> ## 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.

# Keep threads already written in the sequence's Preview

> Makes the threads already written as free previews for up to ten contacts those contacts' threads in the sequence's Preview, word for word: nothing is written again, nothing is charged and no preview allowance is spent, so each contact's thread there shows the emails the previews showed and Looks good can be given on them. A step with no current preview shows as not written. The contacts join the sequence's open Preview; one already in it with the same words keeps its verdict. This never writes: the start route is what writes a thread. The answer names any kept thread written before the plain-words check that uses banned jargon or copies the business context, so it can be written again.



## OpenAPI

````yaml /openapi.json post /sequences/{sequence_id}/agent/training-contacts/bulk/
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 spend 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: Senders, 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 listing, checking and deleting integrations.
    name: integrations
  - description: >-
      Create, preview and update an integration of any type: the body's
      integration_type picks the config and credentials it takes.
    name: integration-specific
  - 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: >-
      AI apps connected to the workspace: Claude, ChatGPT, Claude Code or any
      other MCP client a person signed in to Oneprofile's MCP server with.
    name: ai_apps
  - description: Endpoints for managing billing and subscription information.
    name: billing
  - description: >-
      Accounts: every company the workspace's tables name, with the people at
      it, its key facts, its tables, its org chart and what went to its people;
      the tables that feed it (Sources) and the merges a person made.
    name: accounts
  - 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 an agent's Preview: example rows run one at a time, and a
      Looks good on each. Needs work lives under agent-learnings.
    name: agent-training
  - description: >-
      An agent's learnings, the one-line rules it follows on every output, and
      the thumbs down that teaches them: give one with what was wrong, list the
      ones on a subject, Undo one, and price the redo it would run.
    name: agent-learnings
  - 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 the webhook URL an app or a tool of your own sends records
      to: what can send them, make the URL, show it again, replace it, revoke
      it, save the app's secrets, resume a paused feed, and read and retry the
      deliveries that did not fit.
    name: table-webhooks
  - 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 recording where a new workspace came from: the marketing
      page or campaign its signup link carried, sent once after signup.
    name: attribution
  - 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/training-contacts/bulk/:
    post:
      tags:
        - sequences
      summary: Keep threads already written in the sequence's Preview
      description: >-
        Makes the threads already written as free previews for up to ten
        contacts those contacts' threads in the sequence's Preview, word for
        word: nothing is written again, nothing is charged and no preview
        allowance is spent, so each contact's thread there shows the emails the
        previews showed and Looks good can be given on them. A step with no
        current preview shows as not written. The contacts join the sequence's
        open Preview; one already in it with the same words keeps its verdict.
        This never writes: the start route is what writes a thread. The answer
        names any kept thread written before the plain-words check that uses
        banned jargon or copies the business context, so it can be written
        again.
      operationId: add_previews_to_sequence_training
      parameters:
        - in: path
          name: sequence_id
          required: true
          schema:
            format: uuid
            title: Sequence Id
            type: string
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SequenceTrainingAdoptSchema'
        required: true
      responses:
        '201':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SequenceTrainingPreviewsReadSchema'
          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':
          description: Sequence, audience contact, or Preview not found
        '409':
          description: Sequence, agent, or Preview revision changed
        '422':
          description: Invalid selection, verdict, or Preview action
        '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:
        - APIKeyHeader: []
        - HTTPBearer: []
components:
  schemas:
    SequenceTrainingAdoptSchema:
      properties:
        record_ids:
          description: >-
            The audience rows whose threads were already written as previews,
            between one and ten different ones.
          items:
            format: uuid
            type: string
          maxItems: 10
          minItems: 1
          title: Record Ids
          type: array
      required:
        - record_ids
      title: SequenceTrainingAdoptSchema
      type: object
    SequenceTrainingPreviewsReadSchema:
      description: >-
        The Preview once it keeps threads already written, and which of them to
        write again.
