> ## Documentation Index > Fetch the complete documentation index at: https://docs.lumisreach.com/llms.txt > Use this file to discover all available pages before exploring further. # Message Lincoln AI > Tell Lincoln AI what to do in plain language, the same as typing in Dashboard → Conversations: it plans the work and carries it out with your workspace's tools (phone numbers, voice agents, campaigns, contacts, automations, videos and more). Omit `conversation_id` to start a new conversation; pass it to continue one. The request waits up to `wait_seconds` for Lincoln to finish and returns its `reply` and the `actions` it took. If it is still working, `status` is `working`: poll `GET /v1/lincoln/conversations/{id}`. Anything that spends money or can't be undone pauses with `status: awaiting_approval` and a list of `pending_approvals`; send them back as `approvals` to continue. Requires Lincoln AI on the workspace's plan. Tool actions are billed as they would be in the dashboard. ## OpenAPI ````yaml /openapi.json post /v1/lincoln/messages openapi: 3.1.0 info: title: LumisReach v1 API version: 1.0.0 description: >- Programmatic access to the LumisReach voice platform — calls, numbers, caller trust, and brands. contact: name: LumisReach email: founders@lumisreach.com servers: - url: https://api.lumisreach.com/api security: - bearerAuth: [] tags: - name: Phone Numbers - name: Caller IDs - name: Enterprise Registration - name: Branded Calling - name: Calls - name: SMS - name: WebRTC - name: Reputation - name: Usage - name: Account - name: Billing - name: Conversation History - name: Documents - name: Lincoln AI - name: Quick Agent Actions - name: Sub-entities paths: /v1/lincoln/messages: post: tags: - Lincoln AI summary: Message Lincoln AI description: >- Tell Lincoln AI what to do in plain language, the same as typing in Dashboard → Conversations: it plans the work and carries it out with your workspace's tools (phone numbers, voice agents, campaigns, contacts, automations, videos and more). Omit `conversation_id` to start a new conversation; pass it to continue one. The request waits up to `wait_seconds` for Lincoln to finish and returns its `reply` and the `actions` it took. If it is still working, `status` is `working`: poll `GET /v1/lincoln/conversations/{id}`. Anything that spends money or can't be undone pauses with `status: awaiting_approval` and a list of `pending_approvals`; send them back as `approvals` to continue. Requires Lincoln AI on the workspace's plan. Tool actions are billed as they would be in the dashboard. operationId: v1_lincoln_messages_post parameters: - name: Idempotency-Key in: header required: false description: >- UUID — when present, deduplicates repeat submissions. See /api-reference/idempotency. schema: type: string requestBody: required: true content: application/json: schema: $schema: http://json-schema.org/draft-07/schema# type: object properties: conversation_id: description: Continue this conversation. Omit to start a new one. type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ message: description: >- What you want Lincoln to do, in plain language. Send this or `approvals`, not both. type: string minLength: 1 maxLength: 20000 approvals: description: >- Answers to the actions Lincoln is waiting on (`pending_approvals`). Every pending approval must be answered. Send this or `message`, not both. minItems: 1 type: array items: type: object properties: approval_id: type: string minLength: 1 description: >- `pending_approvals[].approval_id` from the previous response approved: type: boolean description: '`true` lets Lincoln run the action, `false` stops it' reason: description: Optional note Lincoln sees, e.g. why you declined type: string maxLength: 500 required: - approval_id - approved additionalProperties: false wait_seconds: default: 120 description: >- How long to hold the request open for Lincoln to finish. `0` returns immediately. If the turn is still running when this runs out, `status` is `working`: poll `GET /v1/lincoln/conversations/{id}`. type: integer minimum: 0 maximum: 240 required: - wait_seconds additionalProperties: false responses: '200': description: Success content: application/json: schema: $schema: http://json-schema.org/draft-07/schema# type: object properties: data: type: object properties: conversation_id: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ title: type: string status: type: string enum: - working - idle - awaiting_approval - failed description: >- `working`: Lincoln is mid-turn. `idle`: done, waiting for your next message. `awaiting_approval`: paused until you answer `pending_approvals`. `failed`: the turn errored (see `error`). run_id: anyOf: - type: string - type: 'null' reply: anyOf: - type: string - type: 'null' description: >- Lincoln's latest reply as text. Partial while `status` is `working`. actions: type: array items: type: object properties: tool_call_id: type: string tool: type: string description: The tool Lincoln used, e.g. `list_phone_numbers` status: type: string enum: - running - awaiting_approval - approved - denied - completed - failed input: description: The arguments Lincoln passed output: anyOf: - {} - type: 'null' description: What the tool returned, when it completed error: anyOf: - type: string - type: 'null' required: - tool_call_id - tool - status - input - output - error additionalProperties: false description: The tool calls in Lincoln's latest reply pending_approvals: type: array items: type: object properties: approval_id: type: string tool_call_id: type: string tool: type: string input: {} reason: anyOf: - type: string - type: 'null' description: >- Why this action needs a yes: what it costs or changes required: - approval_id - tool_call_id - tool - input - reason additionalProperties: false error: anyOf: - type: string - type: 'null' updated_at: type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$ required: - conversation_id - title - status - run_id - reply - actions - pending_approvals - error - updated_at additionalProperties: false required: - data additionalProperties: false '400': description: Validation error content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' '403': description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' '404': description: Not found content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' '409': description: Conflict (incl. idempotency conflicts) content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' '429': description: Rate limited content: application/json: schema: $ref: '#/components/schemas/ErrorEnvelope' components: schemas: ErrorEnvelope: type: object properties: error: type: object required: - code - message properties: code: type: string message: type: string fields: type: object additionalProperties: type: string doc_url: type: string format: uri securitySchemes: bearerAuth: type: http scheme: bearer ````