> ## 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. # Create Automation > Create a new automation. Its first agent is created alongside it so the caller lands on something editable; `first_agent` seeds that agent's name, configuration, and connections instead of the defaults. On a team on revision semantics the automation holds a single draft revision and no live revision, with the agent's first build bound into that draft, and the first activation makes the draft revision 1; on any other team the automation is a bare container and the build stands on its own. ## OpenAPI ````yaml https://api.duvo.ai/v2/documentation/mintlify.json post /v2/teams/{teamId}/automations 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/teams/{teamId}/automations: post: tags: - Automations summary: Create Automation description: >- Create a new automation. Its first agent is created alongside it so the caller lands on something editable; `first_agent` seeds that agent's name, configuration, and connections instead of the defaults. On a team on revision semantics the automation holds a single draft revision and no live revision, with the agent's first build bound into that draft, and the first activation makes the draft revision 1; on any other team the automation is a bare container and the build stands on its own. operationId: createAutomation parameters: - name: teamId in: path required: true schema: type: string requestBody: required: true content: application/json: schema: type: object properties: name: type: string minLength: 1 maxLength: 100 description: Human-readable automation name. first_agent: description: >- Seeds the automation's first agent, for example from an agent template. Anything left out takes the platform default. type: object properties: name: description: >- Name of the first agent. Defaults to the platform's default agent name. type: string minLength: 1 config: description: >- Configuration of the first agent's build (latest schema version only). Defaults to the platform's default agent configuration. type: object properties: version: type: string enum: - v2 description: >- Schema version discriminator — must be "v2" for the current schema data: type: object properties: models: type: object properties: agent: type: object properties: model: type: string x-extensible-enum: - claude-haiku-4-5-20251001 - claude-sonnet-5 - claude-sonnet-5[1m] - claude-sonnet-5-5 - claude-sonnet-5-5[1m] - claude-opus-5 - claude-opus-5[1m] - claude-opus-5-5 - claude-opus-5-5[1m] - kimi-k3 - kimi-k3-duvo - glm-5.3-flash - deepseek-v4-flash - minimax-m3 - d1-max - duvo-1-max - duvo-1-max-sonnet-1m - duvo-1-max-sonnet-4.5 - duvo-1-max-sonnet-4.5-1m - duvo-1-max-opus - duvo-1-max-opus-4.5 - gpt-4.1 - gpt-4o - gpt-4o-mini - gpt-5 - gpt-5.1 - claude-sonnet-4-20250514 - claude-sonnet-4-20250514[1m] - claude-sonnet-4-5-20250929 - claude-sonnet-4-5-20250929[1m] - claude-sonnet-4-6 - claude-sonnet-4-6[1m] - claude-opus-4-1-20250805 - claude-opus-4-5-20251101 - claude-opus-4-6 - claude-opus-4-6[1m] - claude-opus-4-7 - claude-opus-4-7[1m] - claude-opus-4-8 - claude-opus-4-8[1m] - glm-5.2 - qwen3.6-27b - qwen3.8-max description: >- Model identifier used for the primary agent loop (Claude, or an OSS model when the team's oss_models flag — or oss_models_public for the public subset — is enabled) required: - model description: Primary agent model configuration browsing: type: object properties: provider: type: string enum: - google - anthropic description: >- Provider backing the browsing/computer-use model model: type: string enum: - gemini-2.5-pro - gemini-2.5-flash - gemini-3-pro-preview - claude-haiku-4-5 - claude-sonnet-4-5 - claude-opus-4-1 description: >- Model identifier for the browsing provider required: - provider - model description: Browsing/computer-use model configuration required: - agent - browsing description: >- Model configuration for each capability the agent uses input: anyOf: - type: string - type: array items: type: object properties: role: type: string enum: - system - user - assistant content: anyOf: - type: string - type: array items: anyOf: - type: object properties: type: type: string enum: - input_text text: type: string required: - type - text - type: object properties: type: type: string enum: - input_image detail: nullable: true type: string enum: - low - high - auto file_id: type: string nullable: true url: type: string nullable: true required: - type - type: object properties: type: type: string enum: - input_file file_id: type: string required: - type - file_id type: nullable: true type: string enum: - message required: - role - content description: >- Initial agent instructions — either a single system prompt string or a list of structured messages files: default: [] description: >- Team files that should be available to the agent, each given as the relative file path returned in the `path` field of `GET /v2/teams/{teamId}/files` (for example `report.md` or `folder/doc.md`) — not the `id` field, which is a GCS object identifier. nullable: true type: array items: type: string skills: default: [] description: >- IDs of skills (team or system) that should be available to the agent nullable: true type: array items: type: string plugins: default: [] description: >- Plugins to load — either a built-in plugin name (e.g. "code-review") or a GitHub URL (e.g. "https://github.com/owner/repo") nullable: true type: array items: type: string subAgents: default: [] description: >- Retired — Sub-Assignments was removed. Accepted for backwards compatibility and ignored. nullable: true type: array items: type: string format: uuid options: description: >- Optional runtime options controlling how the agent executes type: object properties: browserProvider: description: Browser infrastructure provider type: string enum: - browserbase - browser-use evaluationSchemaId: description: >- ID of the evaluation schema to apply to runs of this agent type: string benchmarkExpectedOutcomes: description: >- Expected outcomes used when running benchmark scenarios type: array items: type: object properties: description: type: string description: >- Human-readable description of the expected outcome criteria: type: string description: >- Pass/fail criteria used to evaluate the outcome required: - description - criteria supervisedMode: description: >- Run the agent under Duvo's permission classifier: every tool call is classified as