Replace guardrail policies
Replaces the agent’s full set of guardrail policies with the list you send. This is a full overwrite, so include every policy you want to keep; any policy you omit is removed.
Authorizations
Flowyte secret API key (Authorization: Bearer flowyte_sk_live_…). Scope-gated; is scoped to your organization — a key can never reach another tenant. The listed scopes in each operation's apiKey requirement are the scopes that key must hold. The tokenUrl is nominal: keys are minted in the dashboard.
Path Parameters
The agent this resource is scoped to (the UUID returned by createAgent / listAgents).
Body
Server-assigned policy id.
The agent this policy is scoped to.
The owning organization (server-set).
The kind of guard, which determines the shape of config: verify_before_disclose — require a passed caller-verification before answering (config: { "fields": ["balance","ssn"] } — the sensitive fields gated); allowed_fields — allowlist the fields a skill may return (config: { "fields": ["order_status","eta"] }); write_gate — require explicit confirmation before a mutating skill runs (config: { "requireConfirmation": true }); rate_limit — cap how often a skill/action fires (config: { "maxPerCall": 3, "windowSeconds": 60 }); business_hours — only allow the action inside configured hours (config: { "timezone": "America/New_York", "openHour": 8, "closeHour": 18 }); content_policy — block/redact disallowed content (config: { "blocklist": ["competitor pricing"] }).
verify_before_disclose, allowed_fields, write_gate, rate_limit, business_hours, content_policy Optional — restrict this policy to one skill type (e.g. order_lookup). Omit to apply agent-wide.
Policy-type-specific settings. Free-form by contract, but the expected keys depend on policyType (see the enum descriptions above). Send the object shape that matches the type.
Whether the policy is active. Disabled policies are retained but not enforced.