A1 ratingsHarnessHarness AI agents

Harness AI agents

Harness · agent · Any industry Provisional
C
CGrade
46Score
±1995% range
≈#474Rank of 1134
0%From fleets
FR-CAT-00675Catalog 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 emailed invoices · prices on request only
31±38
Desk research 12 · 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
25±38
Desk research 0 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.

Can you tie cost to one agent?

50±59
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?

50±59
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?

Per-agent keys: Scoped · Audit log: By API · Revoke: By API · SSO: SSO only
73±38
Desk research 96 · 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?

50±59
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 research30%Neutral starting point70%

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 capNot known
Per-agent keysScoped
Audit logBy API
RevokeBy API
SSOSSO only
PricesOn request

Service accounts with role bindings issue expiring scoped tokens, deletable via API; audit trail streams to S3/GCS/Splunk/Sumo; SAML SSO documented (these pages not re-read today, values kept). Harness AI can be enabled at account level with per-org/project overrides. No AI usage spend cap found; pricing is contact-sales.

History

11-12 C 4611-13 C 4611-14 C 4611-15 C 4611-16 C 4611-17 C 4611-18 C 4611-19 C 46
First rated 2026-10-07 at 48 (C). Now 46. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-06.

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
Only emailed invoices Inferred 2026-11-04
1 earlier
[1][2] Correct
Prices published
Cost
No Inferred 2026-11-04
3 earlier
[1][2] Correct
Usage API
Usage
None found Inferred 2026-11-04
1 earlier
[1][2] Correct
Per-agent keys
Controls
Scoped Inferred 2026-11-04
3 earlier
[1][2] Correct
Audit log
Controls
By API Inferred 2026-11-04
3 earlier
[1][2] Correct
Revoke access
Controls
By API Inferred 2026-11-04
3 earlier
[1][2] Correct
SSO
Controls
SSO only Inferred 2026-11-04
3 earlier
[1][2] Correct

Notes · Pricing page: Free, Essentials and Enterprise (paid plans contact-sales, no dollar figures) with no AI credit or per-agent pricing; AI modules (AI Security, AI SRE, AI DLC Insights) listed without prices. Docs describe enabling Harness AI per account with org/project overrides but not licensing.

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

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

Run agents on Harness AI agents?

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.