> ## Documentation Index > Fetch the complete documentation index at: https://docs.duvo.ai/llms.txt > Use this file to discover all available pages before exploring further. # Read Automation Policy > Read an automation's whole Policy before answering anything about it: every question by section, with its `id` (the field id updateConfigField takes), key, type, answer and who gave it; `counts.questions` as the Policy screen's header counts them (`required_open` is what still blocks a run) apart from the module's pre-filled `module_defaults`; answers proposed by interviews and waiting for review; accepted and pending process-context notes; the interviews assigned; and `pending_apply`, the structural answers and notes not yet written into an Agent. `running` says whether the automation runs on live work: there a changed answer reaches its Agents from their next run, so name the question, its current answer and the new one, and change it only after the user says yes. A question whose `bindings` include `structural` changes how the Agents run; propose the matching Agent change too. Never invent an answer for a question shown as open. Give the user the full URLs in `urls`. ## OpenAPI ````yaml https://api.duvo.ai/v2/documentation/mintlify.json get /v2/automations/{automation_id}/policy openapi: 3.0.3 info: title: Duvo Public API description: >- Public API for programmatic access to Duvo. Authenticate with API keys created in the Duvo dashboard. ## Rate limits Requests are counted per API key. Every response advertises the quota with the IETF RateLimit fields, so a client can self-throttle without waiting for a rejection: - `RateLimit-Policy: "default";q=;w=` — the policy in force: `q` requests per `w` seconds. - `RateLimit: "default";r=;t=` — the live state: `r` requests left, quota resetting in `t` seconds. - Read the quota from the headers rather than hard-coding it; it differs per environment. - The same numbers are also sent as `ratelimit-limit`, `ratelimit-remaining` and `ratelimit-reset`. Once the quota is exhausted the API answers `429 Too Many Requests` with `Retry-After` set to the seconds to wait; honor it instead of retrying immediately. version: 1.0.0 servers: - url: https://api.duvo.ai description: Production server security: [] tags: - name: Runs description: Start, monitor, and manage agent runs (Runs in the Duvo UI) - name: Sandboxes description: Create sandboxes and upload files for agent runs - name: Queues description: Manage queues and their agent bindings - name: Cases description: Create, list, and manage cases and their labels within queues - name: Case Approvals description: Submit decisions on pending case approval requests issued by an agent run - name: Case Attachments description: Upload, list, download, and remove the files attached to a case - name: Automations description: >- List and manage automations — the workspace container that groups the agents and queues making up one end-to-end process - name: Agents description: Create and manage agents for automation workloads - name: Revisions description: Create and manage agent revisions — the underlying Setup for an Agent - name: Agent Folders description: Organize agents into folders - name: Agent Memory description: Read an agent's memory files (the Memory feature in the Duvo UI) - name: Suggestions description: >- List, apply, and dismiss an Agent's improvement suggestions (the suggestions inbox in the Duvo UI) - name: Notifications description: >- List, read, dismiss, and clear the authenticated user's team notifications (the Notification Center in the Duvo UI) - name: Schedules description: List schedules configured for an agent - name: Duvo Pulse description: >- Create, list, iterate on, and delete Duvo Pulse dashboards — live, agent-generated visualizations of your Duvo data - name: Case Triggers description: >- Configure case triggers that automatically dispatch agent runs (Runs in the Duvo UI) for cases added to a queue - name: Triggers description: >- Configure event triggers that start a Run automatically when an external event fires (e.g. an email arrives, a Linear issue is created, or a file changes in Google Drive) - name: Skills description: Manage team and system skills (reusable knowledge packs). - name: Files description: Manage team files. - name: Plugins description: Discover plugins that can be referenced from a revision. - name: Organizations description: Inspect organizations you belong to and the teams within them - name: Team description: Inspect the team and members associated with the API key - name: Invites description: >- Invite people to a team — one at a time or in bulk, scoped to a Clarity process or the whole team — and manage the team's shareable invite link - name: Integrations description: Browse the team's catalog of available integration types - name: Connections description: Manage your connected integrations - name: Credentials description: >- Manage logins (domain + username + password + TOTP) used by agents to sign in to websites and desktop applications, and attach them to assignment revisions - name: Secrets description: >- Manage env-var secrets injected into runs, and attach them to assignment revisions. Only metadata is exposed; values are never returned - name: Revision Integrations