      properties:
        session:
          $ref: '#/components/schemas/SequenceTrainingReadSchema'
        write_again:
          description: >-
            Contacts whose kept thread was written before the plain-words check
            and uses jargon the writing rules forbid or a business context
            sentence word for word. Writing them again (the step preview with
            fresh) replaces those words; the sequence's Preview shows the thread
            as it is meanwhile.
          items:
            format: uuid
            type: string
          title: Write Again
          type: array
      required:
        - session
        - write_again
      title: SequenceTrainingPreviewsReadSchema
      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
    ServerErrorResponse:
      properties:
        detail:
          description: The detail of why the server returned an error.
          title: Detail
          type: string
      required:
        - detail
      title: ServerErrorResponse
      type: object
    SequenceTrainingReadSchema:
      properties:
        agent_id:
          format: uuid
          title: Agent Id
          type: string
        base_version:
          title: Base Version
          type: integer
        contacts:
          items:
            $ref: '#/components/schemas/SequenceTrainingContactReadSchema'
          title: Contacts
          type: array
        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
        reviewed_ids:
          description: >-
            Every contact given Looks good in this run, including ones that left
            the run to make room.
          items:
            format: uuid
            type: string
          title: Reviewed Ids
          type: array
        revision:
          title: Revision
          type: integer
        status:
          $ref: '#/components/schemas/ContactTrainingStatus'
        steps:
          items:
            $ref: '#/components/schemas/AiStep'
          title: Steps
          type: array
      required:
        - id
        - agent_id
        - status
        - revision
        - base_version
        - contacts
        - error
        - created_at
      title: SequenceTrainingReadSchema
      type: object
    SequenceTrainingContactReadSchema:
      properties:
        context:
          additionalProperties:
            type: string
          title: Context
          type: object
        fields:
          description: >-
            The contact's own columns as the run froze them, read the way the
            approval queue lists a contact: each fact once, a whole-record
            column opened into its facts.
          items:
            $ref: '#/components/schemas/SequenceTrainingContactFieldSchema'
          title: Fields
          type: array
        label:
          title: Label
          type: string
        messages:
          items:
            $ref: '#/components/schemas/SequenceTrainingMessageReadSchema'
          title: Messages
          type: array
        profile_mismatch:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            What the contact's LinkedIn profile says that their row does not,
            usually a job change the row has not caught up with, as one
            sentence: 'LinkedIn says Operations Leader at Chamber Media; the row
            says Sealed.' Null when they agree or no profile was read.
          title: Profile Mismatch
        record_id:
          format: uuid
          title: Record Id
          type: string
        sender_profile_id:
          anyOf:
            - format: uuid
              type: string
            - type: 'null'
          description: >-
            The sender these messages were written as, when the run chose one:
            where a message held because this sender always asks is changed.
          title: Sender Profile Id
        verdict:
          anyOf:
            - $ref: '#/components/schemas/ContactReviewVerdict'
            - type: 'null'
      required:
        - record_id
        - label
        - context
        - fields
        - messages
        - verdict
      title: SequenceTrainingContactReadSchema
      type: object
    ContactTrainingStatus:
      description: A session's phase, also used to resume its review screen.
      enum:
        - running
        - reviewing
        - proposing
        - proposed
        - completed
        - abandoned
      title: ContactTrainingStatus
      type: string
    AiStep:
      additionalProperties: false
      description: >-
        One thing an AI turn did, as the wire spells it.


        Field-for-field identical to
        ``table_live_updates.TableCellActivityStepSchema``

        ON PURPOSE, and the duplication is the design. That schema sits in the
        table

        stratum's kernel, which the lead search, inbox and sequence surfaces
        have no

        business importing; this one sits under every surface equally. Because
        the

        two agree exactly, the frontend's ``TimelineStep`` renders both with no

        conversion and no second component, which is the property worth
        protecting.

        ``test_ai_step_mirrors_the_cell_activity_step`` pins them together.


