> ## 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. # Propose a revised prompt > Rewrite the agent's prompt from this cycle's verdicts, fixing the rows marked bad without losing the ones marked good. Needs at least one bad row. Only the prompt is proposed — the output shape, model and tools are never machine-written — and every declared {{input}} placeholder is verified to survive before the proposal is shown. ## OpenAPI ````yaml /openapi.json post /agent-training/sessions/{session_id}/propose/ 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: /agent-training/sessions/{session_id}/propose/: post: tags: - agent-training summary: Propose a revised prompt description: >- Rewrite the agent's prompt from this cycle's verdicts, fixing the rows marked bad without losing the ones marked good. Needs at least one bad row. Only the prompt is proposed — the output shape, model and tools are never machine-written — and every declared {{input}} placeholder is verified to survive before the proposal is shown. operationId: propose_training_revision parameters: - in: path name: session_id required: true schema: format: uuid title: Session Id type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/TrainingProposeRequestSchema' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/TrainingSessionReadSchema' 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: Training session not found '409': description: The session is not in a state for this '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': description: The proposal could not be generated '503': content: application/json: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Service unavailable. security: - HTTPBearer: [] - APIKeyHeader: [] components: schemas: TrainingProposeRequestSchema: description: A request for a revised prompt, optionally critiquing a prior proposal. properties: revision_request: default: '' description: What to change about the proposal already on screen. maxLength: 2000 title: Revision Request type: string title: TrainingProposeRequestSchema type: object TrainingSessionReadSchema: description: >- A whole training session, as the reviewer's page polls it. Everything the page needs in one payload: the phase (``status``), the cycle, the rows with their results and critiques, and the pending proposal when there is one. properties: created_at: format: date-time title: Created At type: string cycle: title: Cycle type: integer error: anyOf: - type: string - type: 'null' title: Error id: format: uuid title: Id type: string progress: $ref: '#/components/schemas/TrainingProgressSchema' proposal: anyOf: - $ref: '#/components/schemas/TrainingProposalSchema' - type: 'null' rows: items: $ref: '#/components/schemas/TrainingRowReadSchema' title: Rows type: array saved_agent_id: format: uuid title: Saved Agent Id type: string source_input_mappings: additionalProperties: type: string title: Source Input Mappings type: object source_kind: $ref: '#/components/schemas/TrainingSourceKind' source_table_id: anyOf: - format: uuid type: string - type: 'null' title: Source Table Id status: $ref: '#/components/schemas/TrainingSessionStatus' updated_at: format: date-time title: Updated At type: string required: - id - saved_agent_id - status - cycle - source_kind - source_table_id - source_input_mappings - error - created_at - updated_at - progress - rows - proposal title: TrainingSessionReadSchema 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 TrainingProgressSchema: description: How far the current cycle's run has got. properties: done: title: Done type: integer failed: title: Failed type: integer total: title: Total type: integer required: - total - done - failed title: TrainingProgressSchema type: object TrainingProposalSchema: description: A pending prompt revision, alongside what it would replace. properties: changed: description: False when the model proposed no change at all. title: Changed type: boolean current_prompt: title: Current Prompt type: string proposed_prompt: title: Proposed Prompt type: string required: - current_prompt - proposed_prompt - changed title: TrainingProposalSchema type: object TrainingRowReadSchema: description: >- One training row: its fixed inputs and the current cycle's result. ``verdict`` is this cycle's call on the row, null until the reviewer makes one — which is what lets a reloaded page show the rows already judged. ``feedback`` is the note behind a bad verdict (empty otherwise), and ``prior_feedback`` carries the earlier cycles' verdicts so the reviewer can see what they already asked for before asking again. properties: changed_fields: description: >- Names of the output fields whose answer meaningfully differs from `previous_value`. Compared by what each field holds, so an agent rewording the same paragraph does not count. Empty when nothing moved, and on a row with nothing to compare against. items: type: string title: Changed Fields type: array confidence: anyOf: - $ref: '#/components/schemas/AgentConfidence' - type: 'null' credits_charged: title: Credits Charged type: number cycle: title: Cycle type: integer error: anyOf: - type: string - type: 'null' title: Error error_class: anyOf: - $ref: '#/components/schemas/EnrichmentErrorClass' - type: 'null' feedback: title: Feedback type: string id: format: uuid title: Id type: string inputs: additionalProperties: type: string title: Inputs type: object outcome: anyOf: - $ref: '#/components/schemas/EnrichmentCellOutcome' - type: 'null' position: title: