Personality | Yaplet

Where this is

Brand → (your brand) → Vex → Personality. This screen is about this one AI agent and nothing else: what it is called, whether it is switched on, how it writes, what it does when it cannot answer, and when it passes the visitor to a person. It has four tabs — General, Answers, Agent Handoff and Danger Zone — and one Save button that covers all of them. The permission is Vex.

General

Name — what this AI agent is called in your dashboard. Visitors never see it.
Enable this agent — the on/off switch. While it is off, the agent does not respond to visitors at all.
AI Models — the Primary Model and the Fast Model behind this agent. Yaplet chooses and maintains them; they are shown for information and cannot be changed.

Answers

Emoji Usage — the AI uses emojis by default to keep the tone friendly. Tick Disable emojis in AI responses for a more formal voice.
Answer instructions — extra instructions attached to every AI prompt. Use it for tone, house rules, or facts the agent should always have to hand, for example: "Always greet users by name. Never discuss competitor products. Our return policy is 30 days."

When the AI doesn't know the answer

Choose what happens when the agent finds nothing relevant in this brand's knowledge:

Option	What happens
Politely decline (recommended)	The agent tells the visitor it has no information on that topic. It does not guess and does not invent an answer.
Offer to connect with a human	If a human agent is online, it asks whether the visitor would like to be connected and waits for a Yes or No. If nobody is available, it politely declines instead.

Offer to connect with a human is only selectable while Automatic Agent Handoff is on, over on the Agent Handoff tab. With handoff off the option is greyed out and the behaviour falls back to Politely decline.

Either way, the agent writes a natural sentence in the visitor's own language rather than sending a fixed template.

Agent Handoff

Automatic Agent Handoff — the master switch for passing a conversation to a person. With it on, visitors can ask for a human and the Offer to connect with a human option above becomes available. Nobody is ever transferred silently: the visitor confirms with a Yes/No prompt first.
Handoff Message — what the visitor sees immediately before being connected.
Show 'Talk to Support' Button After — how many messages a visitor must send within five minutes before the "Talk to support team" button appears, so that it does not show up too early. The default is 6.

If you switch automatic handoff off, build a workflow to catch the requests instead. Without one, the agent can tell a visitor it is fetching a colleague and then not do it. Build the workflow on this brand's Workflows page, set its trigger to User says, and give it the intent "The user wants to talk to the support team". The screen offers a link straight there whenever the switch is off.

Danger Zone

Delete this AI agent removes the agent, its conversation starters, its suggestions and its report history. This cannot be undone.

Your knowledge is not affected. Knowledge bases, documentation, files, website pages, Q&A entries and products all belong to the brand rather than to the agent, and stay exactly as they are. Add another AI agent later and it answers from the same material. There is no list of chatbots to go back to, so after deleting you land on the brand's Vex screen with the offer to add one.

Settings that used to be here

Five things this screen used to hold now belong to the brand, because they describe the company and its content rather than one agent's personality — and they apply to everything that answers for the brand: chat, phone calls, the inbox's suggested replies and AI social posts alike.

What it was called here	Where it is now
Company Name and Website URL	Brand → Brand settings → General
Knowledge Base Language	Set on each source individually, on Brand → Knowledge
Smart Answer Matching	Brand → Brand settings → Advanced, as Smart answer matching
Privacy Protection (PII Masking)	Brand → Brand settings → Advanced, as Privacy masking

The old Widgets & Knowledge Sources table is gone, and so is the failure it caused. There is nothing left to wire up: a brand owns one chat widget and one pool of knowledge, and Vex answers for that brand. Forgetting to attach the right knowledge base to the right chatbot used to be the single most common reason for "my bot doesn't know anything", and that cannot happen any more. The widget itself is at Brand → Chat widget.

Several languages now work at once. Each knowledge base and documentation set carries its own language, set on Brand → Knowledge, and the brand's language is only the fallback for things with none. The agent searches in every language the brand's content is written in, up to three at a time, so a brand with an English and a Hungarian knowledge base keeps full accuracy in both. This only affects how questions are matched to content — the agent always replies in the visitor's own language.