AI Conversations

Overview

When the widget's brand has a Vex AI agent, visitors can ask questions in natural language and get instant answers. There is nothing to connect: the brand owns both the widget and the AI. This article covers what the AI conversation looks like and feels like from the visitor's side.

Sending a Message

Visitors type their question in the input field at the bottom of the chat and press Enter to send. The message appears as a right-aligned bubble, just like in a regular live chat conversation.

Messages can be up to 20,000 characters long. Visitors can also attach files (images, videos, PDFs) alongside their question — useful for sharing screenshots or documents the AI might need context about.

While the AI is generating a response, the input is temporarily disabled. Visitors can't send another message until the current response finishes streaming.

Visitors typing Japanese, Chinese or Korean use an input method that takes Enter to confirm the characters they are converting. That Enter does not send the message — only an Enter pressed on finished text does.

Streaming Responses

AI responses appear in real time — word by word — in a left-aligned bubble. This streaming effect makes the conversation feel natural and responsive, similar to watching someone type.

While the AI is thinking:

Animated loading dots appear to indicate a response is being generated
The chat auto-scrolls to keep the latest content visible
If the visitor scrolls up to read older messages, auto-scroll pauses so they aren't interrupted — scrolling back to the bottom re-enables it

Each AI message displays a small AI indicator badge at the bottom of the bubble, so visitors always know they're talking to an AI rather than a person.

Where the Answers Come From

The AI searches the brand's whole body of knowledge in one pass — help articles, documentation pages, uploaded files, website pages that were read for you, question-and-answer entries and the product catalogue. There is no per-widget selection to make: everything the brand knows is in scope for every answer.

If the brand's sources are written in more than one language, the search runs in each of them at once, up to three languages at a time, so a brand with an English and a Hungarian knowledge base keeps full recall in both.

When the AI links to one of your own help articles, that link is built at the moment it answers, from the brand's current public web address. Renaming the address does not break the links in content that was indexed before the rename — every citation is rebuilt from the current address each time an answer is written.

Conversation Starters

Conversation starters are suggested topic buttons that appear before the visitor types their first message. They float above the input area as clickable buttons, giving visitors quick entry points for common questions.

When a visitor clicks a starter:

The button's label appears as the visitor's message (e.g., "Pricing plans")
A more detailed prompt is sent to the AI behind the scenes (e.g., "What pricing plans do you offer and what's included in each tier?")
The AI responds based on the detailed prompt
All starter buttons disappear

Visitors can also dismiss the starters by clicking the X button without selecting one, or simply start typing their own message — the starters disappear as soon as any message is sent.

The label/prompt separation means visitors see a clean, short button label while the AI receives a richer question that produces a better answer. See the Conversation Starters dashboard article for setup. The AI setup wizard can also write a first set for you, but only for an AI agent that has none at all — a set you wrote yourself is never touched or added to.

Switching to a Human Agent

After a configurable number of messages, a "Talk to the support team" link appears below the chat input. Clicking it sends an agent request — the chat state changes to "awaiting" while a human agent is assigned.

During the wait:

The visitor sees a confirmation that an agent has been requested
A "Talk to AI Bot" link replaces the support team link, letting the visitor cancel the request and return to the AI conversation
Once an agent joins, the conversation continues in the same chat window — no page change or new thread

The agent can see the full AI conversation history, so the visitor doesn't need to repeat themselves.

Automatic Handoff

In some cases, the AI hands off to an agent automatically:

When the AI determines it can't help based on the conversation
When no relevant knowledge is found (if configured)

The visitor sees a message (e.g., "Let me connect you with a team member...") before the transition.

Message Types in the Chat

The conversation thread includes several types of entries:

Type	What It Looks Like
Visitor message	Right-aligned bubble with the visitor's text and any attached files
AI response	Left-aligned bubble with streamed text and an AI indicator badge
Agent message	Left-aligned bubble with the agent's avatar, name, and timestamp
Event	Centered gray text for system events like "Agent joined" or "Workflow started"

Chat History

Visitors returning to a previously active chat see up to their 20 most recent messages from the last 14 days loaded automatically. If the conversation has more than that, a button appears at the top of the thread — "Load more messages", or "Show older messages" when nothing has loaded yet — and each click fetches the next batch.

The chat maintains scroll position when loading history, so visitors stay anchored on the message they were reading instead of being jumped around.