Lincoln AI must be on the workspace’s plan (it comes with the Growth Marketing Manager). Through the API,
each message is billed from your prepaid balance at the AI model cost of the turn plus a 20% markup (Lincoln
in the dashboard stays free). It shows up as
ai_agent in GET /v1/billing/events, and a request returns
402 payment_required when the balance is empty and auto-refill is off. The actions Lincoln takes are billed
on top, exactly as they are in the dashboard, and anything that costs money waits for your approval first.1. Give Lincoln a task
Leave outconversation_id to start a new conversation.
wait_seconds, default 120, max 240):
conversation_id to follow up. Lincoln remembers the whole thread.
2. Long tasks: poll
If Lincoln is still working whenwait_seconds runs out (or you passed "wait_seconds": 0), status is
working. The task keeps running; poll until it settles:
reply holds what Lincoln has said so far. A conversation takes one message at a time:
sending another while it is working returns 409 conflict.
3. Approvals
Before anything that spends money or can’t be undone (buying a number, placing a call, sending texts, publishing a video), Lincoln stops and asks. The response comes back asawaiting_approval:
approvals instead of message:
"approved": false, optionally with a reason)
tells Lincoln not to do it, and it replies accordingly. A new message is refused with 409 conflict
until the pending approvals are answered.
Over MCP
The same three operations are MCP tools on the LumisReach MCP server:ask_lincoln, get_lincoln_conversation and list_lincoln_conversations. ask_lincoln waits 45
seconds by default (so it fits inside most MCP clients’ tool timeout) and returns working for longer
tasks, which your agent then follows with get_lincoln_conversation.