> ## 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. # Ask the AI Assistant > Run one turn. There is no mode to send: the assistant reads the request, and either answers it or proposes columns as suggestions the caller can accept. Which it did comes back as the reply's `mode`. Synchronous rather than streamed — the turn reads the table before the model call and persists the transcript after it, and a streaming route runs without a database session. ## OpenAPI ````yaml /openapi.json post /tables/{table_id}/assistant/conversations/{conversation_id}/messages/ 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: 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: '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 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. 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 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 and interest signals — plus domain-based generation. name: ai-context paths: /tables/{table_id}/assistant/conversations/{conversation_id}/messages/: post: tags: - table-assistant summary: Ask the AI Assistant description: >- Run one turn. There is no mode to send: the assistant reads the request, and either answers it or proposes columns as suggestions the caller can accept. Which it did comes back as the reply's `mode`. Synchronous rather than streamed — the turn reads the table before the model call and persists the transcript after it, and a streaming route runs without a database session. operationId: send_assistant_message parameters: - in: path name: table_id required: true schema: format: uuid title: Table Id type: string - in: path name: conversation_id required: true schema: format: uuid title: Conversation Id type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/AssistantMessageCreateSchema' required: true responses: '201': content: application/json: schema: $ref: '#/components/schemas/AssistantTurnResponseSchema' description: Successful Response '401': content: application/json: schema: $ref: '#/components/schemas/UnauthorizedResponse' description: Unauthorized '403': content: application/json: schema: $ref: '#/components/schemas/ForbiddenResponse' description: Forbidden '404': content: application/json: schema: $ref: '#/components/schemas/NotFoundResponse' description: Table or conversation not found '422': content: application/json: schema: $ref: '#/components/schemas/UnprocessableEntityResponse' description: Invalid request made to the API. '500': content: application/json: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Internal server error. '502': content: application/json: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Bad gateway error. '503': content: application/json: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Service unavailable. security: - HTTPBearer: [] - APIKeyHeader: [] components: schemas: AssistantMessageCreateSchema: description: |- Ask the assistant something. Just the message: there is no mode to pick. Whether this is a column to build or a question to answer is read off the sentence itself, and the answer comes back as the reply's ``mode``. properties: prompt: maxLength: 4000 minLength: 1 title: Prompt type: string required: - prompt title: AssistantMessageCreateSchema type: object AssistantTurnResponseSchema: description: >- What one turn produced. Carries the persisted user message as well as the reply: the panel rendered its own optimistic copy before sending and needs the server's — including its assigned sequence — to reconcile against. properties: assistant_message: $ref: '#/components/schemas/AssistantMessageReadSchema' suggestions: items: $ref: '#/components/schemas/AssistantSuggestionReadSchema' title: Suggestions type: array user_message: $ref: '#/components/schemas/AssistantMessageReadSchema' required: - user_message - assistant_message - suggestions title: AssistantTurnResponseSchema 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 NotFoundResponse: properties: detail: description: The detail of why the resource was not found. title: Detail type: string required: - detail title: NotFoundResponse 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 AssistantMessageReadSchema: description: One message in a conversation. properties: content: title: Content type: string conversation_id: format: uuid title: Conversation Id type: string created_at: format: date-time title: Created At type: string error: anyOf: - type: string - type: 'null' title: Error id: format: uuid title: Id type: string mode: $ref: '#/components/schemas/AssistantMode' result: anyOf: - $ref: '#/components/schemas/AssistantAnalysisResult' - type: 'null' role: $ref: '#/components/schemas/AssistantMessageRole' sequence: title: Sequence type: integer status: $ref: '#/components/schemas/AssistantMessageStatus' required: - id - conversation_id - sequence - role - mode - status - content - error - result - created_at title: AssistantMessageReadSchema type: object AssistantSuggestionReadSchema: description: >- One proposed column, as its card renders it. The credit figures are per-row and for the two batch sizes the card offers, computed server-side