description: >- Attach integrations to assignment revisions, pin specific connections, and link queues - name: ClarityV2 description: >- Manage Clarity v2 process snapshots, automation proposals, and the extra-capture-request follow-up loop paths: /v2/automations/{automation_id}/policy: get: tags: - Automations summary: Read Automation Policy description: >- Read an automation's whole Policy before answering anything about it: every question by section, with its `id` (the field id updateConfigField takes), key, type, answer and who gave it; `counts.questions` as the Policy screen's header counts them (`required_open` is what still blocks a run) apart from the module's pre-filled `module_defaults`; answers proposed by interviews and waiting for review; accepted and pending process-context notes; the interviews assigned; and `pending_apply`, the structural answers and notes not yet written into an Agent. `running` says whether the automation runs on live work: there a changed answer reaches its Agents from their next run, so name the question, its current answer and the new one, and change it only after the user says yes. A question whose `bindings` include `structural` changes how the Agents run; propose the matching Agent change too. Never invent an answer for a question shown as open. Give the user the full URLs in `urls`. operationId: readAutomationPolicy parameters: - schema: type: string enum: - 'true' - 'false' in: query name: include_hidden required: false description: >- Also list the questions a person hid, under hidden_fields. Defaults to false. - schema: type: string format: uuid in: path name: automation_id required: true description: Automation ID responses: '200': description: Default Response content: application/json: schema: type: object properties: policy: type: object properties: automation: type: object properties: id: type: string format: uuid description: The automation name: type: string description: The automation's name required: - id - name additionalProperties: false description: The automation this Policy belongs to running: type: boolean description: >- Whether the automation runs on live work: a changed answer is used from its Agents' next run, so confirm each change with the user first sections: type: array items: type: object properties: key: nullable: true description: Null for the questions that sit in no section type: string section: type: string description: The section's name fields: type: array items: type: object properties: id: type: string format: uuid description: >- Pass as the field id to updateConfigField and its siblings key: type: string description: Stable key an Agent's AOP references label: type: string description: Short name of the question question: type: string description: The question as the Policy tab asks it type: type: string enum: - freeText - identifier - number - select - multiSelect - list - orderedList - personList - table - compound - sourcePointer description: What kind of answer it takes options: description: >- The choices of a select or multiSelect question type: array items: {} columns: description: The columns of a table question type: array items: {} origin: type: string enum: - template - added description: >- `template`: shipped with the module. `added`: a person added it customized: type: boolean description: >- A template question someone has edited since install bindings: type: array items: type: string enum: - context - parameter - tool - structural - readOnly description: >- `structural` means its answer changes how the module's Agents run: changing it also needs a matching Agent change required: type: boolean description: An open required question blocks a Run fill_mode: type: string enum: - interview - setup - module_default description: How the question is meant to be answered status: type: string enum: - answered - open description: Whether it has an answer value: nullable: true description: >- The current answer; never invent one for an open question allOf: - $ref: >- #/components/schemas/AutomationPolicyJsonValue provenance: nullable: true description: Who answered it, how and when type: object properties: filled_via: type: string enum: - manual - interview - document - template_default - org_default - ask_duvo description: How the answer was given filled_by_name: nullable: true description: Who gave it, when a person did type: string filled_at: type: string description: When, as an ISO timestamp required: - filled_via - filled_by_name - filled_at additionalProperties: false required: - id - key - label - question - type - origin - customized - bindings - required - fill_mode - status - value - provenance additionalProperties: false description: The section's questions, in Policy order required: - key - section - fields additionalProperties: false description: Every visible question, by section hidden_fields: description: 'Present with include_hidden: questions a person hid' type: array items: type: object properties: id: type: string format: uuid description: The question key: type: string description: Its key label: type: string description: Its short name question: type: string description: The question section: nullable: true description: Its section's name type: string required: - id - key - label - question - section