A1 ratingsSnowflakeSnowflake Cortex Agents

Snowflake Cortex Agents

Snowflake · platform · Any industry
A
AGrade
82Score
±795% range
#3Rank of 1134
0%From fleets
FR-CAT-00323Catalog no.

The six pillars

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

Can you see what it costs?

Vendor cost API (ACCOUNT_USAGE.CORTEX_AGENT_USAGE_HISTORY (TOKEN_CREDITS, CREDITS_GRANULAR)) · prices published
90±17
Desk research 100 · 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?

ACCOUNT_USAGE.CORTEX_AGENT_USAGE_HISTORY
90±17
Desk research 100 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.

Can you tie cost to one agent?

Exact, per key or project
93±13
Desk research 100 · 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 · Agents exposed as tools via Snowflake-managed MCP server.
90±17
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 + SCIM
90±17
Desk research 100 · 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
10±17
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 research81%Neutral starting point19%

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 + SCIM
PricesPublished

Per-user AI credit quotas are the only Snowflake AI cost control with built-in enforcement (blocks within minutes); resource budgets can run a custom action at 100%. Programmatic access tokens can carry a ROLE_RESTRICTION and are revoked with ALTER USER ... REMOVE PROGRAMMATIC ACCESS TOKEN. ACCESS_HISTORY (Enterprise+) records object access per user. SAML 2.0/OIDC SSO and SCIM 2.0 supported.

History

11-12 A 8211-13 A 8211-14 A 8211-15 A 8211-16 A 8211-17 A 8211-18 A 8211-19 A 82
First rated 2026-10-02 at 74 (A). Now 82. 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
Vendor cost API Verified 2026-11-15
2 earlier
[1][2] Correct
Prices published
Cost
Yes Declared
high confidence
2026-10-12 [1][2][3][4] Correct
Usage API
Usage
ACCOUNT_USAGE.CORTEX_AGENT_USAGE_HISTORY Declared
high confidence
2026-10-12
1 earlier
[1][2] Correct
Cost per agent
Per agent
Exact, per key or project Verified 2026-11-16
2 earlier
[1][2][3] Correct
How an agent reports out
Reports out
Remote MCP connector Declared
high confidence
2026-10-12
1 earlier
[1][2] Correct
Per-agent keys
Controls
Scoped Declared
high confidence
2026-10-12 [1][2][3][4] Correct
Audit log
Controls
By API Declared
high confidence
2026-10-12 [1][2][3][4] Correct
Revoke access
Controls
By API Declared
high confidence
2026-10-12 [1][2][3][4] Correct
Spend cap
Controls
Hard cap Declared
high confidence
2026-10-12 [1][2][3][4] Correct
SSO
Controls
SSO + SCIM Declared
high confidence
2026-10-12 [1][2][3][4] Correct
Small plans get the data
Small plans
No Declared
high confidence
2026-10-12
1 earlier
[1][2] Correct

Prices · Token credits per request (consumption table)

Notes · Per-request rows with AGENT_NAME, USER_NAME and credit breakdown by model, about 1-hour latency: exact per-agent attribution.

Scored with the rubric for Platforms and APIs (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 Snowflake Cortex 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.