> ## Documentation Index > Fetch the complete documentation index at: https://docs.getoneprofile.ai/llms.txt > Use this file to discover all available pages before exploring further. # Draft a whole cadence from a goal, streaming the work > The streaming form of the draft: the same replacement of the graph with AI-drafted steps, sent as Server-Sent Events. The first frame is `turn`, carrying the `generation_id` a Stop is sent to; then a `step` frame for each thing the drafter actually did (`read_context`, `read_documents` when the workspace has any, `plan`, `write_steps`, `finish`), each with its measured duration; then one `result` frame with the sequence as the plain route returns it, sent once the graph is saved. Failures arrive as an `error` frame, because the stream has already answered 200: reason `limit` or `paused` when the workspace's daily AI Assistant allowance refused the draft, `not_found` and `locked` for what the plain route answers 404 and 423 to, `stopped` when the caller stopped it, and no reason for anything else. Counts against the allowance; a stopped or failed draft gives its turn back. Closing the connection does not stop the draft; the Stop route does. ## OpenAPI ````yaml /openapi.json post /sequences/{sequence_id}/generate-campaign/stream/ openapi: 3.1.0 info: contact: email: support@getoneprofile.ai name: Oneprofile Support description: >- REST API reference for Oneprofile, the GTM data layer for your CRM. Manage tables, enrichments, and integrations. Authenticate with an API key to get started. termsOfService: https://www.getoneprofile.ai/terms title: API Reference | Oneprofile version: '0.0' servers: - url: https://api.getoneprofile.ai security: [] tags: - description: >- The docked AI Assistant: its general chat about the workspace and the product, streamed as Server-Sent Events, and the one list of a person's threads across every assistant, with pin, rename, delete and the search-to-table link. name: assistant - description: >- Granted workspace actions: what the AI Assistant proposed or applied in a conversation, the approve, dismiss and undo decisions on each card, the workspace's approval threshold and default grants, and the eight verbs. name: workspace-actions - description: >- The agent builder's saved conversations: threads of prompt edits, the turns recorded on them, and the one-time import from the browser. name: agent-assistant - description: >- The Getting started checklist: a workspace's progress through the six steps from its first people search to its first launched sequence. name: onboarding - description: Sender profiles, connected mailboxes, tags, and the Google connect flow. name: senders - description: The workspace do-not-contact list, enforced before every send. name: suppression - description: >- The workspace's recontact rule: how long before anyone hears from us again. name: contact_cooldown - description: 'Sequence authoring: the graph, the table-backed audience, previews.' name: sequences - description: >- The LinkedIn channel: connecting an account to a sender, its safety limits and history, and the protocol the browser extension speaks. name: linkedin - description: >- The approval queue: everything waiting on a person across every sender and channel, and the workspace's manual or automatic modes per channel. name: outreach - description: 'The unified outreach inbox: threads, replies, labels, events.' name: inbox - description: 'The AI reply layer: workspace settings, drafts, and approval.' name: inbox-ai - description: Notification rules, per-user preferences, and the Slack connection. name: notifications - description: Endpoints for seeing all available integration types. name: integration-types - description: Endpoints for creating and managing integrations. name: integrations - description: Endpoints for the generic OAuth install/claim app-listings engine. name: app-listings - description: Endpoints for creating and managing API keys. name: apikey - description: Endpoints for managing billing and subscription information. name: billing - description: Endpoints for creating and managing tables. name: tables - description: Endpoints for table columns, formula previews, and on-demand column runs. name: table-columns - description: Endpoints for table rows and manual cell edits. name: table-rows - description: Endpoints for observing and cancelling table recompute runs. name: table-runs - description: >- Endpoints for org-shared per-column display preferences: hidden, pinned, width, and colour tint. name: table-ui-prefs - description: >- Endpoints for the org-shared names given to the column tint palette: what this organisation calls each colour. Org-level, not per-table. name: table-column-color-labels - description: >- Endpoints for the enrichment action catalog, model list, presets, draft generation, and saved agents. name: table-enrichments - description: >- Endpoints for teaching a saved agent from example rows: training sessions, per-row feedback, and the proposed prompt to approve. name: agent-training - description: >- The durable audit trail of a table's enrichment actions: configured, edited, run, cancelled, and settled cost. name: table-enrichment-audit-logs - description: Endpoints for saving and applying column templates. name: table-templates - description: Server-sent change feed for a table's grid. name: table-events - description: 'Endpoints for org-shared saved table views: sort, filters, hidden columns.' name: table-views - description: >- The per-table AI Assistant: named conversations, the column suggestions a build turn produces, and the questions an analyze turn answers. name: table-assistant - description: >- Endpoints for PER-USER table preferences: favourites and recently opened. Unlike the rest of the table surface these are personal, so two members of one organisation legitimately see different answers. name: table-user-prefs - description: >- Endpoints for building a table from an uploaded CSV: upload and preview the inferred columns, commit the reviewed mapping, then poll the row load. name: table-imports - description: Endpoint for downloading a table's rows as CSV. name: table-export - description: >- Endpoints for the integration a table imports from: attach and preview it, promote imported fields into columns, and run the import on demand. name: table-sources - description: >- Endpoints for a table's recurring import cadence: set it, pause it, and read the next fire times. name: table-schedules - description: >- Endpoints for pushing a table's rows out to a connected integration: list writable destinations, derive their write capabilities, and map export columns. name: table-writeback - description: >- Endpoints backing a lookup column's setup: the connections whose records a column could read, and the identity fields one record type can be looked up by. name: table-integration-lookup - description: >- Endpoints for sourcing leads from the lead database: count and preview matches, land them in a table, and keep saved searches. Alongside people and company searches, leads can be sourced from buying signals — what a company or person just did — with a catalogue endpoint behind the picker that builds them. name: find-leads - description: >- Endpoints for discovering a domain's subdomains from public certificate logs and landing the results in a table. name: find-subdomains - description: Endpoints for the credit balance meter and usage reporting. name: credits - description: >- Endpoints for the workspace referral program: the shareable link, the friends who joined through it, and claiming a code after signup. name: referral - description: >- Endpoints for the affiliate program's own dashboard: enrolling and claiming a code, the summary, stats and activity feed, the commission ledger, and identity verification and payouts. name: affiliate - description: >- Endpoints for the design partner program's customer surface: whether this workspace is a design partner, the badges its feedback has earned, and sending and reading that feedback. name: design-partner - description: >- Endpoints for the org-level AI business context — company description, ideal customer profile, buyer personas, interest signals and social proof — plus domain-based generation and the reference documents whose summaries ride alongside those fields. name: ai-context - description: >- Endpoints for the signed-in user's Google Drive connection: starting and finishing the OAuth grant, checking or dropping it, and minting the short-lived token the Google Picker needs. name: google-drive paths: /sequences/{sequence_id}/generate-campaign/stream/: post: tags: - sequences summary: Draft a whole cadence from a goal, streaming the work description: >- The streaming form of the draft: the same replacement of the graph with AI-drafted steps, sent as Server-Sent Events. The first frame is `turn`, carrying the `generation_id` a Stop is sent to; then a `step` frame for each thing the drafter actually