additionalProperties: false counts: type: object properties: questions: type: object properties: answered: type: integer minimum: -9007199254740991 maximum: 9007199254740991 description: Questions with an answer open: type: integer minimum: -9007199254740991 maximum: 9007199254740991 description: Questions without one total: type: integer minimum: -9007199254740991 maximum: 9007199254740991 description: All of them required_open: type: integer minimum: -9007199254740991 maximum: 9007199254740991 description: >- Required questions still open: these block a Run required: - answered - open - total - required_open additionalProperties: false description: >- The team's own questions, as the Policy screen's header counts them module_defaults: type: object properties: filled: type: integer minimum: -9007199254740991 maximum: 9007199254740991 description: Pre-filled values in place open: type: integer minimum: -9007199254740991 maximum: 9007199254740991 description: Ones left empty total: type: integer minimum: -9007199254740991 maximum: 9007199254740991 description: All of them required: - filled - open - total additionalProperties: false description: >- Values the module pre-fills; open ones are not the team's backlog required: - questions - module_defaults additionalProperties: false description: Answered and open counts pending_proposals: type: array items: type: object properties: id: type: string format: uuid description: The proposal field_key: type: string description: The question it answers question: type: string description: That question's text proposed_value: nullable: true description: The proposed answer allOf: - $ref: >- #/components/schemas/AutomationPolicyJsonValue rationale: nullable: true description: Why; null below the role that may read it type: string confidence: description: How sure the extraction was interview_id: nullable: true description: The interview it came from type: string format: uuid interviewee: nullable: true description: >- Who said it; null below the role that may read it type: string required: - id - field_key - question - proposed_value - rationale - confidence - interview_id - interviewee additionalProperties: false description: Answers extracted from interviews, waiting for review context_notes: type: object properties: accepted: type: array items: type: object properties: id: type: string format: uuid description: The note title: type: string description: The note's title note: type: string description: What the note says rationale: nullable: true description: >- The interview's own words; null below the role that may read them type: string source: type: string description: Where the note came from interviewee: nullable: true description: >- Who said it; null below the role that may read it type: string required: - id - title - note - rationale - source - interviewee additionalProperties: false description: Notes accepted into the Policy pending: type: array items: type: object properties: id: type: string format: uuid description: The note title: type: string description: The note's title note: type: string description: What the note says rationale: nullable: true description: >- The interview's own words; null below the role that may read them type: string source: type: string description: Where the note came from interviewee: nullable: true description: >- Who said it; null below the role that may read it type: string required: - id - title - note - rationale - source - interviewee additionalProperties: false description: Notes waiting for review required: - accepted - pending additionalProperties: false description: Process context gathered from interviews interviews: type: array items: type: object properties: id: type: string format: uuid description: The interview invited_email: nullable: true description: Who it was sent to; null for an unassigned slot type: string status: type: string description: Where the interview stands context: nullable: true description: Who the person is, as given when assigning it type: string created_at: type: string description: When it was assigned answers_written: type: integer minimum: -9007199254740991 maximum: 9007199254740991 description: How many Policy answers this interview wrote required: - id - invited_email - status - context - created_at - answers_written additionalProperties: false description: The automation's Policy interviews pending_apply: type: object properties: count: type: integer minimum: -9007199254740991 maximum: 9007199254740991 description: How many items wait fields: type: array items: type: object properties: key: nullable: true description: The question's key type: string question: type: string description: The question value: nullable: true description: The answer to write in allOf: - $ref: >- #/components/schemas/AutomationPolicyJsonValue required: - key - question - value additionalProperties: false description: Structural answers waiting notes: type: array items: type: object properties: id: type: string format: uuid description: The note title: type: string description: Its title required: - id - title additionalProperties: false description: Accepted notes waiting required: - count - fields - notes additionalProperties: false description: >- Structural answers and accepted notes not yet written