A1 ratingsIBMIBM Bob

IBM Bob
IBM · agent Provisional
DGrade
38Score
±1695% range
≈#702Rank of 1134
0%From fleets
FR-CAT-01358Catalog 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?
Only your card statement · prices published
Desk research 40 · 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?
No usage API found
Desk research 0 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.
Can you tie cost to one agent?
Nothing a buyer can read
Desk research 0 · 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: Hard cap · Per-agent keys: Scoped · Audit log: Console only · Revoke: Console only · SSO: SSO only
Desk research 85 · 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?
Small plans don't get the data
Desk research 0 · 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 research51%Neutral starting point49%
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 capHard cap
Per-agent keysScoped
Audit logConsole only
RevokeConsole only
SSOSSO only
PricesPublished
Overage is off by default, resets to off each month and is capped by a user limit or an admin limit (in packs). API keys (General or Inference) are scoped to user, instance and team and revoked in the web console. The Enterprise activity log (downloadable CADF JSON) is in the Admin UI only. SSO is SAML/OIDC on Enterprise; SCIM is not documented.
History
11-12 D 3811-13 D 3811-14 D 3811-15 D 3811-16 D 3811-17 D 3811-18 D 3811-19 D 38
First rated 2026-10-05 at 37 (D). Now 38. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-04.Run agents on IBM Bob?
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.