A1 ratingsPolyAIPolyAI

PolyAI

PolyAI · agent · Any industry
B
BGrade
62Score
±1395% range
≈#213Rank of 1134
0%From fleets
FR-CAT-00365Catalog no.

The six pillars

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

Can you see what it costs?

Admin or analytics API
64±27
Desk research 70 · 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?

Conversations API (v3): transcripts, total_duration and polyai_duration (seconds) and metrics per conversation
86±27
Desk research 100 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.

Can you tie cost to one agent?

By project
64±27
Desk research 70 · 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?

HTTP step in a workflow · Project-scoped API keys issued by PolyAI give conversation records with durations; minutes can be summed, but no billing endpoint.
57±27
Desk research 60 · 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 · Revoke: Console only · SSO: SSO only
68±38
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
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 research67%Neutral starting point33%

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 logNot known
RevokeConsole only
SSOSSO only
PricesNot known

API keys scoped to all or selected agents (fixed at creation) and per API permission, with expiry; deleted from the Agent Studio API Keys page. SSO handles sign-in only (roles set in Users page); SCIM and audit logs not documented.

History

11-11 B 6211-12 B 6211-13 B 6211-14 B 6211-15 B 6211-16 B 6211-17 B 6211-18 B 62
First rated 2026-10-02 at 64 (B). Now 62. 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
Admin or analytics API Declared
medium confidence
2026-10-27
1 earlier
[1] Correct
Usage API
Usage
Conversations API (v3): transcripts, total_duration and polyai_duration (seconds) and metrics per conversation Declared
medium confidence
2026-10-27
1 earlier
[1] Correct
Cost per agent
Per agent
By project Declared
medium confidence
2026-10-27
1 earlier
[1] Correct
How an agent reports out
Reports out
HTTP step in a workflow Declared
medium confidence
2026-10-27
1 earlier
[1] Correct
Per-agent keys
Controls
Scoped Inferred 2026-10-27
2 earlier
[1][2] Correct
Revoke access
Controls
Console only Verified 2026-11-15
3 earlier
[1][2] Correct
SSO
Controls
SSO only Inferred 2026-10-27
3 earlier
[1][2] Correct
Small plans get the data
Small plans
No Declared
medium confidence
2026-10-27
1 earlier
[1] Correct

Prices · Not published; per-minute pricing on annual enterprise contracts (third-party estimates ~$150k+/yr)

Notes · Billing is per minute but no rate card is public and there is no cost endpoint. Conversation durations (total_duration, polyai_duration) from the Conversations API are the closest proxy; v3 keys are issued by your PolyAI rep, scoped to project and region. v1 unsupported since 31 Aug 2026.

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 PolyAI?

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.