into an Agent build links: type: object properties: overview: type: string description: Root-relative path that opens this tab process: type: string description: Root-relative path that opens this tab past_runs: description: >- The Past Runs tab. A Module automation has none: its Runs are on each Agent, opened from agents_queues type: string requests: description: >- The Requests tab: the questions and approvals this automation's runs raised, and answering them type: string policy: type: string description: Root-relative path that opens this tab people: description: >- The People tab: the process roles, meaning who runs, reviews and manages the work. Its own tab, not part of Policy type: string agents_queues: description: >- The Automation tab: its Agents, Queues and the flow between them type: string revisions: description: >- The Revisions tab. A Module automation has none: say so, and do not point to another tab or to the Agents for revision history type: string setup: type: string description: Root-relative path that opens this tab setup_start: type: string description: Root-relative path that opens this tab upload_files: type: string description: Root-relative path that opens this tab interview: type: string description: Root-relative path that opens this tab automation_proposal: type: string description: Root-relative path that opens this tab dashboards: type: array items: type: object properties: artifact_id: type: string format: uuid description: The dashboard name: type: string description: The dashboard's tab label link: type: string description: Root-relative path that opens this tab required: - artifact_id - name - link additionalProperties: false description: >- One link per dashboard on this automation's tab bar required: - dashboards additionalProperties: false description: Root-relative paths of the automation's tabs urls: type: object properties: overview: type: string description: Root-relative path that opens this tab process: type: string description: Root-relative path that opens this tab past_runs: description: >- The Past Runs tab. A Module automation has none: its Runs are on each Agent, opened from agents_queues type: string requests: description: >- The Requests tab: the questions and approvals this automation's runs raised, and answering them type: string policy: type: string description: Root-relative path that opens this tab people: description: >- The People tab: the process roles, meaning who runs, reviews and manages the work. Its own tab, not part of Policy type: string agents_queues: description: >- The Automation tab: its Agents, Queues and the flow between them type: string revisions: description: >- The Revisions tab. A Module automation has none: say so, and do not point to another tab or to the Agents for revision history type: string setup: type: string description: Root-relative path that opens this tab setup_start: type: string description: Root-relative path that opens this tab upload_files: type: string description: Root-relative path that opens this tab interview: type: string description: Root-relative path that opens this tab automation_proposal: type: string description: Root-relative path that opens this tab dashboards: type: array items: type: object properties: artifact_id: type: string format: uuid description: The dashboard name: type: string description: The dashboard's tab label link: type: string description: Root-relative path that opens this tab required: - artifact_id - name - link additionalProperties: false description: >- One link per dashboard on this automation's tab bar required: - dashboards additionalProperties: false description: '`links` as full web-app URLs; give these to the user' required: - automation - running - sections - counts - pending_proposals - context_notes - interviews - pending_apply - links - urls additionalProperties: false description: The automation's whole Policy required: - policy additionalProperties: false '400': description: Default Response content: application/json: schema: type: object properties: error: type: string required: - error additionalProperties: false '401': description: Default Response content: application/json: schema: type: object properties: error: type: string required: - error additionalProperties: false '403': description: Default Response content: application/json: schema: type: object properties: error: type: string required: - error additionalProperties: false '404': description: Default Response content: application/json: schema: type: object properties: error: type: string required: - error additionalProperties: false '500': description: Default Response content: application/json: schema: type: object properties: error: type: string required: - error additionalProperties: false security: - bearerAuth: [] components: schemas: AutomationPolicyJsonValue: anyOf: - type: string nullable: true - type: number - type: boolean - type: array items: $ref: '#/components/schemas/AutomationPolicyJsonValue' - type: object additionalProperties: $ref: '#/components/schemas/AutomationPolicyJsonValue' nullable: true securitySchemes: bearerAuth: type: http scheme: bearer description: API key authentication. Get your API key from the Duvo dashboard. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.