KonvoAI Docs
Analytics

How metrics are calculated

The exact definition behind every Analytics metric — what counts, what doesn't, and when.

Every number in Analytics is computed from each conversation's full event history. This page explains the ground rules that apply everywhere, then defines each metric exactly as it's calculated.

Ground rules

Data refreshes every 15 minutes. Metrics are recomputed on a schedule, so what you see can be up to about 15 minutes behind the live inbox.

Spam is excluded. Conversations marked as spam are left out of every metric — except Spam conversations, which counts only them.

Durations are medians, not averages. Every time metric (first response time, resolution time, handle time, …) reports the median, so a handful of outliers can't distort the picture.

Durations respect business hours. If your organization has business hours configured, time metrics count only the time that passes during those hours — a conversation opened Friday evening and answered Monday morning has a short first response time, not a 60-hour one. Without configured business hours, durations are plain clock time.

What counts as a reply. A reply is a customer-facing message sent by a human agent or the AI agent.

Two ways of counting. Most conversation metrics count a conversation in the period it was created. Metrics about things that happen — closes, reopens, replies, messages, handovers, spam marks — count each event in the period it occurred, regardless of when the conversation started. Open conversations is different again: it's a snapshot of what was open at a point in time.

AI outcomes

Several AI metrics rely on a single classification: every conversation the AI took part in has exactly one outcome, decided in this order of precedence.

OutcomeMeaning
EscalatedA human replied or the conversation was assigned to a human. A human stepping in always wins over everything else.
ResolvedThe conversation reached closed or resolved without a human stepping in.
ConstrainedThe AI is blocked waiting on your team — it asked for input or created a task that nobody has resolved yet.
Still automatedThe AI is handling the conversation and none of the above applies yet.

"The AI took part" means the AI agent acted on the conversation in any way — replying, being assigned, or otherwise taking an action.

Volume

MetricHow it's calculated
New conversationsConversations created during the period.
Open conversationsA snapshot: conversations that were open — created, not closed, not snoozed — at the end of the selected range. As a trend line, each point is the count open at that point in time.
Closed conversationsConversations closed during the period, counted at the moment of closing. A conversation closed more than once in the period counts once.
New vs closedThe two series above, side by side per period.
Reopened conversationsConversations that went from closed back to open during the period. A conversation reopened several times counts once.
Conversations by channelNew conversations, grouped by the channel they arrived on.
Spam conversationsConversations marked as spam during the period. The only metric that counts spam.
Messages receivedEvery message sent by a customer, counted at the moment it was sent.

Responsiveness

All duration metrics here are medians and respect business hours.

MetricHow it's calculated
First response timeConversation created → the first reply from anyone, human or AI — whichever came first.
AI first response timeConversation created → the AI's first reply. Only counts conversations where the AI replied before any human.
Human first response timeConversation created → the first human reply.
Response timeThe median across every customer message → next reply pair, not just the first. Counted at the time of the reply. The heatmap view breaks these pairs down by time period and duration band.
Response time after escalationThe moment the AI handed the conversation to a human → the first human reply after that.
Resolution timeConversation created → its final close.
Time to first closeConversation created → its first close. Reopenings don't push this back.
Handle timeHands-on time human agents spent working the conversation, measured from actual viewing time.

Productivity

MetricHow it's calculated
Replies sentEvery reply from a human or the AI, counted at the moment it was sent.
Conversations replied toConversations that received at least one reply during the period.
One-touch rateOf closed conversations, the share resolved with exactly one reply (human or AI).
Zero-touch rateOf closed conversations, the share with no human reply at all.
Messages per conversationThe median number of messages per conversation — customer, human, and AI messages combined.
Reassignments per conversationThe median number of times a conversation changed owner, including AI → human handovers. The initial assignment doesn't count.

