ChatFrom
In development
Use case

Customer support

Samantha answers Acme Analytics' customers from its help centre and docs, names the page each answer came from, and books a call with the team when someone would rather talk.

In developmentHow it's built
STARTvisitor messageKSKnowledge SearchsearchCMChat ModelanswerCConditionintentanswercallAtAsk the VisitorphoneTCTool Calllist_callback_slotsAtAsk the VisitorwhenTCTool Callrequest_callbackSMSend Messageconfirm

Each step lights as the agent runs it.

SSamantha · Acme AnalyticsOnline
Ask a question…↑
How it's built

What it knows, what it can do, and the steps it follows.

The same three parts make every chatbot, set up in the dashboard without code: knowledge you add, tools you switch on or connect, and a workflow you draw.

01

Knowledge

Every answer names the page it came from, so the customer can check it. A question the knowledge does not cover gets your own fallback message, not a guess.

  • acme-analytics.com/helpWebsite · 42 pages
  • docs/exports.mdMarkdown · 18 passages
  • Refund policy.pdfPDF · 6 passages
  • Pricing questions12 questions and answers
02

Tools

Both are built in: switch them on under Tools.

Call-back requestsOffers the times your team takes calls and books one. The request lands in your dashboard, and your team is told by email or Slack.list_callback_slotsrequest_callback
Hand-offMarks the conversation for a person and tells your team by email or Slack, with the transcript.hand_off_to_human
03

Workflow

Each visitor message runs these steps: a condition reads what they want, and each answer has its own path. A question none of them takes is answered from the knowledge.

More use cases
Orders and returnsSubscriptionsBookingsLeads and quotesIn-app assistantInternal assistantIt can be anything →