Build your own analytics tabs

Add a tab to the dashboard or to an agent's conversations page, choose what to count and how to split it, compare it with the previous period, arrange the widgets, and share the tab with your team.

Build your own analytics tabs

Dashboard → + New tab (sign-in required) adds a tab of your own beside the built-in ones. Each widget on it is one question — How do conversations end?, Which hours are busiest?, Average call length by outcome — answered from the same analysis that feeds Conversation Insights, so a figure here is the figure there. The same tabs exist on every agent's conversations page, locked to that agent.

Where the tabs are

• The dashboard. After the built-in tabs come your own tabs, then the ones your team shared with you (a small dot marks a shared tab), then + New tab. Six show; the rest sit under More.
• An agent's conversations page. A chat agent's Conversations, a voice agent's Calls, an SMS agent's SMS Conversations and a mail agent's Emails page carry a List | Analytics strip under the header. Analytics holds the tabs built for that one agent: every widget counts that agent's conversations only, and the date range is the page's own range (the last 30 days when the list has none). An agent's tabs are separate from the dashboard's.

A tab is yours: nobody else sees it until you share it (below).

Start from a question

+ New tab offers a starter or a blank tab:

Starter	What it answers
Service quality	How conversations end, how people feel, whether the resolved share is improving, unanswered questions.
Where conversations come from	The pages chats start on, the channels, the ad campaigns behind them.
Agents side by side	Outcomes and volume per agent.
Busy hours	Which hours and days conversations land on.
This agent at a glance (agent pages only)	Outcomes, feeling, knowledge gaps, topics and timing for the one agent.

A blank tab shows three one-click suggestions and Build my own. Every starter widget can be edited or removed afterwards.

Add a widget

Add widget opens the builder. One sentence builds the widget, and the preview on the right redraws as you change it:

• Question — the line the card shows as its title. The builder drafts one from your choices; you can rewrite it.
• Show me — Conversations (a count), the share of conversations where a field has a value, or the average or sum of a number (call length, effort, a score, revenue from a pack).
• Broken down by — the field that splits the count: outcome, topic, feeling, the page a chat started or ended on, the hour or weekday, the agent, the channel, the device, the place, how the visitor arrived, and every field your summary prompt or a process pack adds. A number splits into ranges you set by their edges (<60 · 60-300 · 300+ seconds, for example).
• Chart — every chart the builder knows is listed; the ones that fit what you chose are live and the best fit is picked for you. A chart that does not fit is greyed with the reason (a time split draws over time, needs a second split to stack); tap it to read why. Changing the chart never changes the figures — it is the same count drawn another way.
• Compare with — the previous period or the same period last year adds a change badge to a tile, a washed-out Before bar beside every bar, and a dashed line of the previous window on a trend. Two values side by side compares two values of one field (two agents, two channels, two pages). One value vs everything else sets one value of a field against every other conversation (the new section of the site against the rest, one campaign against all others) with no second value to pick.

Advanced (remembered per person) adds a second split (and by), Panels by (one small chart per value of a third field), Filter (up to six conditions, with your workspace's own values offered — see Filter a tab for the conditions), Format, Top N and Min cell. Add to tab saves the widget (Save changes when editing one); the tab runs again.

Which chart for what

One split offers Bar and Column (one hue, longest first), Doughnut, Pie and Polar area (part of a whole; past six slices — eight on a polar — the rest fold into All others, which the table still lists in full), Radar (an outline over three or more values, good for a profile such as topics or effort), Treemap (share of the whole as area, for a long list of values), Pareto (bars ranked with the running share and an 80 % line, for which few values make most of the volume), and Word cloud (free values such as topics or pages, sized by count). A time split offers Area, Line and Columns over time. Two splits offer the Heatmap, Stacked bar and 100% stacked (share within each bar), and, with time first, the same area, line and columns with one series per value plus Rank over time (a bump chart: which value led each week). Three or four splits offer the Flow. Ordered scales (a feeling, an effort, a funnel step) keep their order and their colour ramp whatever the chart, and a clock or a week keeps every hour and day, including the empty ones. An agent split names the agent, not its id.

