Chatbot analytics
Chatbot analytics is the record of what people ask your chatbot and how it answers them. The numbers worth reading are how many people wrote in, the share who got an answer, what they asked about and what went unanswered. Deacon is an AI customer support agent for founders who handle support themselves. It answers your customers in seconds from your own docs, and it counts all four from its first conversation. You hear from everyone who asks, not just the few who email, so you see what customers are stuck on and what they want next. Each question it couldn’t answer is one you can answer once, and Deacon gets better the more you answer.
On every plan, including the free one.
At a glance
| What it counts | Messages, People and Answered over 7, 30 or 90 days or all time, each with its change. Waiting for a reply counts everyone who left an email and hasn’t had a reply from your dashboard. |
|---|---|
| What counts as answered | The share of attempted messages that Deacon answered rather than declined. Greetings and requests for a person count as answered. Messages that failed or came after a month’s answers ran out aren’t attempted. |
| What people ask about | Topics group the questions one written answer would satisfy, in any wording or language, and count the people behind each. Most get a type, such as a feature ask, a bug report or a how-to. |
| What it couldn’t answer | The questions your content didn’t cover, each with an Answer this button in Conversations. Every answer you write there becomes part of what Deacon knows. |
| Every conversation | Saved word for word, with the source each answer named and the page the visitor was on. Search by what visitors asked, and filter by tag and date. |
| Where and in what language | The pages people asked from, with how many questions on each went unanswered, the languages they wrote in and a map of where they were. |
| Plans | Every plan, including the free one. Chats in the Playground are never counted. |
| What it doesn’t have | Ratings, thumbs up or down, satisfaction surveys, exports, scheduled reports or a link to Google Analytics. |
What Deacon’s dashboard tells you
Analytics › Widget holds the numbers and Conversations holds every word, and each links to the other.
Four numbers, and whether they moved
Messages counts everything visitors sent Deacon, and People counts who sent it. Answered is the share of the messages Deacon attempted that got an answer. Waiting for a reply counts the people who left an email and haven’t had a reply from your dashboard, whatever range you pick, with a link to reply to them. The first three show their change on the period before, and on all time they compare the last 30 days with the 30 before. Under them, a chart of messages per day marks each day you added, edited, re-crawled or removed a source, so you can see whether a change to your docs moved anything. Lower down, the Messages card shows what kinds of message people send, how many of each got an answer, which sources did the answering and which answered nothing in that time. Playground tests are never counted.
Topics show what people keep asking
Deacon groups the questions one written answer would satisfy, whatever the wording and whatever the language, names each group in English and counts the people behind it. A topic is listed once two people have asked. Most get one of seven types, which are bug report, feature ask, how-to, pricing, account and billing, wants a person and feedback, and a tie gets none. Sort the list by people or by when a topic was last asked, or show one type. Open a topic to read its newest questions in visitors’ own words, with how many went unanswered and how many people left straight after asking. Mark it done and it drops to the bottom until more people ask.
Every conversation, tagged and searchable
Conversations is the page you land on once you’re set up. Its top line gives the share of what people ask that your agent is handling, with this month’s messages and the gaps left to answer. The filter has a tag for each way a question can go, with a count beside it. They’re Unanswered, Wants a person, Failed, Over limit, Answered and Dismissed. Search looks through what visitors asked, never the replies, so you find a conversation by the customer’s own words. Dates narrow it to today, this week or this month, and the newest conversation is always first.
One conversation, and the answer it was missing
Open a conversation to read every turn, with the source each answer named, the page the visitor was on, the topic each question joined and whether they’ve chatted before. Anything your site passed about them, such as their plan, sits alongside, and Translate puts the whole conversation into your browser’s language. A question your content didn’t cover has an Answer this button. Write the answer once and press Save & check. Deacon asks itself the question again and shows you the reply it now gives. When that reply answers it, you also see how many other open questions your answer covers. From then on it can answer the next person who asks, the gaps left to answer go down, and Deacon needs you a little less.