AI performance

MetricHow it's calculated
Involvement rateThe share of all conversations the AI took part in.
Resolution rateOf the conversations the AI took part in, the share whose outcome is Resolved.
Automation rateOf all conversations, the share the AI resolved — took part in and reached a close without a human stepping in.
Escalation rateOf the conversations the AI took part in, the share whose outcome is Escalated.
Answer rateOf the conversations the AI took part in, the share where the AI sent at least one reply.
Automated conversationsThe number of conversations the AI resolved.
Automation by topicA table with one row per topic: automated conversations, answer rate, resolution rate, automation rate, and Time saved by agents (see AI economics), each broken down by topic. Time saved uses each topic's own median human handle time, so a topic no human has handled yet shows no value.
HandoversConversations the AI handed to a human during the period, counted at the moment of handover. A conversation handed over more than once counts once.
Confirmed vs assumed resolutionAI-resolved conversations split in two: assumed when the close came from the automatic resolver after inactivity, confirmed when it was closed explicitly.
AI outcome funnelA flow diagram over all conversations in the period: new conversations split into those the AI took part in versus those that went straight to a human, then AI-involved ones split by outcome (Closed by AI, Escalated, Constrained, Pending), and escalated ones flow on to Closed by human.

AI economics

MetricHow it's calculated
Time saved by agentsAutomated conversations × the median measured handle time of your human-handled conversations — an estimate of how long the AI's conversations would have taken a person.
Cost savedAutomated conversations × the margin between an assumed human cost of €4.50 per conversation and your plan's AI cost per conversation — never below zero. The €4.50 approximates the midpoint of the $3.00–$6.00 industry benchmark for a human-handled interaction, taking the dollar range at roughly parity.
Decrease in first response timeHow much faster the AI answers than your team: (median human first response time − median AI first response time) ÷ median human first response time, as a percentage.
Decrease in resolution time(Median resolution time of human-handled conversations − median resolution time of AI-resolved conversations) ÷ the median resolution time of human-handled conversations, as a percentage.
AI spendBilled AI conversations in the period × your plan's effective per-conversation rate (the plan price divided by its included conversations — about €0.79 on Starter, €0.70 on Core, €0.60 on Scale).

Usage & plan

These are point-in-time gauges over your current billing period — they ignore the selected date range.

MetricHow it's calculated
AI conversations usedAI conversations consumed so far in the current billing period.
Percent of plan usedUsed ÷ included in your plan × 100. The gauge shows an Overage state past 100%. Blank on a plan with no fixed allowance.
Overage costConversations used beyond your plan's allowance × €1 each. Zero while you're within the allowance.

Quality

MetricHow it's calculated
Sentiment distributionConversations grouped by their detected sentiment.
Sentiment over timeSentiment-classified conversations per period, split by sentiment.
Negative-sentiment conversationsConversations whose detected sentiment is negative.
CSAT score, CSAT response rate, CSAT distribution, CSAT: AI vs human, CX scoreComing soon — these light up once CSAT surveys ship.

Topics & tags

MetricHow it's calculated
Conversations by topicConversations grouped by topic. A conversation with several topics counts under each of them.
Topic trendNew conversations per period, split by topic.
Emerging topicsEach topic's volume change versus the immediately preceding period of the same length, as a percentage. Shows the 10 largest changes; a topic with no prior volume is marked New instead of a percentage.
Top tagsThe 10 most-used tags in the period — AI-applied and manually applied pooled together — each with its previous-period count for comparison.
Priority distributionConversations grouped by priority.
Language distributionConversations grouped by detected language.
Tag volume (% of units sold)Coming soon — requires order data.

Agents

Per-agent metrics group by the person (or AI agent) involved. Spam conversations never count as agent work.

MetricHow it's calculated
Agent performanceA table with one row per agent and six columns: conversations assigned and conversations closed (defined below), first response time (conversation created → that agent's first reply, as a median — anchored at creation, so it reflects how fast customers heard from them regardless of when they were assigned), resolution time (the median resolution time of the conversations the agent closed), one-touch rate (of the conversations the agent closed, the share resolved in a single reply), and replies sent (the total number of replies the agent sent).
Conversations assigned per agentConversations in the period in which the agent was assigned.
Conversations closed per agentConversations whose final close was made by the agent.
Replies & closed per active timeA table with, per agent, their replies sent and their conversations closed, each divided by their hours of Active time in the period.
Active timeThe agent's total tracked time actively viewing conversations during the period, clipped to the selected range. Time while a conversation was snoozed doesn't count. This is the same tracked activity behind handle time, but summed per agent.

Revenue & Conversion

All revenue metrics — Revenue influenced, Conversion rate, Orders influenced, Attributed AOV, Revenue per conversation, Revenue by channel, and Conversion funnel — are coming soon. They require order attribution and will light up once it's configured.

On this page