Flocci Chat Start free
Plain answer

An AI chatbot that does things, not just answers

Short answer

A chatbot becomes genuinely useful when it can act for a specific customer: track this order, check this subscription, raise this ticket. That requires proving who the visitor is, then calling your own API on their behalf. Flocci Chat verifies users with an HMAC-SHA256 signature, exposes your endpoints to the assistant as configured actions with signed X-Flocci-End-User headers, and logs every execution.

The gap between "answering" and "helping"

"What is your refund policy?" is a retrieval question — any grounded chatbot handles it. "Where is my order?" is not. The answer lives in your database, is different for every visitor, and must never be given to the wrong person. Most website chatbots stop at the first kind of question, which is why customers still open a ticket for the second.

Step one: prove who is asking

Your backend computes an HMAC-SHA256 signature over the user's id using a secret only your server and the workspace hold, and your frontend calls flocciChat.identify(user, hmac). The session is then verified: the assistant knows this really is customer 84213, not someone claiming to be. The signature covers the identifier itself, so nothing in the browser payload can be edited into somebody else's account.

Step two: give the assistant your endpoints

In the dashboard's Actions area you describe an action — a name, a plain-English description of when to use it, the parameters, and the endpoint. The assistant then decides on its own when that action fits a customer's question, calls your API with X-Flocci-End-User-* headers identifying the verified user, and answers from the live result. Typical first actions: order status, shipment tracking, subscription or plan lookup, invoice retrieval, appointment or booking status, licence-key resend.

What is built in before you configure anything

Guardrails that matter

Actions execute only for the subject of the verified session — the assistant cannot be talked into looking up a different customer, because identity comes from the signed session rather than from anything the model or the visitor supplies as an argument. Credentials for your endpoints are encrypted at rest with AES-256-GCM. Every execution is written to an audit log with the action, the round and the outcome, and surfaces as a visible chip in the conversation so the customer can see what was done on their behalf.

Practical sequencing

Ship the answering layer first: embed the widget, let it learn the site, watch a week of real questions. The dashboard's unanswered-intent list will tell you exactly which account-specific questions keep arriving — that list, not a guess, is your action backlog. Most teams need two or three actions to remove the majority of their ticket volume.

Frequently asked questions

Can an AI chatbot check a customer's order status?

Yes, if it can verify the customer and call your API. Flocci Chat verifies logged-in users with an HMAC-SHA256 signature and lets you register your order-status endpoint as an action; the assistant calls it with signed end-user headers and answers from the live response.

How do I connect a chatbot to my own API?

In the dashboard's Actions area, describe the action in plain English, define its parameters and point it at your endpoint. The assistant decides when the action applies. No plugin or middleware is required, and connector credentials are encrypted at rest.

Is it safe to let a chatbot call my backend?

The controls that make it safe are: identity proved by a server-side HMAC signature rather than a client claim, actions scoped to the verified session's subject only, encrypted credentials, and an audit log of every execution. Ask any vendor to show you all four.

What is agentic chat and do I need it?

Agentic chat means the assistant can call tools mid-conversation rather than only generating text. You need it when a meaningful share of your questions are account-specific — order status, subscriptions, bookings. If your questions are all policy and product questions, retrieval alone is enough.

Do actions cost extra?

No. Metering is one credit per answered visitor message; tool calls, ticket creation and web searches inside that turn are not billed separately.

Try it on your own website

One script tag. 500 free credits — roughly 500 answered visitor messages. Every feature on, no card. The widget in the corner of this page is the product, running on its own site.

Create your workspace — free