Set up the website chat
chat_setupCreate or change the business's website chat widget, which you answer: each visitor message reaches you as a chat.message_received event (subscribe a webhook to it, or use chat_wait) and you reply with chat_reply. Or answer_with webhook: your own brain (your server, n8n, Flowise) gets each message as a signed POST and its reply goes to the visitor at once. Or answer_with model: a model on the business's own key answers, with instructions and knowledge you give. Conecto pays for no model in it. Only the fields you pass change. A model without its key (none kept, or a new provider), or the keys named in ask_owner_for, come from the owner: the answer is a link where they type them on a Conecto page, so they never pass through the chat (from_a_terminal does the same from a terminal), and nothing changes until they do (account.credential_added says when). The reply has the HTML snippet to put on the website. $0.05 per conversation, charged on the visitor's first message; messages and replies are free. Costs $0.001 per call; nothing if it fails.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | The business name. | |
| color | No | Accent colour, e.g. #1a73e8. | |
| model | No | The provider's model name, e.g. gpt-5.4-mini or claude-sonnet-5-5; for azure the deployment name. It must support tool calling. | |
| website | No | The website it goes on. | |
| greeting | No | The first line visitors see. | |
| language | No | Widget language, e.g. en, de. | |
| knowledge | No | answer_with model: facts it answers from (prices, delivery, opening hours). Replaces what was given before; empty removes it. The published help center is used as well. | |
| agent_name | No | The name your replies are signed with, e.g. "Acme Support". | |
| experience | No | chat: the classic chat widget. beside: Beside, which also tells you the page the visitor is on (its address, title and text) with each message. Same price. | |
| answer_with | No | bot (the default): you answer through events and chat_reply. webhook: each visitor message is POSTed to webhook_url and its reply goes to the visitor at once. model: a model on the business's own key answers (model_provider, model, model_api_key). | |
| cant_answer | No | What the chat says when your webhook or model gave no reply; it then asks for the visitor's email. Needed for languages other than en, de, es, fr, it, nl, pt and sv. | |
| webhook_url | No | Your brain's https endpoint for each visitor message. | |
| instructions | No | answer_with model: how the model answers (tone, scope, what to offer), in the business's words. | |
| ask_owner_for | No | Keys the owner types on a Conecto page: the answer is a link, and nothing changes until they do. | |
| model_api_key | No | The business's API key for model_provider. Kept encrypted, never shown again; its usage is billed by the provider to the business. | |
| rotate_secret | No | Make a new webhook_secret (the old one stops working). | |
| webhook_token | No | Sent as Authorization: Bearer, for brains that want a key (Flowise, n8n header auth). Empty removes it. | |
| model_base_url | No | azure only: the resource's address, like https://acme.openai.azure.com/openai/v1/. | |
| model_provider | No | Whose model answers with answer_with model. | |
| starter_questions | No | Beside: up to 3 questions visitors can tap to start. |