Dashboard - Cloosphere Guide

Admin › Monitoring › Dashboard

The Dashboard auto-generates SQL charts from a single natural language line.

Add and edit panels by chatting with the AI assistant, then share the completed dashboard with your team or export to HTML.

Method	Process	Time
Manual	Write SQL → execute → Excel chart → slide	30 min ~ hours
Dashboard	Natural language input → AI auto-generates chart	30 sec

dashboard list — Admin > Monitoring > Dashboard — list of created dashboards

Access Path

Permission	Dashboard List	Create/Edit/Delete	Shared Dashboards
Admin (monitoring write)	All	✓	✓
Admin (monitoring read)	All	✗	✓
Regular user	Owned + public/shared only	✗	✓

Creating Dashboards

Create dashboard

Click Create Dashboard in the dashboard list.

Field	Required	Description
Name	✓	Dashboard name (must be unique system-wide)
Description	✗	Dashboard purpose

DB connection isn’t configured at this stage. Different DBs can be used per panel, so DB is selected when adding panels.

Add panels

From the created dashboard, add panels via Add Panel or AI Assistant. In the add-panel modal, first choose the Chart / Card type.

Chart
Card

Visualize SQL execution results as various charts. Enter a natural language question in the panel editor and AI auto-generates SQL.

Add panel modal — Chart type — Add chart panel modal

Supported chart types:

Chart	Description	Use Case
Table	Display data in table form	Detailed data viewing
Bar	Per-item comparison	Per-model usage count
Grouped Bar	Compare multiple grouped series	Per-model · per-period cost comparison
Line	Trend over time	Daily token usage trend
Area	Trend + area emphasis	Cumulative usage change
Pie	Ratio distribution	Per-agent usage share
Scatter	Correlation between two variables	Response time vs. token count
Histogram	Numeric distribution	Response time distribution
Heatmap	2D matrix value distribution	Per-time-of-day · per-day-of-week usage

Click the chart-type icon at the top of the panel in edit mode for instant switching.

A summary card showing key KPI values at a glance.

Add panel modal — Card type — Add card panel modal

Source	Description
Manual Input	Direct fixed value entry (e.g., “1,234” or “Active”)
DB Query	Real-time value lookup via natural language → SQL

Specify a background color for visual distinction.

Then configure SQL and period filters in the Panel Editor; for conversational creation, see AI Assistant.

Adjust layout

In Edit mode, drag panels to move them and use the bottom-right handle to resize. Layout is on a 12-column grid.

Panel Composition

A dashboard consists of individual panels.

Each panel has its own DB connection and SQL.
For panel type (chart · card) selection, see the Add panels step.

Usage dashboard composed of multiple panels — Example dashboard with multiple panels — top card metrics arranged alongside chart panels

Panel Editor

Click Add Panel or the edit icon on an existing panel to open the panel edit modal.

Field	Description
Panel name	Panel title (required)
Database selection	Pick the DbSphere to connect
Model selection	AI model used for SQL generation
Natural language question	Describe the data you want in natural language
Generate SQL	AI auto-converts the natural language question to SQL (the generated SQL can be edited directly)
Use period filter	Specify date column to integrate with the dashboard period filter
Title display	Choose where the panel title appears (header / inside bottom)

The generated SQL can be edited freely. If the AI-generated SQL isn’t accurate, just edit it directly.

AI Assistant

Click the purple AI Assistant button at the bottom-right of the dashboard to open a chat panel at the bottom.

Pick a model at the top and describe what you want in natural language.
When starting out, click one of the suggested prompts to begin right away.

AI Dashboard Assistant panel — chat interface for creating and editing panels in natural language — Admin > Monitoring > Dashboard — AI Assistant panel (model selection, example prompts, input box)

Conversational Dashboard Builder

Add, edit, and delete panels by chatting in natural language.

Open AI Assistant

Click the bottom-right purple button. Pick DB and model at the top.

Request in natural language

Examples:

“Make a chart of this month’s per-model token usage”
“Add a per-user cost card too”
“Change the period to 30 days”
“Change the pie chart to a bar chart”

Review AI results

The AI generates SQL and auto-places panels. Positions are auto-adjusted to avoid overlap.

Iterate

Continue panel edits/deletes/relayouts via additional conversation. Conversation history is saved on the dashboard.

