Design a chatbot or AI assistant conversation flow
Conversation flows, intents, responses, and handoff rules for a support, sales, or booking bot.
The prompt
Role: Act as a marketing operations specialist designing a website chatbot flow.
Context: Goal of the bot: [BOT_GOAL]. Pages it runs on: [PAGES]. Qualifying criteria: [QUALIFYING_CRITERIA]. Routing options (teams, booking links, content): [ROUTES]. Tone: [TONE]. Data we may collect and consent rules: [DATA_CONSENT]. Out-of-scope topics: [OUT_OF_SCOPE].
Task: Design the flow: opening message, 3-5 qualifying questions with branch logic, the routing decision for each branch, a graceful human-handoff path, a fallback for unrecognised input, and the consent/disclosure line before any data capture.
Format: A numbered flow with branches shown as indented options; a table mapping branch -> route; the consent line verbatim.
Verification: Ensure no branch collects personal data before the consent line, and every branch ends in a route or handoff (no dead ends). Flag any question that is leading.
Validation: Walk 3 visitor types (ready-to-buy, researching, wrong-fit) through the flow: does each reach a sensible outcome fast? Shorten any path over 5 steps.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Customer Support prompts
What to fill in
- BOT_GOAL
- PAGES
- QUALIFYING_CRITERIA
- ROUTES
- TONE
- DATA_CONSENT
- OUT_OF_SCOPE
How this prompt is built
This prompt follows the RCTFVV structure (Role, Context, Task, Format, Verification, Validation). RCTFVV extends RCTF with two checking steps. Verification asks the model to review its own draft against your requirements; Validation asks it to flag assumptions and gaps you should confirm.
Related prompts
- Write an empathetic reply to a customerClear, warm, accurate responses to customer emails and chats.
- Write troubleshooting steps for a customer issueStep-by-step troubleshooting guides for agents or customers, from simple fixes to escalation.
- Create or rewrite support macros and templatesConsistent, on-tone response templates for common issues across channels.
- Turn resolved tickets into a knowledge-base articleHelp-center articles customers and agents can follow, built from real tickets.