        Plain strings rather than enums, for the same reason the cell schema
        uses

        them: the vocabulary is open, clients must tolerate tokens they have not

        learned yet, and a new action should never be able to break a running

        dashboard.
      properties:
        action:
          description: >-
            What kind of move this was, e.g. `read_table`, `plan`,
            `write_column`.
          title: Action
          type: string
        detail:
          default: ''
          description: >-
            The step's input: the instruction, the column it read, the query it
            ran.
          title: Detail
          type: string
        duration_ms:
          anyOf:
            - type: integer
            - type: 'null'
          description: Wall clock for the work this step describes, never an estimate.
          title: Duration Ms
        observation:
          default: ''
          description: >-
            One line on what came back. The half that makes a step worth
            reading.
          maxLength: 500
          title: Observation
          type: string
        outcome:
          default: completed
          description: >-
            `completed`, `failed`, `refused` or `stopped`. Clients must tolerate
            new tokens.
          title: Outcome
          type: string
        thought:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            The model's stated reasoning for choosing this step. Set by the
            agent loop; the assistant surfaces leave it null, and the renderer
            simply omits the rung.
          title: Thought
      required:
        - action
      title: AiStep
      type: object
    SequenceTrainingContactFieldSchema:
      properties:
        name:
          title: Name
          type: string
        value:
          title: Value
          type: string
      required:
        - name
        - value
      title: SequenceTrainingContactFieldSchema
      type: object
    SequenceTrainingMessageReadSchema:
      properties:
        authored:
          title: Authored
          type: boolean
        body:
          anyOf:
            - type: string
            - type: 'null'
          title: Body
        conditional:
          anyOf:
            - type: string
            - type: 'null'
          title: Conditional
        error:
          anyOf:
            - type: string
            - type: 'null'
          title: Error
        facts_used:
          items:
            type: string
          title: Facts Used
          type: array
        id:
          format: uuid
          title: Id
          type: string
        kind:
          title: Kind
          type: string
        looks_good:
          default: false
          description: >-
            These very words are marked Looks good, so they are what sends: by
            the thread's Looks good, or on their own from the Builder, which
            marks one email at a time.
          title: Looks Good
          type: boolean
        own_words:
          anyOf:
            - $ref: '#/components/schemas/SequenceTrainingOwnWordsSchema'
            - type: 'null'
          description: >-
            The words a person typed for this contact on this step, which send
            in place of the agent's. Null when the agent's words are what sends.
        reasoning:
          anyOf:
            - type: string
            - type: 'null'
          title: Reasoning
        reply_to_step_id:
          anyOf:
            - format: uuid
              type: string
            - type: 'null'
          description: >-
            The step whose thread this message replies in, or null when it opens
            a thread of its own.
          title: Reply To Step Id
        send:
          anyOf:
            - $ref: '#/components/schemas/SequenceTrainingSendSchema'
            - type: 'null'
          description: >-
            Whether the agent's words would send on their own or wait for
            approval, under the sequence's settings as they stand. Null for a
            message a person typed, one not written, or when nothing would send
            it (no sender, no LinkedIn account).
        send_after_hours:
          anyOf:
            - type: integer
            - type: 'null'
          description: >-
            Hours after the contact is added at which this message goes, along
            the no-reply path, before the sending window moves it to an open
            hour. Null for a step off the path, and on a Preview written before
            it was recorded.
          title: Send After Hours
        steps:
          items:
            $ref: '#/components/schemas/AiStep'
          title: Steps
          type: array
        subject:
          anyOf:
            - type: string
            - type: 'null'
          title: Subject
        timing:
          title: Timing
          type: string
        title:
          title: Title
          type: string
      required:
        - id
        - title
        - timing
        - kind
        - authored
        - conditional
        - subject
        - body
        - error
        - reasoning
        - facts_used
        - steps
        - reply_to_step_id
      title: SequenceTrainingMessageReadSchema
      type: object
    ContactReviewVerdict:
      description: >-
        What a person said about one contact's whole thread.


