> ## 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. # Get Clarity Process > Get the v2 read model for a clarity process: the process row (with operational fields like generation_error, generation_progress, generation_started_at, generation_last_activity_at, custom_prompt), its captures, and the lightweight version arrays for both snapshot tabs. The full payload of any specific snapshot is fetched lazily via the unified per-snapshot detail endpoint (`GET .../snapshots/:kind/:id`); this read model deliberately doesn't carry it so the response stays small. ## OpenAPI ````yaml https://api.duvo.ai/v2/documentation/mintlify.json get /v2/clarity-v2/processes/{process_id} 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/clarity-v2/processes/{process_id}: get: tags: - ClarityV2 summary: Get Clarity Process description: >- Get the v2 read model for a clarity process: the process row (with operational fields like generation_error, generation_progress, generation_started_at, generation_last_activity_at, custom_prompt), its captures, and the lightweight version arrays for both snapshot tabs. The full payload of any specific snapshot is fetched lazily via the unified per-snapshot detail endpoint (`GET .../snapshots/:kind/:id`); this read model deliberately doesn't carry it so the response stays small. operationId: getClarityProcess parameters: - schema: default: full type: string enum: - full - lite in: query name: captures required: false description: >- Capture payload mode. `full` (default) embeds each capture's transcript content. `lite` omits `transcript`/`videoTranscript` (returned as null) and relies on the `hasTranscript`/`hasVideoTranscript` flags; fetch content on demand via `GET .../captures/:capture_id`. - schema: type: string format: uuid in: path name: process_id required: true description: The clarity process id responses: '200': description: Default Response content: application/json: schema: type: object properties: process: type: object properties: id: type: string format: uuid description: Clarity process id team_id: type: string format: uuid description: Owning team id user_id: type: string format: uuid description: Creator user id name: type: string description: Process name status: type: string enum: - draft - collecting - generating - generating-current-process - generating-transformation-proposal - review - complete - generation_failed description: Lifecycle status visibility: type: string enum: - team - restricted description: >- Process visibility. 'team' is workspace-visible to full members; 'restricted' is visible to the creator, org admins, workspace managers/admins, and accepted grant holders. version: type: integer minimum: -9007199254740991 maximum: 9007199254740991 description: Schema version (always 2 here) generation_error: nullable: true description: >- Error message from the most recent failed generation, if any type: string generation_progress: nullable: true description: >- Live progress checklist while a generation is in flight; null otherwise. Field names inside the payload are camelCase, matching the legacy v1 generation-progress shape. type: object properties: steps: type: array items: type: object properties: key: type: string label: type: string status: type: string enum: - pending - in_progress - complete order: type: number count: type: number required: - key - label - status - order additionalProperties: false required: - steps additionalProperties: false generation_started_at: default: null description: >- ISO 8601 timestamp for the most recent generation kickoff; useful for generation-duration reporting nullable: true type: string format: date-time generation_last_activity_at: default: null description: >- ISO 8601 timestamp of the latest process or message activity while generation is in flight; use it for stale-generation detection nullable: true type: string format: date-time custom_prompt: nullable: true description: User-supplied custom prompt that steers generation type: string independent_interviews: default: false description: >- When true, each interview starts fresh: no briefing from earlier interviews and no context from other people's captures type: boolean created_at: type: string description: ISO 8601 creation timestamp updated_at: type: string description: ISO 8601 last-update timestamp required: - id - team_id - user_id - name - status - visibility - version - generation_error - generation_progress - generation_started_at - generation_last_activity_at - custom_prompt - independent_interviews - created_at - updated_at additionalProperties: false current_process_versions: type: array items: type: object properties: id: type: string format: uuid description: Snapshot id process_id: type: string format: uuid description: Parent clarity_process id parent_current_process_id: nullable: true description: >- Parent current-process snapshot this draft forked from type: string format: uuid created_at: type: string description: ISO 8601 creation timestamp version_number: type: integer exclusiveMinimum: true maximum: 9007199254740991 description: >- 1-based position of this snapshot in the process's full chronological history for its kind, counted over every non-deleted row — not the row's index in the returned page. status: type: string enum: - live - historic - draft - generating