> ## Documentation Index > Fetch the complete documentation index at: https://conductorone-docs-terraform-v2-owner-resources.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Get Agent Classifier Policy > Get returns the tenant's classifier policy with its ordered rules. A tenant that has never written a policy receives an empty policy. ## OpenAPI ````yaml https://spec.speakeasy.com/conductor-one/conductorone/my-source-with-code-samples get /api/v1/settings/ai-governance/agent-classifier-policy openapi: 3.1.0 info: description: The C1 API is a HTTP API for managing C1 resources. title: C1 API version: 0.1.0-alpha servers: - description: The C1 API server for the current tenant. url: https://{tenantDomain}.conductor.one variables: tenantDomain: default: example description: The domain of the tenant to use for this request. security: - bearerAuth: [] oauth: [] paths: /api/v1/settings/ai-governance/agent-classifier-policy: get: tags: - AI Governance Settings summary: Get Agent Classifier Policy description: >- Get returns the tenant's classifier policy with its ordered rules. A tenant that has never written a policy receives an empty policy. operationId: c1.api.ai_governance.v1.AgentClassifierService.GetAgentClassifierPolicy responses: '200': content: application/json: schema: $ref: >- #/components/schemas/c1.api.ai_governance.v1.GetAgentClassifierPolicyResponse description: Successful response components: schemas: c1.api.ai_governance.v1.GetAgentClassifierPolicyResponse: description: The GetAgentClassifierPolicyResponse message. properties: policy: oneOf: - $ref: >- #/components/schemas/c1.api.ai_governance.v1.AgentClassifierPolicy - type: 'null' title: Get Agent Classifier Policy Response type: object x-speakeasy-name-override: GetAgentClassifierPolicyResponse c1.api.ai_governance.v1.AgentClassifierPolicy: description: >- AgentClassifierPolicy is the tenant's full classifier policy: the ordered rule cascade plus the no-match default. properties: agentId: description: Optional agent scoping. Empty is the tenant-wide default policy. type: string createdAt: format: date-time type: - string - 'null' defaultDenyReason: description: The defaultDenyReason field. type: string defaultOutcome: description: The defaultOutcome field. enum: - AGENT_CLASSIFIER_RULE_OUTCOME_UNSPECIFIED - AGENT_CLASSIFIER_RULE_OUTCOME_ALLOWED - AGENT_CLASSIFIER_RULE_OUTCOME_DENIED type: string x-speakeasy-unknown-values: allow rules: description: The rules field. items: $ref: '#/components/schemas/c1.api.ai_governance.v1.AgentClassifierRule' type: - array - 'null' tenantId: description: The tenantId field. type: string updatedAt: format: date-time type: - string - 'null' title: Agent Classifier Policy type: object x-speakeasy-name-override: AgentClassifierPolicy c1.api.ai_governance.v1.AgentClassifierRule: description: AgentClassifierRule is one entry in the ordered cascade. properties: action: description: The action field. enum: - AGENT_CLASSIFIER_RULE_ACTION_UNSPECIFIED - AGENT_CLASSIFIER_RULE_ACTION_EVALUATE_HOOKS - AGENT_CLASSIFIER_RULE_ACTION_BLOCK type: string x-speakeasy-unknown-values: allow celCondition: description: Empty matches every tool call. type: string denyReason: description: The denyReason field. type: string description: description: The description field. type: string displayName: description: The displayName field. type: string id: description: >- Stable rule identifier. Leave empty on a rule being added; the server assigns one. type: string mode: description: The mode field. enum: - AGENT_CLASSIFIER_RULE_MODE_UNSPECIFIED - AGENT_CLASSIFIER_RULE_MODE_ENFORCE - AGENT_CLASSIFIER_RULE_MODE_OBSERVE - AGENT_CLASSIFIER_RULE_MODE_DISABLED type: string x-speakeasy-unknown-values: allow outcome: description: The outcome field. enum: - AGENT_CLASSIFIER_RULE_OUTCOME_UNSPECIFIED - AGENT_CLASSIFIER_RULE_OUTCOME_ALLOWED - AGENT_CLASSIFIER_RULE_OUTCOME_DENIED type: string x-speakeasy-unknown-values: allow postHookIds: description: The postHookIds field. items: type: string type: - array - 'null' preHookIds: description: The preHookIds field. items: type: string type: - array - 'null' preOutputHookIds: description: >- Hook ids of event type HOOK_EVENT_TYPE_PRE_OUTPUT curated by this rule, evaluated against the assistant's outgoing response rather than a tool call. Parallel to pre_hook_ids/post_hook_ids. items: type: string type: - array - 'null' sourceTemplateId: description: >- Rule template this rule was composed from via AddClassifierRuleFromTemplate. Empty for hand-authored rules; drives the "from template / Custom" provenance chip. Cleared once the rule diverges from its template. type: string systemManaged: description: |- system_managed is true for rules the platform inserts and manages (currently: the baseline fallback rule appended at the end of every policy's rule list). system-managed rules cannot be created, updated, or deleted through the admin API — the frontend renders them read-only. Persisted user rules always serialize with system_managed = false. type: boolean toolGateIds: description: The toolGateIds field. items: type: string type: - array - 'null' required: - displayName title: Agent Classifier Rule type: object x-speakeasy-name-override: AgentClassifierRule securitySchemes: bearerAuth: scheme: bearer type: http oauth: description: >- This API uses OAuth2 with the Client Credential flow. Client Credentials must be sent in the BODY, not the headers. For an example of how to implement this, refer to the [c1TokenSource.Token()](https://github.com/ConductorOne/conductorone-sdk-go/blob/3375fe7c0126d17e7ec4e711693dee7b791023aa/token_source.go#L101-L187) function. flows: clientCredentials: scopes: {} tokenUrl: /auth/v1/token type: oauth2 ````