did (`read_context`, `read_documents` when the workspace has any, `plan`, `write_steps`, `finish`), each with its measured duration; then one `result` frame with the sequence as the plain route returns it, sent once the graph is saved. Failures arrive as an `error` frame, because the stream has already answered 200: reason `limit` or `paused` when the workspace's daily AI Assistant allowance refused the draft, `not_found` and `locked` for what the plain route answers 404 and 423 to, `stopped` when the caller stopped it, and no reason for anything else. Counts against the allowance; a stopped or failed draft gives its turn back. Closing the connection does not stop the draft; the Stop route does. operationId: stream_generate_campaign parameters: - in: path name: sequence_id required: true schema: format: uuid title: Sequence Id type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/GenerateCampaignSchema' required: true responses: '200': content: text/event-stream: schema: $ref: '#/components/schemas/SequenceReadSchema' type: string description: >- A stream of Server-Sent Events; the final `result` frame's `data` is the sequence with its drafted graph. '401': content: text/event-stream: schema: $ref: '#/components/schemas/UnauthorizedResponse' description: Unauthorized '403': content: text/event-stream: schema: $ref: '#/components/schemas/ForbiddenResponse' description: Forbidden '422': content: text/event-stream: schema: $ref: '#/components/schemas/UnprocessableEntityResponse' description: Invalid request made to the API. '500': content: text/event-stream: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Internal server error. '502': content: text/event-stream: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Bad gateway error. '503': content: text/event-stream: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Service unavailable. security: - HTTPBearer: [] components: schemas: GenerateCampaignSchema: description: §CMP-14. One line describing what the campaign is for. properties: goal: maxLength: 1000 minLength: 3 title: Goal type: string required: - goal title: GenerateCampaignSchema type: object SequenceReadSchema: properties: ai_cta_label: anyOf: - type: string - type: 'null' title: Ai Cta Label ai_cta_url: anyOf: - type: string - type: 'null' title: Ai Cta Url ai_goal: anyOf: - type: string - type: 'null' title: Ai Goal ai_language: anyOf: - type: string - type: 'null' title: Ai Language ai_reply_mode: anyOf: - $ref: '#/components/schemas/AiReplyMode' - type: 'null' ai_tone: anyOf: - $ref: '#/components/schemas/AiTone' - type: 'null' ai_translate: anyOf: - type: boolean - type: 'null' title: Ai Translate audience_table_id: anyOf: - format: uuid type: string - type: 'null' title: Audience Table Id audience_view_id: anyOf: - format: uuid type: string - type: 'null' title: Audience View Id bcc_addresses: description: 'SEQ-21: blind copies on every email this sequence sends.' items: type: string title: Bcc Addresses type: array cc_addresses: description: 'SEQ-21: addresses copied on every email this sequence sends.' items: type: string title: Cc Addresses type: array column_mapping: $ref: '#/components/schemas/ColumnMappingSchema' connection_requests_sent: anyOf: - type: integer - type: 'null' title: Connection Requests Sent connections_accepted: anyOf: - type: integer - type: 'null' description: >- SEQ-06: invitations from this sequence confirmed accepted. With connection_requests_sent this yields the acceptance rate. title: Connections Accepted contacts_added: anyOf: - type: integer - type: 'null' description: >- §21 rollup, list reads only. None when the rollup has never run for this org — show a zero state, not a fake 0. title: Contacts Added contacts_failed: anyOf: - type: integer - type: 'null' title: Contacts Failed contacts_finished: anyOf: - type: integer - type: 'null' title: Contacts Finished contacts_in_progress: anyOf: - type: integer - type: 'null' title: Contacts In Progress continuous_enrolment: default: true description: >- TRUE (the default) keeps the audience live: rows added to the table later enrol on their own, and rows that leave it stop. FALSE freezes the audience after launch; Enrol now still adds to it by hand. title: Continuous Enrolment type: boolean created_at: format: date-time title: Created At type: string edges: items: $ref: '#/components/schemas/SequenceEdgeSchema' title: Edges type: array email_approval_mode: anyOf: - type: string - type: 'null' description: >- manual | auto; null inherits the sender's mode, then the workspace's. title: Email Approval Mode emails_sent: anyOf: - type: integer - type: 'null' title: Emails Sent id: format: uuid title: Id type: string last_synced_at: anyOf: - format: date-time type: string - type: 'null' description: >- §20: when the audience-enrolment diff last completed. None until the first sync (launch runs one inline) — the Audience tab shows this plus a manual trigger, never a background job the user cannot see. title: Last Synced At launched_at: anyOf: - format: date-time type: string - type: 'null' title: Launched At linkedin_approval_mode: anyOf: - type: string - type: 'null' description: >- manual | auto; null inherits the sender's mode, then the workspace's. title: Linkedin Approval Mode linkedin_check_max_seconds: anyOf: - type: integer - type: 'null' title: Linkedin Check Max Seconds linkedin_check_min_seconds: anyOf: - type: integer - type: 'null' title: Linkedin Check Min Seconds linkedin_messages_sent: anyOf: - type: integer - type: 'null' title: Linkedin Messages Sent multithreading: anyOf: - additionalProperties: true type: object - type: 'null' title: Multithreading name: title: Name type: string opportunity_values: anyOf: - additionalProperties: type: integer type: object - type: 'null' description: 'SEQ-23: dollars per outcome label; None = tracking off.' title: Opportunity Values opt_out_footer_text: title: Opt Out Footer Text type: string pause_reason: anyOf: - type: string - type: 'null' title: Pause Reason plain_text_only: default: true description: >- SEQ-16: TRUE (recommended) sends text-only with formatting marks stripped; FALSE sends a multipart/alternative with the marks as HTML. title: Plain Text Only type: boolean positive: anyOf: - type: integer - type: 'null' description: Threads labelled positive (rollup, list reads only). title: Positive positive_rate: anyOf: - type: number - type: 'null' title: Positive Rate replies: anyOf: - type: integer - type: 'null' description: 'SEQ-06: distinct contacts who replied — reply_rate''s numerator.' title: Replies reply_rate: anyOf: - type: number - type: 'null' title: Reply Rate sender_profile_names: description: 'Only meaningful on list reads: the assigned sender profiles'' names.' items: type: string title: Sender Profile Names type: array senders_ready: default: true description: >- Only meaningful on list reads: False when the sequence has assigned sender profiles but none currently has a connected mailbox. title: Senders Ready type: boolean sending_priority: default: new_contacts description: 'SEQ-20: who gets scarce capacity first — new_contacts or follow_ups.' title: Sending Priority type: string sending_window: anyOf: - additionalProperties: true type: object - type: 'null' title: Sending Window status: $ref: '#/components/schemas/SequenceStatus' status_column_id: anyOf: - format: uuid type: string - type: 'null' title: Status Column Id step_count: title: Step Count type: integer steps: items: $ref: '#/components/schemas/SequenceStepSchema-Output' title: Steps type: array updated_at: format: date-time title: Updated At type: string required: - id - name - status - audience_table_id - audience_view_id - column_mapping - status_column_id - sending_window - multithreading - opt_out_footer_text - launched_at - pause_reason - created_at - updated_at - steps - edges - step_count title: SequenceReadSchema type: object UnauthorizedResponse: properties: detail: description: The detail of why the request is unauthorized. title: Detail type: string required: - detail title: UnauthorizedResponse type: object ForbiddenResponse: properties: detail: description: The detail of why the request is forbidden. title: Detail type: string required: - detail title: ForbiddenResponse type: object UnprocessableEntityResponse: properties: detail: description: >- The detail of the error. This is the error message to show to the user. You should also use the issues field to show more detailed error messages per field. Use this field for a single liner error message. title: Detail type: string issues: description: >- The issues that caused the error. There can be multiple issues. Each issue is a user-facing error message. items: $ref: '#/components/schemas/UnprocessableEntityIssue' title: Issues type: array required: - detail - issues title: UnprocessableEntityResponse type: object ServerErrorResponse: properties: detail: description: The detail of why the server returned an error. title: Detail type: string