What is a prompt?
A prompt is the “brain” behind your AI Agent — a set of written instructions that tell it who it is, how it should act, and what it should do.
Think of your AI Agent as a new team member. The prompt is their onboarding guide: it explains their job, how to talk to customers, and what to avoid.
If your prompt is too vague, your agent will improvise. If your prompt is clear and detailed, your agent will stay on-brand and accurate — just like a well-trained teammate.
Why prompts matter
Your AI Agent already knows how to chat, but it doesn’t know your business until you tell it. The prompt defines your brand voice, priorities, and personality.
It’s what turns your AI Agent from “just another chatbot” into a virtual team member your customers trust.
A great prompt helps the AI:
Understand what to do — including its main tasks and responsibilities.
Adopt your brand’s tone of voice — knowing how to chat, sound, and behave.
Recognize what to avoid — including taboos, boundaries, and things it should never say.
Your AI Agent follows instructions literally — so write your prompt in a way that a 10-year-old could follow. Short sentences, no guesswork, no “creative interpretation.”
The 3 building blocks of a great prompt
In Superchat, your prompt is split into three key sections — each with a clear purpose:
Role & Task
This is where you explain who your AI Agent is and what exactly it should do. Here you define the agent’s “job” and step-by-step instructions for completing it. If your agent should use tools — like saving data or writing notes — explain when and how to do so.
Ask yourself:
What is my AI Agent responsible for: What are its main tasks or functions?
What is the ultimate business goal: Qualify applicants, support customers, close deals?
What is the AI Agent’s name? Should it say it’s an AI or not?
Is there a step-by-step process it should follow (first do this, then that)?
Should it use tools like Update Contact or Internal Note — and when exactly should it do that?
Examples:
“You are ‘Sophie,’ a support assistant at Super Sofa Co. Your job is to help customers with returns, delivery updates, and product info.”
“If a customer shares an order ID, confirm that it matches our format (it always starts with an ‘X’ followed by eight numbers) before proceeding.”
“Ask for first name, last name, and email. If any of these are already stored, skip that question.”
“Once you’ve collected all three, save them.”
“After finishing a conversation, summarize the key points and next steps in an internal note.”
Style & Language
This section defines how your AI Agent should sound — the tone, level of formality, and writing style. Think of it like your brand voice guide. The clearer you describe how your business sounds, the more natural and consistent your AI’s replies will be.
Ask yourself:
How should the AI sound — friendly, formal, casual, or professional?
Should it use short, direct sentences or longer, detailed ones?
Should it use emojis, or avoid them completely?
Examples:
“Be friendly, clear, and professional — sound like a helpful team member, not a bot.”
“Write short, direct sentences. Avoid repeating the same phrases.”
“Only use emojis if the customer does first.”
“Be kind and empathetic, but stay concise — don’t overexplain.”
💡 Pro Tip
If you’re unsure how to describe your tone, write one short example reply in your style (e.g. how your team would reply). The AI will automatically learn from that sample and use it as a reference for tone and structure.
Boundaries & Taboos
This section defines what the AI must not do. It’s your safety net — your way to make sure the AI stays on brand and avoids overstepping. Without clear boundaries, the AI might try to guess or give answers it shouldn’t.
Ask yourself:
What are potential mistakes my AI Agent must avoid? (e.g., confirming prices, giving medical advice)
What should it never say? (e.g., mention competitors, discuss company policies in detail)
What topics should it completely stay away from?
Are there any legal, brand, or compliance rules it must always follow?
Examples:
“Never give medical, legal, or financial advice.”
“Never confirm offers or prices — only share information that’s in the knowledge base.”
“Avoid mentioning competitors or comparing products.”
“Do not discuss internal company policies or team details.”
“Never invent data or order details.”
“If unsure, ask for clarification instead of guessing.”
💡 Pro Tip:
Escalation and handover rules should not be written in the prompt. Set them up in the AI Agent node in Automations instead.
There, you can define custom exit conditions (e.g., “human_handover” or “billing_request”), specify when they should trigger (e.g., when the contact asks for a human), and then decide what happens next — such as assigning the conversation to a teammate.
Writing tips for better prompts
Be literal – The AI does exactly what you say, word for word.
Be specific – Describe when and how to do what (“ask this, then that”).
Avoid fluff – Skip “usually,” “try,” or “in general.”
Include examples – Real samples help the AI understand intent.
Keep facts separate – Don’t mix company info into the prompt — use Knowledge instead.
Test often – Small tweaks make big differences.