A1 ratingsBoxBox Agent

Box Agent

Box · agent · Any industry Not sold to buyers
-
-Grade
-Score
±1495% range
-Rank of 1136
0%From fleets
FR-CAT-00277Catalog no.
An internal or bundled tool nobody buys on its own, so there is nothing for a buyer to rate.

The six pillars

Each bar is the score; the bracket is its 95% range.

Can you see what it costs?

Nothing a buyer can read · prices published
35±38
Desk research 20 · 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
14±27
Desk research 0 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.

Can you tie cost to one agent?

By user
50±27
Desk research 50 · 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?

Remote MCP connector · Agent can connect to Box's remote MCP server (https://mcp.box.com, OAuth); no confirmed API to push/pull usage.
86±27
Desk research 100 · 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: By API · Revoke: By API · SSO: SSO only
74±38
Desk research 97 · 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
14±27
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 research62%Neutral starting point38%

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 logBy API
RevokeBy API
SSOSSO only
PricesPublished

Box AI runs on monthly AI Units per plan. When they run out, Expanded Mode and Automate agent runs are blocked (no automatic overage) while standard Box Agent keeps working, and admins get a console banner plus email. The enterprise events admin_logs stream is readable by API, and AI agents can be deleted via DELETE /ai_agents/{id}. SAML SSO is documented, but SCIM was not confirmed. Box Agent keeps existing permissions and retention, and Enterprise Advanced is quote-only.

History

11-12 - 11-13 - 11-14 - 11-15 - 11-16 - 11-17 - 11-18 - 11-19 -
Not saved yet. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-02.

Every fact, with its rung and source

Each fact stands on its own source and its own rung of the evidence ladder (Rule N2.1). Verified Observed Declared Inferred. The weakest fact in a pillar sets its weight.

FactValueRungCheckedSources
How a buyer sees cost
Cost
None found Declared
medium confidence
2026-10-18
1 earlier
[1][2] Correct
Prices published
Cost
Yes Inferred 2026-10-18
2 earlier
[1][2][3][4] Correct
Usage API
Usage
None found Declared
medium confidence
2026-10-18
1 earlier
[1][2] Correct
Cost per agent
Per agent
By user Declared
medium confidence
2026-10-18
1 earlier
[1][2] Correct
How an agent reports out
Reports out
Remote MCP connector Declared
medium confidence
2026-10-18
1 earlier
[1][2] Correct
Per-agent keys
Controls
Scoped Inferred 2026-10-18
2 earlier
[1][2][3][4] Correct
Audit log
Controls
By API Inferred 2026-10-18
2 earlier
[1][2][3][4] Correct
Revoke access
Controls
By API Inferred 2026-10-18
2 earlier
[1][2][3][4] Correct
Spend cap
Controls
Hard cap Inferred 2026-10-18
2 earlier
[1][2][3][4] Correct
SSO
Controls
SSO only Inferred 2026-10-18
2 earlier
[1][2][3][4] Correct
Small plans get the data
Small plans
No Declared
medium confidence
2026-10-18
1 earlier
[1][2] Correct

Prices · Standard Box Agent is non-chargeable; Expanded Mode consumes AI Units

Notes · Standard mode is included at no extra cost within usage limits, and Pro Mode is non-chargeable but subject to daily limits. Expanded Mode and agent runs inside Automate workflows draw AI Units. Box Agent is available on Enterprise Plus and Enterprise Advanced, with Pro and Expanded Mode on Enterprise Advanced only.

Scored with the rubric for Agents and agent platforms (Rule N7.1). Each pillar blends a neutral 50, desk facts weighted by rung, and independent fleets. A1 is 85+ with fleet proof, A 70, B 55, C 40, D 25, E below. Part N of the Rules

Corrections

2 awaiting review. Accepted corrections are published in the corrections register with an FR-C number.

Run agents on Box Agent?

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.