> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sreagent.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Read the AI settings

> How this organization's AI work is routed and retried, as the Settings page's Investigation Settings card shows it: whether calls may fall back to this deployment's shared credentials, whether prompts are redacted first, how many extra attempts one provider is given for a transient failure, and whether an investigation runs as several agents. retry_budget is the value in force, so it carries the default when nothing is stored; retry_budget_configured says which of the two it is.



## OpenAPI

````yaml /api-reference/openapi.json get /ai_settings
openapi: 3.1.0
info:
  description: >-
    A resource-shaped endpoint onto the same tool surface the MCP server
    (/api/mcp) reaches. Every gate, refusal and audit row a caller sees here is
    the exact one the MCP endpoint answers for the same tool. Authenticated with
    an API key holding the api:admin scope, or the read-only api:config_read
    scope for GET alone.
  title: SRE Agent configuration API
  version: 1.0.0
servers:
  - url: https://sreagent.app/api/v1/config
security:
  - apiKey: []
tags:
  - name: ai_providers
  - name: ai_settings
  - name: alert_mutes
  - name: alert_routes
  - name: aws_external_id
  - name: certificate_monitors
  - name: change_notifications
  - name: compliance_periods
  - name: connectors
  - name: data_sources
  - name: deploy_policies
  - name: export
  - name: github_settings
  - name: image_targets
  - name: notification_settings
  - name: organization_settings
  - name: outbound_configs
  - name: outbound_rules
  - name: overseer_settings
  - name: prompt_templates
  - name: repo_settings
  - name: service_bindings
  - name: slack
  - name: slis
  - name: slos
  - name: status_page_components
  - name: status_page_incidents
  - name: status_page_settings
  - name: synthetic_checks
  - name: team_members
  - name: teams
  - name: ticket_import_rules
  - name: ticket_integrations
paths:
  /ai_settings:
    get:
      tags:
        - ai_settings
      summary: Read the AI settings
      description: >-
        How this organization's AI work is routed and retried, as the Settings
        page's Investigation Settings card shows it: whether calls may fall back
        to this deployment's shared credentials, whether prompts are redacted
        first, how many extra attempts one provider is given for a transient
        failure, and whether an investigation runs as several agents.
        retry_budget is the value in force, so it carries the default when
        nothing is stored; retry_budget_configured says which of the two it is.
      operationId: get_ai_settings
      parameters: []
      responses:
        '200':
          content:
            application/json:
              schema:
                properties:
                  data:
                    $ref: '#/components/schemas/ai_settings_row'
                  organization:
                    type: object
                type: object
          description: The row.
        '404':
          description: No such resource.
        default:
          description: The request failed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
components:
  schemas:
    ai_settings_row:
      properties:
        anonymization_enabled:
          type:
            - boolean
            - 'null'
        multi_agent_investigation:
          type:
            - boolean
            - 'null'
        own_providers_only:
          type:
            - boolean
            - 'null'
        retry_budget:
          type:
            - integer
            - 'null'
        retry_budget_configured:
          type: boolean
      required:
        - retry_budget
        - own_providers_only
        - anonymization_enabled
        - multi_agent_investigation
        - retry_budget_configured
      type: object
    Error:
      type: object
      description: The body of every failed request.
      properties:
        error:
          type: string
          description: >-
            A short machine-readable code such as forbidden, conflict or
            read_only_key.
        message:
          type: string
          description: A sentence that says what to change.
      required:
        - error
        - message
      additionalProperties: true
  securitySchemes:
    apiKey:
      description: >-
        An sre_ak_* API key holding the api:admin scope (or api:config_read,
        which every write refuses with read_only_key).
      scheme: bearer
      type: http

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.