See what your customers ask this week
Install Deacon and the counting starts with its first conversation, with no report to build and nothing to switch on. You get 50 answers a month on the free plan, and it needs no card.
What to read in your chatbot analytics
These hold for any chatbot, whichever tool you use. Start at the top.
The questions it couldn’t answer
This list is worth more than any percentage. Each question on it is either missing from your docs or something customers want that you don’t offer yet. Work through it every week, starting with the one most people asked.
What your answered share counts
Tools name it differently, from the resolution rate to the containment rate, and they count it differently too. Some count a greeting, or a visitor who gave up, as a success. Find out what yours counts before you compare it with anyone else’s.
People, not just messages
One stuck customer can send a dozen messages. Read the number of people beside the number of messages, or one bad afternoon looks like a busy month.
What people ask about
Group the questions by what they’re about and count the people behind each group. That tells you what to fix in the product and what to write in the docs. If 30 people ask how to export invoices, a page is missing. If 30 ask for an integration you don’t have, it belongs in your planning. Those questions are the part of the voice of the customer that arrives without a survey. Customer insights goes through what each kind of question points to.
Where people ask from
The page a question comes from shows you where people get stuck. Lots of questions from your pricing page mean the page isn’t clear, however good your docs are.
Handoffs to a person
The escalation rate is the share of conversations passed to a person. It matters most when one question is behind most of the handoffs, because you can write that answer down once.
Deflection, with care
The deflection rate counts the questions that never reached your team. A visitor who closed the chat in frustration never reached you either, so read real conversations alongside it.
A few conversations every week
Numbers tell you where to look, and conversations tell you what happened. Reading 10 a week is enough to catch a wrong answer, a missing page or a tone you don’t like.
Questions about chatbot analytics
Start with the questions it couldn’t answer, because each one is either missing from your docs or something your customers want that you don’t offer. Then read the share answered, what people ask about, and how many people wrote in as well as how many messages they sent. Deacon shows all of them from its first conversation.
A reply Deacon wrote instead of declining. A greeting and a request for a person count as answered, although Conversations tags the second Wants a person. A reply saying it doesn’t know counts as unanswered, and so does the short fixed reply sent when nothing in your content matched at all. Messages that failed, and ones that arrived after a month’s answers ran out, are left out of both sides of the sum.
Not for questions already asked. Each figure records what the visitor got at the time, so last week’s share stays as it was. What goes down is the count of gaps left to answer, and the next person who asks can get your answer.
No. There’s no rating, no thumbs up or down and no survey after a chat. In their place you have the share answered, the list of what went unanswered and every conversation to read.
It compares each new question with the ones nearest to it in meaning, and a model judges whether each pair is the same question, meaning one written answer would satisfy both people. So a question in Spanish can join a topic that started in English. It joins a topic only when that topic’s own example question is judged the same too, so a loose match can’t drag in a different question. A topic is listed once two people have asked, and its name is in English.
Yes. Each conversation shows the page the visitor was on, and Where in your product lists the pages people asked from, with how many questions on each went unanswered. Once a page has had enough questions, and they go unanswered clearly more often than anywhere else, the card says so. Deacon doesn’t use the page to answer, only to show you where people get stuck.
No. There’s no export, no API for it, no link to Google Analytics and no weekly email. Your website’s visitors, sources and goals are counted by the same script and sit under Analytics › Website.
Not the ones in the Playground. They show in Conversations tagged Playground and are never counted, in the analytics or against your plan’s answers. A chat you start on your live site counts like any visitor’s.
Yes. Every number, topic and conversation is on every plan, the free one included, and nothing here is kept for a paid plan. The plans differ only in answers, knowledge, pages a month from your website and seats. See the plans
Find out what your customers ask
It takes about five minutes to install. The free plan is 50 answers a month, for as long as you like.