Your assistant can search, write and remember. It cannot ring the restaurant. Give it one errand; Sakhai rings the business, says she is an AI, gets it done, and hands back what happened — in words.
book_tabledate, time, party
"a table for two on Friday at seven"order_pickupitems, when
"an order for collection: two idli at noon"check_stockitem, item number
"do you have the 14-inch one on the floor right now"check_appointmentdate
"whether Friday's appointment still stands"report_absencedate, reason
"Arjun will not be in on Friday"get_quotewhat, when
"what they would charge for a gutter clean"askone question
your user's own words, oncearrangeone request
your user's own words, oncePOST https://api.sakhai.care/api/v1/calls
Authorization: Bearer sk_sakhai_…
{"task": "book_table", "business": "Piatti", "phone": "+1 925 …",
"details": {"date": "2026-09-26", "time": "19:00", "party": 2},
"for": {"name": "Moses"}, "fallback": "any time between six and eight",
"tz": "America/Los_Angeles", "consent": true}
→ 202 {"id": "c_…", "status": "calling",
"errand": "a table for 2 on 2026-09-26 at 19:00"}
… she rings them, waits through the hold, comes back …
→ your webhook, signed:
{"id": "c_…", "status": "completed",
"outcome": {"answer": "seven for two, in the name Rajan",
"booked": true, "confirmed": true,
"conditions": "fifteen minutes' grace", "held_s": 75}}
Plain HTTP with an OpenAPI spec, or an MCP server for Claude and ChatGPT hosts. The docs are one page.
A phone number is the account: a code by text, the key shown once. Nothing to install on your side.
consent: true: your user asked, and saw the business, the number and the errand.Anyone building an assistant that stops at the phone: a personal-assistant app, a concierge, an agent that books and checks and asks on someone's behalf. Sakhai's own companion app was the first customer; the engine is the same.
Questions: support@cogniolab.com.