Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.gumloop.com/llms.txt

Use this file to discover all available pages before exploring further.

Organization Analytics gives enterprise organizations a centralized place to track adoption, performance, and outcomes. It combines a built-in dashboard with an AI-powered conversational interface, so you can explore your organization’s data without writing SQL or building reports.

​
Overview

The analytics page at Settings > Organization > Analytics has two parts: a conversational explorer and a dashboard overview.
Organization Analytics page with conversational explorer and dashboard overview

​
Conversational Explorer

At the top of the page, you can ask questions in natural language. Type a question or pick from the suggested prompts to get instant answers about your organization’s activity. Suggested prompts include:
  • Who are my top 3 most active users this week?
  • What are the most used agents this week?
  • What are the most used MCP servers this week?
The AI agent connects to your organization’s data and returns results as tables, charts, or CSV exports.

​
Dashboard Overview

Below the conversational explorer, the dashboard provides at-a-glance metrics for your organization. Use the date range picker to adjust the time window. Key metrics include:
  • Credits Used Over Time: A chart showing total credit consumption across the selected period.

Credit Tracking

Monitor credit consumption across users, workflows, and agents over any time period

Usage Insights

Understand which workflows and agents are most active and who is using them

User Activity

See which team members are running workflows, chatting with agents, and consuming credits

Visual Reports

Generate charts and download CSV exports for stakeholder reporting

​
How to Access

​
In the Dashboard

Navigate to Settings > Organization > Analytics to access the full analytics page with both the conversational explorer and the dashboard overview.

​
In Slack

You can also use the analytics agent directly in Slack:
1

Add the Gumloop bot to your channel

Invite the Gumloop bot to the Slack channel where you want to use analytics.
2

Enable the analytics agent

Type /gummie add analytics in the channel to activate the analytics agent.
Running /gummie add analytics in Slack
3

Ask your questions

Mention @Gumloop in the channel and ask your analytics questions. The agent will respond with results directly in the thread.
Analytics agent responding to a query in Slack

​
What You Can Ask

The analytics agent has access to the following data about your organization:
DataWhat It Covers
Workflow RunsRun history, credit costs, execution counts, completion timestamps
Agent ChatsChat sessions with agents, credit costs per chat, chat volume over time
AgentsAgent names, descriptions, models used, tools configured, creator info
WorkflowsWorkflow names, descriptions, creator info
UsersUser emails and activity across your organization
MCP ServersMCP server usage across your organization

​
Example Questions

Credit usage: 
How many credits has our organization used in the last 30 days?
Break it down by user.
Workflow activity: 
What are our top 10 most-run workflows this month? Show credit cost for each.
Agent usage: 
How many agent chats happened last week? Which agents are most popular?
MCP server usage: 
What are the most used MCP servers this week?
Trend analysis: 
Show me daily credit consumption for the past 3 months as a chart.
User activity: 
Which users have been most active in the last 7 days?
Show their workflow runs and agent chats separately.

​
Data Access and Permissions

Organization Analytics enforces role-based access to ensure data security:
RoleData Scope
AdminFull access to all organization-wide data across all users
ManagerFull access to all organization-wide data across all users
MemberPersonal data only, can only see their own workflow runs, agent chats, and credit usage
Non-admin and non-manager users are automatically scoped to their own data. They cannot query or view other users’ activity, even if they explicitly ask for it.

​
Security

Organization Analytics is built with multiple layers of data protection:
  • Organization isolation: Every query is automatically scoped to your organization. The agent cannot access data from other organizations, even if prompted to do so.
  • Parameterized queries: All queries use parameterized SQL. User input is never interpolated into query strings, preventing SQL injection.
  • Schema validation: The agent can only query pre-defined tables and columns. It cannot run arbitrary SQL or access tables outside the analytics schema.
  • Role-based scoping: Non-admin users are automatically filtered to their own data at the query level, not just at the display level.
  • Prompt injection protection: The agent is designed to refuse attempts to bypass data access restrictions through prompt injection, role-play scenarios, or other techniques.

​
Credit Usage

Queries made through the analytics agent consume credits based on the amount of data scanned. The agent is optimized to minimize data scanning by:
  • Using aggregation queries instead of raw row dumps
  • Applying automatic partition filters (defaulting to the last 90 days for time-series tables)
  • Limiting result sets to only the data needed to answer your question
For time-range questions, the agent automatically applies efficient date filters. If you need data beyond the default 90-day window, specify the date range explicitly in your question.

Usage Data Export

Export raw usage data as CSV for external analysis

Audit Logging

Track user actions and system events for compliance

Custom Roles

Configure granular permissions and access controls

AI Model Control

Manage which AI models are available in your organization