description: >- Versioning state. Only one 'live' row per process at a time; drafts may be edited or generating before promotion. creator_type: type: string x-extensible-enum: - human - ai - seed description: >- Whether this row was created by a user edit ('human'), an AI pipeline run ('ai'), or a module template's seeded document ('seed'). The value set may grow; see x-extensible-enum. user_id: nullable: true description: >- Creator user id (the human who edited or triggered the run). type: string format: uuid sandbox_id: nullable: true description: >- E2B sandbox id that produced AI rows; null for user edits. type: string last_session_id: nullable: true description: >- Claude SDK session id for artifact-chat follow-up reuse. type: string user_email: description: >- Email of the creator user, resolved from `user_id`; null when the user is unknown or was deleted. nullable: true type: string required: - id - process_id - parent_current_process_id - created_at - version_number - status - creator_type - user_id - sandbox_id - last_session_id additionalProperties: false description: >- The newest page of non-deleted current-process snapshots, newest first (at most CLARITY_VERSIONS_PAGE_SIZE rows). Lightweight rows (no `data`) for the version-picker UI. Clients lazy-fetch the live (or selected) snapshot via the per-snapshot detail endpoint, and page the older history from the snapshots list endpoint. current_process_versions_total: type: integer minimum: 0 maximum: 9007199254740991 description: >- Total non-deleted current-process snapshots for this process. Compare against the embedded array's length to tell whether older versions remain to be paged in. transformation_proposal_versions: type: array items: type: object properties: id: type: string format: uuid description: Proposal id process_id: type: string format: uuid description: Parent clarity_process id clarity_current_process_id: type: string format: uuid description: >- The current-process snapshot this proposal was generated against (provenance only; the live proposal can target any current-process snapshot). parent_transformation_proposal_id: nullable: true description: >- Parent automation proposal snapshot this draft forked from type: string format: uuid created_at: type: string description: ISO 8601 creation timestamp version_number: type: integer exclusiveMinimum: true maximum: 9007199254740991 description: >- 1-based position of this snapshot in the process's full chronological history for its kind, counted over every non-deleted row — not the row's index in the returned page. status: type: string enum: - live - historic - draft - generating description: >- Versioning state. Only one 'live' row per process at a time; drafts may be edited or generating before promotion. creator_type: type: string x-extensible-enum: - human - ai - seed description: >- Whether this row was created by a user edit ('human'), an AI pipeline run ('ai'), or a module template's seeded document ('seed'). The value set may grow; see x-extensible-enum. user_id: nullable: true description: >- Creator user id (the human who edited or triggered the run). type: string format: uuid sandbox_id: nullable: true description: >- E2B sandbox id that produced AI rows; null for user edits. type: string last_session_id: nullable: true description: >- Claude SDK session id for artifact-chat follow-up reuse. type: string user_email: description: >- Email of the creator user, resolved from `user_id`; null when the user is unknown or was deleted. nullable: true type: string extra_capture_requests: description: >- Active extra-capture requests for this proposal. Populated only on the live proposal version row in the read-model endpoint so the FE can render assignment UI without a second round-trip; historic versions return an empty array. Other endpoints (e.g. admin snapshot views) may omit it entirely, in which case it is `undefined`. The standalone list endpoint stays the source of truth for paginated/admin views. type: array items: type: object properties: id: type: string format: uuid description: Extra-capture-request id proposal_id: type: string format: uuid description: >- The automation proposal this request belongs to step_id: type: string description: Step id within the proposal's BPMN graph capture_id: nullable: true description: >- Capture that fulfilled this request, once one is created type: string format: uuid requested_user_id: nullable: true description: Assigned team member, if any type: string format: uuid status: type: string enum: - requested - captured - resolved description: Lifecycle status of the request gap: type: string description: Plain-language gap blocking automation suggested_prompt: nullable: true description: LLM-produced suggested capture prompt type: string suggested_person: nullable: true description: >- Process person nominated to fill this gap in a follow-up interview, if the agent could identify one type: object properties: id: type: string format: uuid description: The suggested clarity_process_person id user_id: nullable: true description: >- The Duvo user this person maps to, if a team member type: string format: uuid name: nullable: true description: Display name of the suggested person type: string role: nullable: true description: >- Role of the suggested person within the