A1 ratingsHarveyHarvey

Harvey
Harvey · platform · Law firms Provisional
BGrade
59Score
±1795% range
≈#272Rank of 1134
0%From fleets
FR-CAT-00752Catalog no.
Provisional: the range is wide because some facts are thin or not yet known. It narrows as research and fleets fill in.
The six pillars
Each bar is the score; the bracket is its 95% range.
Can you see what it costs?
Admin or analytics API · prices on request only
Desk research 56 · counts for 25% · A cost API you can call scores highest; an admin console or cloud billing export next; a card statement or emailed invoice is all some products leave you. Published prices add to it.
Can you see how much it's used?
https://developers.harvey.ai/guides/usage_history.md (GET /api/v2/history/usage; per-user, workflow and client-matter events, no tokens or cost; 2 req/min; max 30-day range)
Desk research 100 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.
Can you tie cost to one agent?
partial
Not known yet. Sits at a neutral 50 with a wide range until facts arrive · counts for 15% · Exact (one key or project per agent) beats by-project, by-workspace or by-user.
Can an agent on it report out?
Not known yet. Sits at a neutral 50 with a wide range until facts arrive · counts for 15% · A remote MCP connector scores highest, then a local MCP server, an SDK, an API or a workflow step; copy-and-paste lowest. Any open standard counts, not just FleetRegistry.
Can you control spend and access?
Spend cap: None · Per-agent keys: Scoped · Audit log: By API · Revoke: Console only · SSO: SSO + SCIM
Desk research 66 · counts for 20% · Hard spend caps (30%), scoped per-agent keys (25%), an audit log you can read by API (20%), revoking by API (15%), SSO with SCIM (10%).
Does it work on small plans?
Not known yet. Sits at a neutral 50 with a wide range until facts arrive · counts for 10% · Whether the plan a person or small business buys gets the cost and usage data at all.
Where the evidence comes from
Independent fleets0%Desk research43%Neutral starting point57%
Once three independent fleets report on a pillar, desk research counts for at most a third of it. FleetRegistry's own fleets never count.
Controls on record
Spend capNone
Per-agent keysScoped
Audit logBy API
RevokeConsole only
SSOSSO + SCIM
PricesOn request
API tokens are created and managed in workspace settings with per-endpoint permission lists; token create/delete/rotate events are logged. Audit Log API (search/earliest/latest/paginate, queries up to 1 year back) includes SSO and SCIM events, built for SIEM export. SCIM (Okta, Entra ID) requires SAML SSO. Seat pricing via sales with no usage spend controls.
History
11-12 B 5911-13 B 5911-14 B 5911-15 B 5911-16 B 5911-17 B 5911-18 B 5911-19 B 59
Rated since 2026-10-07. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-06.Run agents on Harvey?
Give each one a permanent number, a named person who answers for it, and a record of what it can touch and what it costs. Free.