required: - detail title: ServerErrorResponse type: object AiReplyMode: description: >- How far the AI reply layer may go on this sequence. Auto-drafting is PHASE2 §8. OFF is the default everywhere: a workspace opts in. DRAFT_AND_QUEUE is as far as it goes: every draft waits in Needs approval for a person, whatever its confidence. There is deliberately no mode past it. A self-sending auto-pilot shipped as INB-15 and was removed under F-15's ruling that a send cannot be taken back, so nothing may send with nobody present; rows that carried it were moved to DRAFT_AND_QUEUE by the ``retire_auto_send_reply_mode`` release task. A SENT draft with no approver is therefore always history from before that ruling. enum: - 'off' - draft_and_queue title: AiReplyMode type: string AiTone: description: How a generated reply should read. enum: - professional - friendly - direct - casual title: AiTone type: string ColumnMappingSchema: description: >- Which audience columns carry a meaning, all detected from the table. One field per channel (email, LinkedIn, phone) plus the company domain the coverage line reports on. Leave the whole object out when binding an audience and the columns are detected server-side. Send it only to correct a detection: a first name, a company or a last-contacted date is no longer part of this — every column on the table is already addressable as a `{{Column name}}` variable. properties: company_domain_column_id: anyOf: - format: uuid type: string - type: 'null' description: >- The account identity, reported on by the audience coverage counts. Unmapped, the coverage count is zero. title: Company Domain Column Id email_column_id: anyOf: - format: uuid type: string - type: 'null' description: >- Where the send address is read from, and the deduplication key: two rows sharing an address are one contact. title: Email Column Id linkedin_url_column_id: anyOf: - format: uuid type: string - type: 'null' description: Required by LinkedIn steps; a row without one skips them. title: Linkedin Url Column Id phone_column_id: anyOf: - format: uuid type: string - type: 'null' description: >- Required by call steps: the number the call task carries. A sequence with call steps cannot launch without it. title: Phone Column Id title: ColumnMappingSchema type: object SequenceEdgeSchema: properties: branch: $ref: '#/components/schemas/SequenceEdgeBranch' default: default from_step_id: anyOf: - format: uuid type: string - type: 'null' description: None = the start node. title: From Step Id to_step_id: anyOf: - format: uuid type: string - type: 'null' description: None = an end node. title: To Step Id title: SequenceEdgeSchema type: object SequenceStatus: description: >- Lifecycle of a sequence. DRAFT until launch; RUNNING sequences are locked against structural edits (pause → edit → resume); PAUSED stops scheduling while leaving every enrolment exactly where it is; COMPLETED is terminal. enum: - draft - running - paused - completed title: SequenceStatus type: string SequenceStepSchema-Output: properties: agent_subject: default: false description: >- F-26: the agent writes the subject line too. Off, the step's own subject applies, and a blank one still replies in the same thread. title: Agent Subject type: boolean authoring: $ref: '#/components/schemas/StepAuthoring' default: written description: >- F-26: who writes the email. 'written' sends the subject and body below; 'agent' writes the whole email for each contact at send time from `instruction`, the contact's row and the workspace's business context, priced per contact. Email steps only. body_segments: items: $ref: '#/components/schemas/TemplateSegmentSchema' title: Body Segments type: array condition_kind: anyOf: - $ref: '#/components/schemas/SequenceConditionKind' - type: 'null' condition_window_days: anyOf: - maximum: 90 minimum: 1 type: integer - type: 'null' title: Condition Window Days id: format: uuid title: Id type: string instruction: anyOf: - maxLength: 2000 type: string - type: 'null' description: >- F-26: what the agent is told to write. Required when authoring is 'agent'. title: Instruction kind: $ref: '#/components/schemas/SequenceStepKind' position: default: 0 minimum: 0 title: Position type: integer requires_approval: default: false description: >- F-25: hold this step for approval even when its channel would run on its own. One-way: true adds an approval, false never removes the one the channel's resolved mode already wants. title: Requires Approval type: boolean