Filter a tab: one part of the site, one campaign, one language

The Filter button in the filter row sets conditions every widget on the tab inherits, and the line above the widgets, the footers and the drill-downs count only the conversations that match. Up to six conditions, all of which must hold; a chip under the row says each one in words, and anyone reading a shared tab sees the same chips.

A condition is a field, a comparison and a value. The value box offers your workspace's most common values for the field, and as you type it offers the values that contain what you typed, so a long list of pages or topics is reachable. Besides is, is not, is one of and is set, the text comparisons select by shape, so a section of the site needs no list of pages:

• starts with — Start page · starts with · /concierge/ keeps every chat that opened under that section, new pages included.
• contains — Start page · contains · pricing; Topic · contains · refund.
• matches pattern — * stands for anything: Start page · matches pattern · /clinics/*/book keeps the booking page of every clinic.
• Each has a does not twin, several alternatives are joined with | (/concierge/|/help/), and case does not matter.

So "what happens on the new part of the site" is one tab: Filter → Start page · starts with · /the-section/, then widgets for outcomes, topics, feeling, hour of day, where the chat ended and whether the visitor was new, with Compare with the previous period on the one that matters. The same conditions are offered on a single widget under Advanced → Filter when only that widget should narrow.

Start page is the page the chat opened on; End page is the page the visitor last wrote from, which is empty for conversations closed before your workspace's close-time facts were filled in (see What the figures count).

Arrange the tab

Edit layout turns on the handles: drag a widget by its handle, resize it from the corner, or use the kebab's Move & size row to nudge it one cell at a time with the keyboard. Done turns them off again. The layout saves on its own (Saved appears in the header). Reading a tab shows no handles at all.

The row above the widgets narrows every widget on the tab together: the channel and the handled-by chips, and the tab's own Compare setting (vs previous period, vs same period last year) for every widget that does not set its own. The date range is the dashboard's range, or the page's range on an agent page.

Clicking a bar, a slice or a cell lists the conversations behind it, exactly as on Conversation Insights; a widget's kebab exports its data as CSV (any widget) or PNG (a bar, line, doughnut or stat; a heatmap or a table exports as CSV).

Share, duplicate, delete

The tab's kebab (⋯) holds Share with the team — the tab appears for everyone in your workspace who can read analytics, read-only for them, and the header says Shared with everyone who can read analytics. Stop sharing takes it back. Sharing needs the analytics: manage permission; reading a shared tab needs analytics: read.

Duplicate makes a private copy of your own tab; on a tab shared with you it is Duplicate to my tabs — the way to start from a colleague's work. The pencil beside the tab's name renames it in place. Delete tab removes it for good.

What the figures count

A widget counts what Conversation Insights counts: every closed, billable conversation on every channel in the range, handled by a production agent. On an agent page, only that agent's. A card's footer says how many conversations in the range carry the field it reads (312 of 340), which matters for the fields written at the end of a conversation:

• Where a chat ended is the page the visitor last wrote from, not where the browser went afterwards. Pages visited lists every page the visitor viewed during the chat, in order, so Pages visited · starts with · /the-section/ selects chats that touched the section at any point, whether they started there or walked in later.
• Device (desktop, phone, tablet; the browser and the system) comes from the chat widget's page visits; chats that happened before the widget reported it have none.
• New or returning is whether the same contact had an earlier conversation on any channel; a conversation without a contact is anonymous.
• Tools used and tool errors come from the conversation's own log; SMS and email conversations cannot tell an errored tool call from a successful one, so their error count is not reported.
• How the visitor arrived (the referring site, UTM) is what the chat page recorded; it is the page's attribution, not the first touch.

The Emails page's Analytics counts the email threads the agent handled; the list beside it counts sent emails, failed and skipped ones included, so the two differ by design.

Reading a tab from a connector

An MCP connector can list the tabs shared with the team (list_dashboards) and run one (run_dashboard) for the same figures the screen shows. A connector has no login of its own, so it never sees a private tab. See MCP servers.