Position type: integer previous_value: description: >- The output that earlier verdict was reacting to, so the reviewer can be shown what the prompt revision moved. title: Previous Value previous_verdict: anyOf: - $ref: '#/components/schemas/TrainingVerdict' - type: 'null' description: >- The verdict this row carried the last time it was judged, on an earlier cycle. Null on the first cycle and on a row never judged. prior_feedback: items: $ref: '#/components/schemas/TrainingFeedbackHistorySchema' title: Prior Feedback type: array reasoning: anyOf: - type: string - type: 'null' title: Reasoning skipped_reason: anyOf: - type: string - type: 'null' title: Skipped Reason sources: items: type: string title: Sources type: array status: $ref: '#/components/schemas/TrainingRowStatus' steps: items: $ref: '#/components/schemas/TrainingStepSchema' title: Steps type: array value: description: The produced value, on success. title: Value verdict: anyOf: - $ref: '#/components/schemas/TrainingVerdict' - type: 'null' required: - id - position - inputs - cycle - status - outcome - error - error_class - skipped_reason - confidence - reasoning - steps - sources - credits_charged - verdict - feedback - prior_feedback title: TrainingRowReadSchema type: object TrainingSourceKind: description: Where a session's training inputs came from. enum: - table - manual title: TrainingSourceKind type: string TrainingSessionStatus: description: |- Where a training session stands — the state the reviewer's screen shows. One enum rather than a separate lifecycle flag and phase, because the phase IS the state: a session is either waiting on the machine (``RUNNING``), waiting on the reviewer (``REVIEWING``, ``PROPOSED``), or finished. Callers never derive the screen from row counts. enum: - running - reviewing - proposed - completed - abandoned title: TrainingSessionStatus 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 AgentConfidence: description: The agent's own read on how solid its final answer is. enum: - high - medium - low title: AgentConfidence type: string EnrichmentErrorClass: description: |- Machine-readable classification of a failed enrichment cell. The class decides everything downstream: whether the executor retries (transient classes) or gives up (terminal ones), what the cell tooltip names, and whether the failure is free — errors never charge, but only a classified error can prove which kind it was. enum: - timeout - rate_limited - provider_error - network - schema_violation - refused - invalid_input - no_data - enrichment_failed - unexpected title: EnrichmentErrorClass type: string EnrichmentCellOutcome: description: |- How one cell's enrichment execution ended. ``SKIPPED`` is a first-class third outcome: the action was deliberately not run (a required input was empty), no work was done, and nothing is charged. enum: - succeeded - failed - skipped title: EnrichmentCellOutcome type: string TrainingVerdict: description: >- The reviewer's call on one row's output. Kept as its own enum rather than reusing the cells' ``up``/``down`` thumbs: a training verdict is a judgement on a worked example, and the two domains are deliberately independent of each other. ``BAD`` always carries a note — a complaint with no explanation gives the prompt rewrite nothing to act on. ``GOOD`` never does: it says the output was right, and the rewrite is told to preserve whatever produced it. enum: - good - bad title: TrainingVerdict type: string TrainingFeedbackHistorySchema: description: One earlier cycle's verdict on the same row. properties: cycle: title: Cycle type: integer feedback: title: Feedback type: string verdict: $ref: '#/components/schemas/TrainingVerdict' required: - cycle - verdict - feedback title: TrainingFeedbackHistorySchema type: object TrainingRowStatus: description: >- How far one training row has got in the CURRENT cycle's run. ``DONE`` means the run settled, not that it succeeded — a row whose agent call failed is still done, and its ``outcome`` says what happened. The reviewer critiques failures too. enum: - pending - running - done title: TrainingRowStatus type: string TrainingStepSchema: description: One research step the agent took on a training row. properties: action: $ref: '#/components/schemas/AgentStepAction' detail: title: Detail type: string duration_ms: anyOf: - type: integer - type: 'null' description: How long the step took; null on records that predate timing. title: Duration Ms observation: title: Observation type: string outcome: $ref: '#/components/schemas/AgentStepOutcome' default: completed description: How the step ended, so a failed or refused step reads as one. thought: anyOf: - type: string - type: 'null' description: The model's stated reasoning for this step; null when not recorded. title: Thought required: - action - detail - observation title: TrainingStepSchema type: object AgentStepAction: description: |- What one agent step did. ``FETCH_PAGE`` is historical: the loop emits ``SCRAPE`` for the same act today, but stored step traces still carry the old value and must keep deserializing, so the member stays. enum: - search - fetch_page - map - scrape - crawl - mcp_tool - finish title: AgentStepAction type: string AgentStepOutcome: description: How one agent step ended — the structured half of its observation. enum: - completed - failed - refused title: AgentStepOutcome type: string securitySchemes: HTTPBearer: scheme: bearer type: http APIKeyHeader: in: header name: X-API-Key type: apiKey ````