI across research, analysis, drafting, and diligence |
| Who it was built for | In-house legal departments serving a business | Law firms first, with a growing in-house customer base |
| Intake | Structured intake from Slack, email, and business systems, in whatever form requests arrive | Work begins once a document or question is brought to the platform |
| Business context | Counterparty history, prior decisions, and relationships surfaced before work starts | Matter and document context within the platform |
| Workflows | Built step by step, with approval gates at each one | Workflow agents built from user input, AI action, logic, and output steps |
| Permissions across systems | Permissions mapped across every connected integration | Enterprise platform controls |
| Repository and system of record | Serves as system of record, with contracts connected to matters, counterparties, and obligations | Document and matter workspaces |
| Reporting | Cycle time, risk exposure, capacity, and deviation rates across the function | Usage and workflow analytics |
| Internal collaboration | Legal works a request together in the app or the plugins, with comments and drafts staying behind the scenes until you choose otherwise | Shared workspaces and workflows |
| Acting back in source systems | Replies and actions go back to Slack, procurement, and contract systems under a shared team identity, with permissions mapped across those integrations centrally | Platform-based |
| Best fit for | In-house teams whose bottleneck is the volume and variety of inbound legal work | Firms and large legal organizations doing research and document-heavy work at scale |
Based on publicly available information as of September 2026. Names and trademarks belong to their respective owners. If anything here is inaccurate or out of date, contact us and we'll update it.
Frequently asked questions
Sandstone assumes a legal department serving a business — requests arriving from sales and procurement, questions that never become documents, context that needs to survive between matters. Platforms built firm-first assume a matter already exists and a lawyer is already working it. Both are legitimate; they solve different halves.
Sandstone does basic research, grounded in your own playbooks, precedent, and prior decisions rather than external case law. It isn't built to replace Westlaw or Lexis, and teams doing heavy case law and statutory research generally keep a dedicated research platform alongside it.
Yes — roughly five to a hundred lawyers is the range, and small teams often feel the problem hardest because there is nobody to absorb the overflow. Seat economics differ a lot across enterprise platforms, so it is worth checking pricing against your actual headcount early in any evaluation.
Commonly, yes. A research and document-analysis platform sits alongside Sandstone rather than competing with it. The overlap is narrow.
