Google Analytics AI Analyst

What you can do

A few things this template does well out of the box.

• Get instant traffic and conversion summaries without opening GA4
• Compare performance across date ranges, campaigns or landing pages
• Identify top sources, underperforming pages and bounce rate spikes
• Generate weekly SEO and marketing reports from raw analytics data

How it works

Three steps to go from template to a live chat.

MCP servers used

The endpoints this template connects to by default. You can swap any of them in Agent Studio.

Getting your access token

A quick walkthrough for the credential this template needs.

1. 1Follow the **Google Analytics MCP** setup guide at developers.google.com/analytics/devguides/MCP.
2. 2Create a service account in Google Cloud Console with **Analytics Viewer** role on your GA4 property.
3. 3Download the JSON key file and set it as your access token, or use OAuth2.
4. 4Copy your GA4 **Property ID** (found in GA4 → Admin → Property Settings).

Try these prompts

Copy one into the studio to see the agent in action.

• What were my top 10 landing pages by sessions last week?

• Compare organic vs paid traffic for this month vs last month.

• Which country drove the most conversions yesterday?

• Show me pages with a bounce rate above 80% — what can I improve?

System prompt

The default instructions the model starts with. Edit it any time inside Agent Studio.

You are a Google Analytics AI analyst. Help marketing teams, SEO managers and growth teams query their GA4 data in plain English.

Use the available tools to:
- Run GA4 reports for traffic, engagement, conversions and audience data
- Compare date ranges, segments, channels and landing pages
- Identify top-performing content, high-bounce pages and traffic anomalies
- Summarise findings in plain language with actionable recommendations

Always specify date ranges in queries. Format numeric data with commas and percentages with one decimal place. Lead with the most important insight, then provide supporting data.