so the card never does credit arithmetic of its own. properties: accepted_column_id: anyOf: - format: uuid type: string - type: 'null' title: Accepted Column Id action_key: anyOf: - type: string - type: 'null' title: Action Key column_type: anyOf: - type: string - type: 'null' title: Column Type conversation_id: format: uuid title: Conversation Id type: string created_at: format: date-time title: Created At type: string credit_tenths_per_row: title: Credit Tenths Per Row type: integer description: anyOf: - type: string - type: 'null' title: Description dismissed_reason: anyOf: - type: string - type: 'null' title: Dismissed Reason display_name: title: Display Name type: string id: format: uuid title: Id type: string kind: title: Kind type: string message_id: format: uuid title: Message Id type: string position: title: Position type: integer rationale: anyOf: - type: string - type: 'null' title: Rationale status: $ref: '#/components/schemas/SuggestionStatus' table_id: format: uuid title: Table Id type: string required: - id - table_id - conversation_id - message_id - position - display_name - description - rationale - kind - action_key - column_type - status - accepted_column_id - dismissed_reason - credit_tenths_per_row - created_at title: AssistantSuggestionReadSchema 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 AssistantMode: description: >- What a turn turned out to be. BUILD proposes columns and changes the table's shape, ANALYZE answers a question and changes nothing. Not a switch the user sets: the planner reads the request and decides, because someone who types "how many of these are missing an email" has already said which one they meant, and a toggle that asks them to say it again in the product's vocabulary is a tax on every message for the sake of a classification the model can make. Recorded per MESSAGE rather than per conversation because one thread mixes both — a question about the data, then a column built from the answer — and a single mode stamped across the transcript would misreport its history. enum: - build - analyze title: AssistantMode type: string AssistantAnalysisResult: additionalProperties: false description: >- An analyze turn's rendered result table, as it was shown. The RENDERED result is persisted rather than only the query that produced it: re-running the query a week later answers a different table, and a transcript has to show what it showed. Bounded by the group and measure caps, so the stored JSON cannot grow without limit. properties: columns: items: $ref: '#/components/schemas/AssistantResultColumn' maxItems: 50 title: Columns type: array kind: const: analysis default: analysis title: Kind type: string rows: items: items: anyOf: - type: string - type: number - type: boolean - type: 'null' type: array maxItems: 500 title: Rows type: array scanned_row_count: description: Rows the aggregation covered after filters — the trust number. minimum: 0 title: Scanned Row Count type: integer truncated: description: The rendered table was capped; scanned_row_count is not. title: Truncated type: boolean required: - columns - rows - scanned_row_count - truncated title: AssistantAnalysisResult type: object AssistantMessageRole: description: Who authored a message. enum: - user - assistant title: AssistantMessageRole type: string AssistantMessageStatus: description: >- Whether a turn finished. A crashed turn is persisted FAILED rather than dropped: a reply that never appears reads as a silent product failure, while a failed one the user can see and retry reads as an incident with a cause. enum: - complete - failed title: AssistantMessageStatus type: string SuggestionStatus: description: >- Where a proposed column stands. Note what is absent: previewing ("try on N rows") is NOT a transition. It creates nothing, so the suggestion is still on offer afterwards, and a status that moved on a preview would take the offer away from a user who had only just started evaluating it. SUPERSEDED exists because a follow-up turn re-proposing the same column would otherwise leave two near-identical cards on screen, and the user accepts whichever they happen to click — which is as likely to be the one they asked to change as the one they asked for. enum: - pending - accepted - dismissed - superseded title: SuggestionStatus type: string AssistantResultColumn: additionalProperties: false description: One column of an analyze turn's rendered result table. properties: column_type: $ref: '#/components/schemas/TableColumnType' name: maxLength: 255 title: Name type: string required: - name - column_type title: AssistantResultColumn type: object TableColumnType: description: >- The type a user picks for a table column. Ordered as the picker shows them, which is also the order the groups below run in: text-ish, then numeric, then choice, then structured. enum: - text - paragraph - url - email - image_url - person - select - number - decimal - currency - checkbox - date - multi_select - list - object title: TableColumnType type: string securitySchemes: HTTPBearer: scheme: bearer type: http APIKeyHeader: in: header name: X-API-Key type: apiKey ````