Dashboard
The Dashboard (Home) is your primary command centre for understanding conversation volume, message depth, and function-tool adoption across any time window you choose. It answers the question: Is my agent being used, and is usage growing?
Open the Dashboard first every morning to catch overnight spikes or silent outages before your users notice them.
Opening the Dashboard
Click the hamburger menu (☰) in the top-left corner to open the sidebar, then click Home.
In the sidebar, confirm Home is highlighted before continuing.
The Dashboard loads with five metric cards at the top and two chart panels below.
You should immediately see the KPI cards in the top row, with analytics charts directly underneath.
Metric Cards
The five cards give you an immediate health-check of your agent. They update automatically whenever you change the period selector.
| Card | What it measures | What to look for |
|---|---|---|
| Total Conversations | Number of distinct conversation threads started | Sudden drops may indicate a channel or access issue |
| Total Messages | Sum of all messages sent and received | A stable ratio to conversations suggests predictable usage |
| Average Conversations | Conversations per hour / day / month (adapts to period) | Growth over time means the agent is finding its audience |
| Average Messages | Messages per hour / day / month | A rising average without more conversations can mean longer exchanges |
| Average Messages / Conversation | Mean depth of each conversation | Ideal depth varies by use case; a rising number can mean the agent is not resolving requests efficiently in one reply |
If any card appears unusually low or flat compared to recent periods, treat it as an early warning and drill down in the charts below.
Reading the Averages
The average cards adapt their denominator to the selected period. In a 24-hour view, averages are per hour. In a 30-day view, averages are per day. In a 12-month view, averages are per month. This makes them directly comparable regardless of how long the selected window is.
A rising Average Messages / Conversation over multiple weeks is one of the earliest signals that something in the agent is not resolving user needs cleanly. Common causes include:
- Knowledge resources that answer part of a question but leave follow-ups unanswered
- Mission scope that is too narrow, causing the agent to deflect edge cases
- Interaction style that asks too many clarifying questions before answering
Period Selector
Click any of the four period buttons — 24 Hours, 72 Hours, 30 Days, or 12 Months — to change the time window for all charts and cards simultaneously.
The period controls are located near the top of the Dashboard and update every panel in place.
When to use each period:
| Period | Best use |
|---|---|
| 24 Hours | Daily morning health check. Catches overnight spikes or outages immediately. |
| 72 Hours | After deploying a configuration change. Shows the before/after window in a single view. |
| 30 Days | Weekly reviews. Reveals weekly patterns and sustained trend changes. |
| 12 Months | Monthly business reporting and year-over-year comparisons. |
Changing the period does not navigate away from the Dashboard — all panels update in place. Use this fluently to zoom in when something looks unusual.
Conversation Chart
The grouped bar chart shows Total Conversations (purple) and Total Messages (blue) side by side for each time bucket in the selected period.
Read each grouped pair left-to-right to compare thread starts versus message volume in the same bucket.
Patterns to Look For
| Pattern | Likely explanation |
|---|---|
| Spike followed by a sharp drop | Viral mention or a campaign that did not convert to regular users |
| Consistent low volume at specific hours | Region-specific audience; note the window for maintenance scheduling |
| Messages growing faster than conversations | Users are writing more per session — possible confusion or incomplete answers |
| Both metrics flat for several weeks | Discovery problem; users do not know the agent exists or cannot access it |
| Conversations high but messages low | Users open the chat and leave immediately — check the opening greeting |
Bar Drilldown
Click any bar to open a drilldown panel beneath the chart. The panel shows the individual conversation threads that occurred during that time bucket, with a time-range slider to narrow further. Click any thread row to open the full conversation detail.
After selecting a bar, look directly below the chart for the drilldown table and filtering controls.
Tip: Enable the "Only conversations with messages" filter in the drilldown to exclude sessions where the user opened the chat but never typed anything. This gives you a cleaner signal for engagement rate.
Function-Tool Usage
Below the conversation chart, the Function Tools panel shows two visualisations:
- Pie chart — Proportional breakdown of how often each function tool was invoked across all conversations in the selected period.
- Usage history bar chart — Click a slice in the pie chart to plot that tool's invocations over time.
The pie appears first in the Function Tools panel; the corresponding usage history chart updates beneath it after you click a slice.
Why Tool Adoption Matters
The AI model decides which function tools to invoke based on their configured Name and Description. If a tool is correctly configured but seldom appears in the pie chart, the description is probably too vague for the model to recognise when it applies.
Common tool adoption issues:
| Symptom | Likely cause | Fix |
|---|---|---|
| A tool with a tiny slice despite frequent relevant queries | Description too generic | Rewrite the description with specific trigger phrases and example scenarios |
| A tool dominating the pie unexpectedly | Description too broad | Narrow the description to only the scenarios where this tool is the right choice |
| A tool completely absent from the chart | Tool disabled or configuration error | Check Custom API or plugin settings for the tool |
| Two tools sharing roughly equal usage for the same scenario | Overlapping descriptions | Differentiate the descriptions to remove ambiguity for the AI |
Clicking Through
Click any pie slice to switch the history chart to that tool's time series. Use the same period selector as the rest of the Dashboard to compare tool adoption across time windows. A tool whose usage is trending downward after a description change may mean the new description is less effective — revert or iterate.
Exporting the Dashboard
Click the â‹® (three-dot menu) at the top-right of the Dashboard and select Download as PDF to export the current view including all charts and metrics.
If you do not see the option immediately, open the top-right overflow menu first, then choose Download as PDF.
When to export:
- Before a configuration change — baseline snapshot to compare against after the change
- After a configuration change (72 h later) — confirm the change had the intended effect
- Weekly stakeholder review — attach to a report as objective evidence of trend direction
- Monthly business reporting — year-over-year archive showing growth
Best practice: Name your exports consistently, for example
dashboard-YYYY-MM-DD-30d.pdf, and store them in a shared folder so any team member can find the historical baseline.
Related Pages
- Analyse User Feedback — understand what users rate negatively and why
- Investigate with Monitoring Logs — trace errors and debug integrations at a technical level
- Analytics & Logs Overview — monitoring cadence and improvement loop
- Automate with Custom API — configure the function tools whose adoption you track here