Interpret Lead Filter
Turn a lead filter typed in plain words into a segment's filters (nothing is saved).
API key access
leads:read scope with an API key (ro_pat_...). A signed-in session uses the caller's role./api/v1/ai/lead-filterAccess token from /api/v1/auth/login, or an API key (ro_pat_..., RO-176) from /api/v1/workspaces/current/api-keys: the key implies its workspace and needs the route's scope. MCP connectors (/api/v1/mcp only) may use an OAuth access token (ro_oat_..., RO-284).
In: header
Header Parameters
Id of the workspace to act on (must be a member).
Which leads, in plain words, e.g. 'spa owners in Texas who replied'.
1 <= length <= 300Response Body
curl -X POST "http://localhost:8000/api/v1/ai/lead-filter" \ -H "X-Workspace-Id: string" \ -H "Content-Type: application/json" \ -d '{ "text": "string" }'{
"filters": {},
"unsupported": [
"string"
],
"summary": "string",
"source": "ai"
}Get Ai Usage
Today's AI request counts vs the free-tier budgets (platform admins only: the counts are app-wide), including the workspace overrides' own budgets (`provider` = `<provider>@ws-<workspace id>`). Unguarded providers (e.g. a paid Anthropic key) are not listed. Workspace search overrides are listed with `kind` = `search` (their daily bucket; RO-245). `llm_calls` sums today's recorded LLM calls (every provider, guarded or not).
List Ai Column Values
The cells of every AI column of a table for the given rows (`ids` repeated, at most 200): status, value, score, sources, credits and whether it's stale.