What Answer instructions are
Answer instructions — what other tools call a system prompt — are a set of rules and background that go out with every message the AI writes. They shape how it introduces itself, how formal or casual it sounds, what it will and will not discuss, and how it handles awkward cases.
You will find the field at Brand → Vex → Personality → Answers, labelled Answer instructions. The description under it reads: "Extra instructions sent with every AI prompt. Use this to define tone, rules, or specific information the AI should always know." The instructions belong to that one agent, so a second brand has its own set and nothing is shared between them.
What to write in them
Think of it as the briefing you would give a new support hire on their first morning. Cover:
- Role: what the agent is and who it is for ("You are Vex, a support agent for Acme Corp, helping customers with billing and product questions.")
- Tone: formal, friendly, concise, warm — pick one or two words and stay with them.
- Topics to avoid: competitors, legal advice, medical advice, whatever is off-limits for you.
- Things to always do: sign off with a contact address, use the visitor's name, point at the knowledge base first.
- What to say when it does not know: the behaviour itself is a separate setting on the same tab (see below), but you can reinforce the wording here.
Tone settings beyond the instructions
One toggle on the same Answers tab changes the voice without you writing a word: Emoji Usage. By default the AI uses emojis to keep conversations friendly; tick "Disable emojis in AI responses" for a more formal tone.
Your company name is no longer set here. It is a brand setting, at Brand settings → General, alongside your website and a description of the business — and Fill from website can write all three for you from your website address. The AI reads them, so it is worth filling in properly even though it is not on this screen.
When Vex doesn't know the answer
Still on the Answers tab, When the AI Doesn't Know the Answer decides what happens when nothing relevant turns up in this brand's knowledge. There are two choices:
- Politely decline (recommended): the agent tells the visitor it does not have information about that topic. It does not guess and does not make things up. Safest for most setups.
- Offer to connect with a human: if one of your people is online, the agent asks the visitor whether they want to be connected, and only hands over if they say yes. If nobody is available, it politely declines instead.
The second option is greyed out until automatic handoff is on, with the hint "Enable agent handoff on the Agent Handoff tab to use this option." There is no third "answer anyway from general knowledge" option — that choice does not exist in the product.
Tips for effective instructions
- Be specific, not vague. "Be friendly" is hard to act on. "Use first names when the visitor introduces themselves, never say 'ticketing system', and keep replies under four sentences" is actionable.
- List what NOT to do. Restrictions usually land harder than positive instructions.
- Keep it short. A few tight paragraphs beat a page of prose — these instructions go out with every single message, and a long one dilutes the rules that matter most.
- Test after every change in the chat widget's preview.
Example instructions
You are Vex, a support agent for Acme Corp. Your job is to help customers with questions about our project management software.
Tone: Friendly but professional. Use first names when offered. Keep replies concise — 2–3 sentences max unless a step-by-step answer is needed.
Always: Suggest the knowledge base first. If you can't find the answer, say so clearly and offer to connect the visitor with a human agent.
Never: Discuss competitors. Give pricing advice beyond what's in the knowledge base. Make promises about features that aren't documented.
If asked about your technical nature, say: "I'm Vex, Acme's AI support assistant."Next step
Try your wording before real visitors see it: Test your chatbots before going live. To control when the agent escalates to a person, see Control when Vex hands off to a human.