allow/deny/ask, with 'ask' routed to human-in-the-loop approval. Mutually exclusive with browsing and computer-use connections. type: boolean additionalProperties: {} required: - models - input description: Agent configuration payload required: - version - data integration_slugs: description: >- Connection types to attach to the first agent's build, in place of the platform's default connections. A type the team has no connection for is skipped. type: array items: type: string enum: - googlecalendar - google-calendar - gmail - slack - googledocs - googlesheets - googledrive - firecrawl - exa - exa-search - exa-company-search - exa-people-search - deep-research - system - browser-agent - browser-agent-devtools - notion - linear - confluence - custom_mcp - user_mcp - snowflake - sharepoint - teams - onedrive - bigquery - databricks - netsuite - outlook - microsoft-calendar - excel - word - saps4hana - md365 - businesscentral - oraclefusion - workday - coupa - signavio - sap-ecc - msteams - human-in-the-loop - email-attachments-reader - document-processor - google-docs - google-sheets - google-drive - outbound-call - case-queue-producer - case-queue-consumer - handover - shopify - hubspot - zendesk - intercom - powerbi - salesforce - pipedrive - tableau - image-generation - forecasting - supabase - attio - amplitude - websets - firecrawl-platform - duvo-computer-use - duvo-computer-use-rdp - eu-commodity-prices - asana - jira - ssh - scheduling - github - linear-native - notion-native - granola - apify - bamboohr - edi - maersk - infor-nexus - dhl - fedex - ups - dsv - trinity-logistics - ontrac - dachser - hellmann - omni-logistics - ceva-logistics - dpd - canada-post - o9 - manhattan - blue-yonder required: - name responses: '201': description: Default Response content: application/json: schema: type: object properties: automation: type: object properties: id: type: string format: uuid name: type: string agent_count: type: integer minimum: -9007199254740991 maximum: 9007199254740991 queue_count: type: integer minimum: -9007199254740991 maximum: 9007199254740991 created_at: type: string updated_at: type: string folder_id: default: null description: >- The agent folder this automation sits in, or null when it sits at the root. Automations reuse the team's existing agent_folder tree rather than a parallel one, so a converted team keeps the grouping it already had. Defaulted rather than required for the same reason is_setting_up is: the client parses this response, and a backend that predates the column must not throw and take the automation's name down with it. nullable: true type: string pinned_at: default: null description: >- When the calling user pinned this automation to the top of their Automations list, or null when they have not. A pin is per user, like an Agent pin: teammates each keep their own. Defaulted rather than required for the same reason folder_id is. nullable: true type: string is_setting_up: default: false description: >- True while this Module automation's setup is under way. setup_started_at is stamped when the team starts setting up (and again by reopen-setup) and cleared when setup finishes, so this reads as currently in setup, not as a record of a past one. Read together with is_demo, which lives on the detail response: both true is a demo with a build under way; is_demo alone is a demo nobody has begun. On the summary rather than the detail so that a client holding only a list, create or patch response knows the state too, and so every write onto the shared automation collection carries it. Defaulted rather than required: the client parses this response, so a backend that predates the column must not throw and take the automation's name down with it, and nothing on the wire has always meant an automation nobody has set up. type: boolean setup_step: default: null description: >- The key of the latest confirmed setup step, null until Start Setup is pressed. The server only ever advances it forward, so reopening a setup can resume where the team got to. Cleared with the rest of the setup state when setup finishes. nullable: true type: string setup_build_chat_id: default: null description: >- The Ask Duvo chat building the automation from the approved proposal, or null while setup has not reached the build. Not a hard reference: the chat can be deleted while this still names it, which the client reads as no build yet. nullable: true type: string format: uuid setup_progress: default: null description: >- The setup facts behind the tile's Setup badge — captures uploaded, the team's own process map generated, a proposal written — or null while the automation is not being set up (and whenever it has no module process for the facts to hang off). nullable: true type: object properties: has_captures: type: boolean has_process_map: type: boolean has_proposal: type: boolean required: - has_captures - has_process_map - has_proposal additionalProperties: false viewer_can_edit: description: >- Whether the caller may change this automation. An automation takes its agents' ownership rule: a Builder may edit one whose every agent they created, and Lead Builder or above may edit any. Sent by the list and detail endpoints; absent from create and update responses, where the client falls back to the caller's role. type: boolean required: - id - name - agent_count - queue_count - created_at - updated_at - folder_id - pinned_at - is_setting_up - setup_step - setup_build_chat_id - setup_progress additionalProperties: false draft_revision_id: nullable: true description: >- The draft revision the new automation was created with, or null when the team isn't on revision semantics and the automation is a bare container. A manually created automation has no live revision until it is first activated, so this is where its first agent build belongs. type: string format: uuid first_agent_id: type: string format: uuid description: >- The automation's first agent, created alongside it with its first build bound into the draft revision, so the caller can open it directly. required: - automation - draft_revision_id - first_agent_id 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 '500': description: Default Response content: application/json: schema: type: object properties: error: type: string required: - error additionalProperties: false security: - bearerAuth: [] components: 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.