
Notion Custom Agents
The six pillars
Each bar is the score; the bracket is its 95% range.
Can you see what it costs?
Can you see how much it's used?
Can you tie cost to one agent?
Can an agent on it report out?
Can you control spend and access?
Does it work on small plans?
Where the evidence comes from
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
Admins can cap credits per member and per Custom Agent; shared-credit agents pause at the cap, with alerts at 80%/100%; an admin API (PATCH /v1/spaces/{space_id}/credit_limit, org bot token with workflows:write scope) sets the default agent cap. Workspace Notion credits for overage are off by default. Audit log (Enterprise) exports CSV and streams to a SIEM via webhook (no query API) and logs Custom Agent runs, not per-run actions. SAML SSO from Business, SCIM on Enterprise; individual agents disabled in Settings > Notion AI > Agents.
History
Run agents on Notion Custom 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.