Contents

The documentation is written in English and Dutch. You are reading the English version.

Overview

What each figure on an agent's Overview counts, what visitors thought of the answers, and how to use the tips for improving them.

The Overview is the first page in an agent's menu. It answers three questions: is the agent being used, what do people ask, and what would help it answer better? It also shows whether the agent is ready and how it is installed.

The period

The page covers the last 30 days unless you choose other dates, and keeps the same period when you switch between Overview and Activity. Days are your own: the period and the bars follow the clock of the computer you are reading on, so a conversation at eleven in the evening is on that evening's bar.

The figures

FigureWhat it counts
ConversationsConversations that visitors started in the period, through the widget, the iframe or the API.
QuestionsEvery message visitors sent in the period, greetings included.

Your own tests in the Playground are left out of every figure on this page, and of client reports. A line under the figures says how many conversations that were, with a link to them in Activity.

The Volume chart shows conversations and questions per day. A quiet day is drawn as an empty day, not left out.

The agent itself

Three panels do not change with the period. Knowledge counts the sources that are ready, and of which kind (Files, Links, Q&A, Text), the ones being processed and failed, the storage they use, and when the agent was last trained. Deployment shows the language, the model, the Credits this month its answers used, whether the widget is limited to Allowed domains, and whether the ChatterLab badge is shown. The credits are counted per answer at the model's price, the figure on the Client management screen; files visitors send cost credits on top and are not in it. Recent conversations lists the latest 5 with visitors, your tests left out, each a click from its transcript.

Widget

What the chat on your site did in the period. Opened, Conversations and the three that split them count only the chat the button opened, since only it says what opened it. Leads, Forms declined and Where conversations start count the iframe snippet too, as the Leads page does. The Playground and the API are in none of them. They were first counted on 24 September 2026.

FigureWhat it counts
OpenedHow often a visitor opened the chat with the button, once for each page it was opened on. It comes from the chat's own page loading, so nothing is sent only to count it, and one address adds at most 20 an hour.
ConversationsConversations started in a chat the button opened. A visitor who opens the chat and asks nothing counts under Opened only.
LeadsContact details left in the chat's form in the period.
From the button, From the greeting, From the second nudgeThe same conversations, by what the visitor clicked to open the chat, each with its share. The share of the greeting and the second nudge is what they bring in.
Forms declinedConversations in which the visitor answered the contact form with Not now, or chose Skip before their first question.

Opened is kept per hour. In a time zone that is not a whole number of hours from UTC, such as India's, an open in the half hour around midnight can land on the day before.

Where conversations start lists the 10 pages of your site that the most conversations started on, by the page of their first question: by name when the agent has read the page as a source, otherwise by its path, masked as in Activity.

Visitor ratings

How many answers visitors gave a thumbs up and how many a thumbs down in the period. What a visitor thought of an answer is worth more than any score we could put on it. See Visitor feedback.

Repeated questions

Questions asked more than once in the period, most frequent first, up to eight. They are matched on wording, not on meaning: "What are your opening hours?" and "When are you open?" count as two different questions. Capitals and punctuation are ignored.

Use the list to see what your site fails to make clear. A question asked twenty times a month deserves a line on your homepage, not just a good answer from the agent.

Tips to improve your answers

Ways to give the agent more to go on. It is not a list of wrong answers: the answers it points at may well have been right.

Visitors asked about these holds up to eight questions from the period that your sources said little about. Click one to open the conversation. Under each, Improve answer adds your answer as a Q&A pair, and Add a page or file opens Sources.

Below that are general tips: write instructions when the agent has none, add your most asked questions as Q&A when it has none, and read a few conversations in Activity. What to do with each is in Improving your answers.

Greetings

"Hello", "hi", "goedemiddag" and their kin in all five languages are left out of both lists. A greeting finds nothing in your sources, so it would top the list of questions every week, and visitors greet more often than they ask any one thing. Only a message that is a greeting and nothing else is left out. "Hello, do you deliver to Belgium?" counts as the question it is.

Greetings are still counted in the figures.

Over the API

The same figures are available from GET /agents/{id}/analytics, which also returns the confidence measures the Overview no longer shows. See the API reference.