        BAD is no longer given here (Agent Learnings, 2026-10-20): Needs work is
        a thumbs down,

        which saves a learning and writes the thread again with no verdict on
        it. It stays for

        the sessions saved with one.
      enum:
        - good
        - bad
        - skipped
      title: ContactReviewVerdict
      type: string
    SequenceTrainingOwnWordsSchema:
      properties:
        body:
          title: Body
          type: string
        subject:
          anyOf:
            - type: string
            - type: 'null'
          title: Subject
      required:
        - subject
        - body
      title: SequenceTrainingOwnWordsSchema
      type: object
    SequenceTrainingSendSchema:
      description: >-
        Whether a message would leave on its own when its turn comes, and if
        not, why.
      properties:
        alone:
          description: >-
            True when the send would let these words go without a person; false
            when they would wait for approval in Tasks.
          title: Alone
          type: boolean
        doubt:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            When the words themselves hold the message (the agent did not rate
            them high, or knew too little): the agent's reason for its rating.
            Null otherwise.
          title: Doubt
        reason:
          anyOf:
            - $ref: '#/components/schemas/AskReason'
            - type: 'null'
          description: >-
            Why they would wait, in the approval queue's own reasons; null when
            alone.
      required:
        - alone
        - reason
      title: SequenceTrainingSendSchema
      type: object
    AskReason:
      description: >-
        Why a message that could have sent unattended was put in front of a
        person.


        One vocabulary for every gate between an agent writing a message and the

        message leaving: what the agent itself said about the draft

        (``LOW_CONFIDENCE``, ``FINDINGS``, ``INSUFFICIENT_DATA``, ``POLICY``),
        what

        the sender or the cadence asked for (``ALWAYS_ASK``,
        ``SEQUENCE_MANUAL``,

        ``STEP_REQUIRES_APPROVAL``), what the pacing rules refused

        (``DAILY_CAP``, ``CONSECUTIVE_CAP``, ``THREAD_CAP``, ``HOURLY_CAP``,

        ``ORG_DAILY_CAP``), what the mailbox or the thread made unsafe

        (``UNVERIFIED_SENDER``, ``DIFFERENT_SENDER``, ``LABEL``, ``QUESTION``,

        ``STALE_INBOUND``, ``SEQUENCE_GONE``), and what the counterparty turned
        out to be

        (``BOT_QUESTION``, ``AUTOMATED_COUNTERPARTY``, ``AUTHENTICATION``,

        ``LANGUAGE``, ``LINKEDIN_ONLY``). ``KILL_SWITCH`` is the platform switch

        that stops unattended sending outright, and ``SEND_INTERRUPTED`` an

        unattended reply whose send never got as far as a provider.

        ``SENDER_SWITCHED_TO_MANUAL`` is a LinkedIn step queued unasked that
        went

        back to a person because its sender switched to manual before it ran.


        Stored on the task so the queue can say why each row is there, and so

        "why did nothing send" is answerable by counting rows rather than by

        reading logs.
      enum:
        - low_confidence
        - findings
        - insufficient_data
        - policy
        - always_ask
        - sequence_manual
        - step_requires_approval
        - daily_cap
        - unverified_sender
        - suppressed
        - different_sender
        - label
        - question
        - consecutive_cap
        - thread_cap
        - hourly_cap
        - org_daily_cap
        - stale_inbound
        - sequence_gone
        - bot_question
        - automated_counterparty
        - kill_switch
        - authentication
        - language
        - linkedin_only
        - send_interrupted
        - sender_switched_to_manual
      title: AskReason
      type: string
  securitySchemes:
    APIKeyHeader:
      in: header
      name: X-API-Key
      type: apiKey
    HTTPBearer:
      scheme: bearer
      type: http

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.