subject_segments: anyOf: - items: $ref: '#/components/schemas/TemplateSegmentSchema' type: array - type: 'null' description: 'None or blank = in-thread follow-up (Re: the previous step).' title: Subject Segments wait_amount: default: 0 maximum: 365 minimum: 0 title: Wait Amount type: integer wait_unit: $ref: '#/components/schemas/SequenceWaitUnit' default: days required: - id - kind title: SequenceStepSchema type: object UnprocessableEntityIssue: properties: input: anyOf: - type: string - type: integer - type: number - type: boolean - items: {} type: array - additionalProperties: true type: object description: The user's input that caused the error. title: Input loc: description: >- The location of the error. Always contains 1 or 2 elements. The first element is the type of location (e.g. 'body', 'query', 'path', 'header'). The second element is the name of the field that caused the error. If the error is not related to a specific field, the second element is not present. items: type: string title: Loc type: array msg: description: The message of the error. The error message to show to the user. title: Msg type: string type: description: >- The type of the error. Useful for frontend code to handle different types of errors. title: Type type: string required: - loc - msg - type - input title: UnprocessableEntityIssue type: object SequenceEdgeBranch: description: DEFAULT for message-step flow; YES/NO for a condition's two branches. enum: - default - 'yes' - 'no' title: SequenceEdgeBranch type: string StepAuthoring: description: >- Who writes an email step's words (F-26). WRITTEN is the default and what every step was before: the author's own subject and body, with variables, snippets and spintax resolved per contact. AGENT holds an instruction instead of a body; the whole email is written for each contact at send time from that instruction, the row and the workspace's written business context, and priced per contact. enum: - written - agent title: StepAuthoring type: string TemplateSegmentSchema: properties: builtin: anyOf: - $ref: '#/components/schemas/BuiltinVariable' - type: 'null' column_id: anyOf: - format: uuid type: string - type: 'null' title: Column Id kind: $ref: '#/components/schemas/SegmentKind' options: description: §CMP-9 spintax alternatives; one is chosen per contact. items: type: string maxItems: 20 title: Options type: array prompt: default: '' description: §CMP-8 AI snippet instruction, resolved per contact at send time. maxLength: 2000 title: Prompt type: string required: default: true title: Required type: boolean text: default: '' title: Text type: string required: - kind title: TemplateSegmentSchema type: object SequenceConditionKind: description: >- The branching conditions. ``BOUNCED`` and ``REPLIED`` are only pickable after a message step exists earlier on the same path — enforced at save, explained in the picker. enum: - has_email - has_linkedin_url - linkedin_connected - bounced - replied - linkedin_invite_accepted - linkedin_open_profile - call_connected title: SequenceConditionKind type: string SequenceStepKind: description: >- What a graph node does. The LINKEDIN_* kinds do not send anything themselves — they enqueue browser work and park the contact until it runs, because the action happens in the customer's own browser and that browser may be closed. CALL sends nothing and runs nothing: it hands a person a task (the number to dial and a brief) and parks the contact until that person records how the call went. The engine cannot dial, so a call step is the one kind whose execution is entirely somebody's hands. enum: - message - condition - linkedin_profile_view - linkedin_connection_request - linkedin_message - linkedin_inmail - linkedin_withdraw_invitation - linkedin_follow - linkedin_like_post - call title: SequenceStepKind type: string SequenceWaitUnit: enum: - days - hours title: SequenceWaitUnit type: string BuiltinVariable: description: |- Non-column variables the composer offers. Weekday variables render the *name* of the day ("Thursday") so a cadence can reference real days without weekly rewrites. enum: - sender_first_name - sender_full_name - sending_domain - sequence_name - greeting - today - yesterday - tomorrow - day_plus_2 - day_plus_3 - day_plus_4 title: BuiltinVariable type: string SegmentKind: description: One piece of a subject or body template. enum: - text - column - builtin - ai - spintax title: SegmentKind type: string securitySchemes: HTTPBearer: scheme: bearer type: http ````