> ## 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. # Preview one contact's agent-written message, streaming the research > Have the sequence's agent write one agent-written step's message for one contact as a preview, researching the contact on the web the way the real first message would, and stream its work as Server-Sent Events. Nobody receives the preview and it costs no credits; it counts against the workspace's daily preview allowance, where a preview that researches counts for more than one that does not. The agent researches only when its research switch is on, the contact has never been researched and the workspace has credits; otherwise it writes from the contact's row and what earlier research found. The same preview asked for again the same day is shown again at no further cost. The first frame is `turn`, carrying the `preview_id` a Stop is sent to; then a `step` frame for each thing the agent did (searching, reading pages, writing, checking), each with its measured duration; then one `result` frame with the message, the agent's confidence, the independent quality score, its reasoning and what the checks found. Failures arrive as an `error` frame, because the stream has already answered 200: reason `not_found` when the sequence, the step or the contact is gone, `limit` when today's preview allowance is spent, `stopped` when the caller stopped it, and no reason for anything else. Closing the connection does not stop the preview; the Stop route does. ## OpenAPI ````yaml /openapi.json post /sequences/{sequence_id}/agent/preview/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: >- The messages a person keeps to send the assistant again: the ones the workspace saved and the ones that ship with the product, with save, rename, edit and delete. name: assistant-prompt - description: >- Granted workspace actions: what the AI Assistant proposed or applied in a conversation, the approve and dismiss decisions on each card, the workspace's approval threshold and default grants, and the eight verbs. name: workspace-actions - 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 outbound agent behind a sequence: the voice it writes in, its per-message prompts, what it wrote and what people told it. name: outbound-agents - 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: >- The Model Context Protocol endpoint: use Oneprofile from Claude Code, Claude Desktop, Cursor or any other MCP client, with an API key as the bearer token. name: mcp - 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: >- 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}/agent/preview/stream/: post: tags: - sequences summary: Preview one contact's agent-written message, streaming the research description: >- Have the sequence's agent write one agent-written step's message for one contact as a preview, researching the contact on the web the way the real first message would, and stream its work as Server-Sent Events. Nobody receives the preview and it costs no credits; it counts against the workspace's daily preview allowance, where a preview that researches counts for more than one that does not. The agent researches only when its research switch is on, the contact has never been researched and the workspace has credits; otherwise it writes from the contact's row and what earlier research found. The same preview asked for again the same day is shown again at no further cost. The first frame is `turn`, carrying the `preview_id` a Stop is sent to; then a `step` frame for each thing the agent did (searching, reading pages, writing, checking), each with its measured duration; then one `result` frame with the message, the agent's confidence, the independent quality score, its reasoning and what the checks found. Failures arrive as an `error` frame, because the stream has already answered 200: reason `not_found` when the sequence, the step or the contact is gone, `limit` when today's preview allowance is spent, `stopped` when the caller stopped it, and no reason for anything else. Closing the connection does not stop the preview; the Stop route does. operationId: stream_outbound_agent_preview parameters: - in: path name: sequence_id required: true schema: format: uuid title: Sequence Id type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/SequenceAgentPreviewRequestSchema' required: true responses: '200': content: text/event-stream: schema: $ref: '#/components/schemas/SequenceAgentPreviewReadSchema' type: string description: >- A stream of Server-Sent Events; the final `result` frame's `data` is the preview message. '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: SequenceAgentPreviewRequestSchema: description: Which message to preview, for which contact. properties: record_id: description: 'The contact: a row of the sequence''s audience table.' format: uuid title: Record Id type: string step_id: description: An agent-written step of this sequence. format: uuid title: Step Id type: string required: - step_id - record_id title: SequenceAgentPreviewRequestSchema type: object SequenceAgentPreviewReadSchema: description: |- One message the agent wrote for one contact as a preview. Nobody receives it. Sender variables such as `{{Sender first name}}` are left in place: they are filled in for whichever mailbox sends the real message. properties: angle: anyOf: - type: string - type: 'null' description: The hook the message leads with. title: Angle body: title: Body type: string cached: description: >- True when the same preview was already written today and is shown again at no further cost. title: Cached type: boolean confidence: anyOf: - $ref: '#/components/schemas/MessageConfidence' - type: 'null' description: >- The agent's own read on whether the message is ready to send unedited. confidence_score: anyOf: - type: integer - type: 'null' description: The same read as a score from 0 to 100. title: Confidence Score confident: anyOf: - type: boolean - type: 'null' description: >- Whether the message would be trusted to send on its own under a sender set to send when confident. title: Confident facts_used: description: The facts about the contact the message is built on. items: type: string title: Facts Used type: array findings: description: >- What the checks noticed: spam phrases, placeholders, claims nobody can back. items: $ref: '#/components/schemas/SequenceAgentPreviewFindingReadSchema' title: Findings type: array insufficient_data: description: >- True when the agent said the contact's row gave it too little to go on. title: Insufficient Data type: boolean kind: $ref: '#/components/schemas/MessageKind' description: Which kind of message the step sends. message_id: description: >- The preview's id; rate it through the agent's feedback like any message. format: uuid title: Message Id type: string quality_score: anyOf: - type: integer - type: 'null' description: >- An independent reviewer's score from 0 to 100 for how well the message is grounded, safe and on topic. title: Quality Score reach: $ref: '#/components/schemas/AgentReach' description: >- `web` when the agent researched the contact on the web for this preview. reasoning: anyOf: - type: string - type: 'null' description: Why the agent wrote what it wrote. title: Reasoning subject: anyOf: - type: string - type: 'null' description: >- The subject; null when the message follows the previous email in its thread. title: Subject required: - message_id - kind - subject - body - confidence - confidence_score - quality_score - confident - reasoning - insufficient_data - facts_used - angle - findings - reach - cached title: SequenceAgentPreviewReadSchema 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 MessageConfidence: description: The writer's own read on whether its message is ready to send unedited. enum: - high - medium - low title: MessageConfidence type: string SequenceAgentPreviewFindingReadSchema: description: One thing the checks noticed about the preview's words. properties: code: title: Code type: string excerpt: anyOf: - type: string - type: 'null' title: Excerpt message: title: Message type: string severity: description: warning (likely hurts) or info (worth knowing). title: Severity type: string required: - code - severity - message title: SequenceAgentPreviewFindingReadSchema type: object MessageKind: description: >- What one written message is, which decides its rules, its length and its channel. enum: - email - linkedin_connection_note - linkedin_message - linkedin_inmail - reply_email - reply_linkedin title: MessageKind type: string AgentReach: description: |- How far a Use AI run may reach beyond the table's own data. The price lever and the budget lever both key on this. ``NONE`` is one plain completion; ``MCP`` runs the research loop against ONLY the org's attached MCP tools (no Firecrawl fees, no page summaries); ``WEB`` is the full web research loop. A run that has both web and MCP executes — and bills — as ``WEB``. enum: - none - mcp - web title: AgentReach type: string 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 securitySchemes: HTTPBearer: scheme: bearer type: http ````