A1 ratingsGoogle DeepMindCodeMender

CodeMender

Google DeepMind · agent · Any industry Early access
-
-Grade
-Score
±1995% range
-Rank of 1134
0%From fleets
FR-CAT-00580Catalog no.
In beta or announced. A1 shows the facts but grades only released products, so early numbers never follow a product into release.

The six pillars

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

Can you see what it costs?

Cloud billing export · prices on request only
53±38
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?

No usage API found
60±38
Desk research 70 · 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
7±13
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?

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?

50±59
Not known yet. Sits at a neutral 50 with a wide range until facts arrive · 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
25±38
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 research38%Neutral starting point62%

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

Being researched now. Spend caps, per-agent keys, audit logs, revoking and SSO land here as the research writes them.

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
Cloud billing export Inferred 2026-10-30
1 earlier
[1][2][3] Correct
Prices published
Cost
No Verified 2026-11-16
3 earlier
[1][2] Correct
Usage API
Usage
None found Inferred 2026-10-30
1 earlier
[1][2][3] Correct
Cost per agent
Per agent
None found Verified 2026-11-16
2 earlier
[1][2][3][4] Correct
Small plans get the data
Small plans
No Inferred 2026-10-30
1 earlier
[1][2][3] Correct

Prices · No public price; Pre-GA public preview for a limited set of Google Cloud customers via Gemini Enterprise Agent Platform (contact sales); not for production use

Notes · Since Jul 21, 2026 offered as a managed agent in public preview on Gemini Enterprise Agent Platform and within AI Threat Defense (Wiz). Google docs show token counts per run and point to Cloud Billing reports for billed usage; no rate published.

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

Run agents on CodeMender?

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.