Documentation Index

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

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

What is Tugger AI Insights?

Prev Next

Tugger AI Insights lets you ask questions about your business data using everyday language — no reports to build, no formulas to write. Connect Tugger to an AI platform like Claude, and simply ask things like "Who are my top 10 customers this quarter?" or "How many hours did the team log last week?"

The AI queries your live Tugger data and gives you answers in seconds.

How it works

Tugger AI Insights uses MCP (Model Context Protocol) — an open standard that lets AI platforms securely connect to your data. Instead of exporting data or copying it into a chat window, the AI connects directly to Tugger and queries your data in real time.

Here's the flow:

  1. You connect your AI platform (e.g. Claude) to Tugger's MCP server
  2. You authorise via a secure OAuth login — the same kind of login you use with Google or Microsoft
  3. You ask a question in plain English, and the AI fetches the answer from your Tugger data

There's nothing to install and no API keys to manage.

Which AI platforms are supported?

Platform Status
Claude (Anthropic) ✅ Available
ChatGPT (OpenAI) ✅ Available
Gemini (Google) ✅ Available
Cursor (Anysphere) ✅ Available
Perplexity ✅ Available

We're always looking to add more platforms. If there's one you'd like to see, let us know.

Security & access control

AI Insights is designed with security at its core:

  • OAuth authentication — no passwords or API keys are shared with the AI platform. You log in securely through Tugger each time.
  • Per-user connector access — your Tugger admin controls exactly which connectors each user can access through AI Insights. A user can be given access to none, one, or multiple connectors.
  • Your data stays yours — the AI platform queries your data on demand. Tugger doesn't send your data to AI platforms in bulk.

Access is managed in the Tugger MCP Configuration section. See Tugger MCP Configuration for details on managing user access.

What can you ask?

The beauty of AI Insights is that you don't need to know your data structure — just ask what you want to know. Here are some examples by connector type:

Accounting & Finance (Xero, QuickBooks, Sage 50)

  • "What's our total revenue for the last 3 months?"
  • "Show me all overdue invoices over £1,000"
  • "Which customers owe us the most right now?"

CRM & Sales (HubSpot, Pipedrive, Zoho CRM)

  • "How many deals did we close this month?"
  • "What's our average deal size this quarter vs last?"
  • "Which sales rep has the most deals in pipeline?"

Project & Job Management (Simpro, Jira, monday.com)

  • "Which jobs are currently overdue?"
  • "What's our average job completion time?"
  • "Show me all open jobs for customer X"

Time Tracking (Clockify, Harvest, Deputy)

  • "How many hours did the team log last week?"
  • "Who logged the most billable hours this month?"
  • "What's our billable vs non-billable split?"

For more tips, see Tips for Getting the Best Results from AI Insights.

Getting started

Ready to try it? Follow the setup guide for your AI platform:

Connecting Tugger to Claude
Connecting Tugger to ChatGPT
Connecting Tugger to Google Gemini
Connecting Tugger to Cursor
Connecting Tugger to Perplexity