process, if known type: string reason: nullable: true description: >- One-line rationale for why this person can fill the gap type: string required: - id - user_id - name - role - reason additionalProperties: false priority: type: string enum: - low - medium - high description: Priority of fulfilling this request created_at: type: string description: ISO 8601 creation timestamp updated_at: type: string description: ISO 8601 last-update timestamp required: - id - proposal_id - step_id - capture_id - requested_user_id - status - gap - suggested_prompt - suggested_person - priority - created_at - updated_at additionalProperties: false required: - id - process_id - clarity_current_process_id - parent_transformation_proposal_id - created_at - version_number - status - creator_type - user_id - sandbox_id - last_session_id additionalProperties: false description: >- The newest page of non-deleted automation proposal snapshots, newest first (at most CLARITY_VERSIONS_PAGE_SIZE rows). Lightweight rows (no `data`) for the version-picker UI. transformation_proposal_versions_total: type: integer minimum: 0 maximum: 9007199254740991 description: >- Total non-deleted automation proposal snapshots for this process. removed_captures: description: >- Usable captures removed since each live snapshot was generated. Counts are scoped to base captures or the live proposal's linked captures; deleted content is never returned. type: object properties: current_process: type: integer minimum: 0 maximum: 9007199254740991 transformation_proposal: type: integer minimum: 0 maximum: 9007199254740991 required: - current_process - transformation_proposal additionalProperties: false captures: type: array items: type: object properties: id: type: string format: uuid processId: type: string format: uuid userId: type: string format: uuid userName: type: string type: type: string x-extensible-enum: - video - interview - document - screenshare - meeting - image videoUrl: type: string nullable: true videoTranscript: type: string nullable: true documentFileName: type: string nullable: true documentTextMetadata: nullable: true type: object properties: pages: type: array items: type: object properties: pageNumber: type: integer exclusiveMinimum: true maximum: 9007199254740991 startOffset: type: integer minimum: 0 maximum: 9007199254740991 endOffset: type: integer minimum: 0 maximum: 9007199254740991 lines: type: array items: type: object properties: pageNumber: type: integer exclusiveMinimum: true maximum: 9007199254740991 lineNumber: type: integer exclusiveMinimum: true maximum: 9007199254740991 startOffset: type: integer minimum: 0 maximum: 9007199254740991 endOffset: type: integer minimum: 0 maximum: 9007199254740991 required: - pageNumber - lineNumber - startOffset - endOffset additionalProperties: false required: - pageNumber - startOffset - endOffset - lines additionalProperties: false sourceArtifactGeneration: type: string required: - pages additionalProperties: false processingFailureReason: nullable: true type: string maxLength: 500 transcript: nullable: true type: array items: type: object properties: source: type: string enum: - ai - user - interviewer speakerName: type: string message: type: string minLength: 1 timestamp: type: number required: - source - message additionalProperties: false hasTranscript: type: boolean hasVideoTranscript: type: boolean transcriptQuestionCount: type: integer minimum: 0 maximum: 9007199254740991 status: type: string enum: - pending - recording - processing - complete - failed isDistillingPolicy: type: boolean usabilityStatus: default: usable type: string enum: - usable - excluded usabilityReason: default: null nullable: true type: string usabilitySource: default: null nullable: true type: string enum: - agent - interviewee - manager usabilityConfidence: default: null nullable: true type: string enum: - high - medium - low createdAt: type: string format: date-time updatedAt: type: string format: date-time required: - id - processId - userId - type - videoUrl - videoTranscript - transcript - status - usabilityStatus - usabilityReason - usabilitySource - usabilityConfidence - createdAt - updatedAt additionalProperties: false description: >- All captures (videos, interviews, documents) attached to this process. Field names follow the legacy v1 capture wire format (camelCase) so existing capture consumers keep working unchanged. required: - process - current_process_versions - current_process_versions_total - transformation_proposal_versions - transformation_proposal_versions_total - captures additionalProperties: false '401': description: Default Response content: application/json: schema: type: object properties: error: type: string message: type: string required: - error additionalProperties: false '403': description: Default Response content: application/json: schema: type: object properties: error: type: string message: type: string required: - error additionalProperties: false '404': description: Default Response content: application/json: schema: type: object properties: error: type: string message: type: string required: - error additionalProperties: false '500': description: Default Response content: application/json: schema: type: object properties: error: type: string message: 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.