Example — Changing an Existing Chart Type Specify the panel to change, and the same data is instantly redrawn as a different chart. For example, entering:

Change the Revenue by City bar chart to a pie chart

Revenue by City bar chart (before) — Before — bar chart

Revenue by City pie chart (after) — After — pie chart

The AI sometimes presents button-form choices. Click for quick responses.

One-shot Generation

Starting fresh with an empty dashboard, describe the dashboard’s purpose to the AI to generate a suitable panel set at once.

DB connection is auto-tested first, generating only when valid.

Filtering

The dashboard top has period filter and custom filters.

Period Filter (TimeRangePicker)

Preset	Description
Today / Yesterday	Today / Yesterday
This Week / Last Week	This week / Last week
This Month / Last Month	This month / Last month
7d / 30d	Last 7 / 30 days
All	Entire period
Custom	Specify start/end dates directly

Default is Yesterday. Changing the period auto-re-executes SQL on all panels with period filter enabled.

Custom Filters (FilterBar)

In edit mode, use the Add Filter button to add filters that apply to the entire dashboard.

Filter Type	Description
Text	Free text input (e.g., username)
Date Range	Start ~ end date range
Select	Selection options

When adding a filter, specify the display label and DB column name. Active filters appear as blue badges at the top of each panel.

Share completed dashboards with team members.

Click the Share button

Click the Share button at the top of the dashboard to open the Share Dashboard window; the share URL is automatically copied to the clipboard.

Share Dashboard modal — share URL, visibility status, edit access and copy link — Admin > Monitoring > Dashboard > Share — Share Dashboard window (share URL, visibility status)

Share URL format: https://{domain}/dashboard/{share_id}. Use Delete share link to revoke sharing at any time.

Edit access (access control)

Click Edit access and copy link to open the Access Control window. Specify the visibility scope and who can access.

Access Control modal — permission (public/private), groups, organizational units — Admin > Monitoring > Dashboard > Share > Edit access — Access Control window

Item	Description
Permission	Toggle between Public (all signed-in users) and Private (only users/groups you grant)
Groups	Grant read access to specified groups
Organizational units	Grant read access to specified organizational units (OUs)

When done, click Edit access and copy link to save the changes and copy the link again.

Shared dashboards operate as view-only — period filter and custom filters can query data, but panel edit/add/delete and AI Assistant are disabled.

Sign-in is required to access share links. Non-signed-in users go to the sign-in page and auto-return to the dashboard.

HTML Export

Export dashboards as standalone HTML files.

Click the Export button at the top of the dashboard to execute SQL with the currently applied period and filter conditions, downloading the HTML file with the latest data.

Exported file characteristics:

Item	Description
Format	Single HTML file (no external dependencies)
Chart interaction	Hover, zoom, and other Plotly default features supported
Theme	Light/dark mode auto-supported (follows system setting)
Layout	Same 12-column grid as the dashboard
Responsive	Charts auto-adjust on window resize

Exported HTML files can be email-attached, uploaded to internal share drives, or integrated with scheduled tasks for regular reports. See Schedules for details.

Security

Item	Policy
SQL execution	Only `SELECT` queries allowed. INSERT/UPDATE/DELETE/DROP and other modification queries are blocked
Filter input	Special character escaping to prevent SQL Injection
Share access	Verification based on access control (public/private permission + group/organizational-unit designation)
DB connection	Only read-only connections registered in DbSphere

Use Cases

Executive KPI Monitoring

AI auto-generation via “Make a key KPI dashboard for this month”
Card panels show key values (total revenue, active user count, etc.)
Line charts show daily trends
Share as Public for team-wide access

Periodic Report Automation

Compose monthly report panels in the dashboard
Integrate HTML export with scheduled tasks
Auto-generate HTML reports and email every Monday morning

Model Usage Analysis

Generate charts via “Compare per-model token usage and cost”
Grouped Bar for per-model · per-period comparison
Analyze across last 7 days/30 days/all via period filter

Database (DbSphere)

Configure databases that the Dashboard connects to

Schedules

Scheduler for automating dashboard exports

Usage

Token usage and cost statistics dashboard

​Access Path

​Creating Dashboards

​Panel Composition

​Panel Editor

​AI Assistant

​Conversational Dashboard Builder

​One-shot Generation

​Filtering

​Sharing

​HTML Export

​Security

​Use Cases

​Related Pages

Database (DbSphere)

Schedules

Usage

Access Path

Creating Dashboards

Panel Composition

Panel Editor

AI Assistant

Conversational Dashboard Builder

One-shot Generation

Filtering

Sharing

HTML Export

Security

Use Cases

Related Pages