This article explains how Hugo Analytics helps you monitor AI Agent activity, outcomes, and improvement opportunities.

Analytics make it easier to understand what Hugo handles, where conversations are escalated, and which topics generate the most volume. Use these insights to improve training resources, instructions, routing, and the overall automation strategy.

Watch the Hugo Analytics walkthrough

If you prefer a quick visual walkthrough, this video shows how to use Hugo Analytics to understand what your AI Agent is doing, review real conversations, analyze workflow heatmaps, and identify what customers ask the most.

Where to monitor the AI Analytics?

Hugo Analytics lets you monitor three main types of data in the AI Analytics section:

1. Conversation Funnels
2. Escalation rate
3. Topics volume

To find this data go to: AI Agent → Evaluate → Analytics

Conversation Funnels

Conversation Funnels show the full journey of conversations handled by Hugo, from their entry point to their final outcome.

You can see whether a conversation passed through the AI Agent, a Workflow, or an integration, and how it eventually ended, for example as Handled by AI Agent, Escalated, or Routed to Inbox.

Each conversation is counted once based on its final outcome, so the different outcomes represent the actual distribution of conversations without counting the same conversation several times.

You can click on a branch to access more details about the conversations associated with that step or outcome.

Depending on the branch, you can download the conversations for further analysis or open them directly in Hugo Observability to inspect what happened during individual conversations.

This is especially useful to:

• Understand how conversations move through Hugo, Workflows, and integrations
• Review how Hugo handled specific cases
• Identify where conversations are escalated or routed elsewhere
• Improve your training data, Routing, and Workflows based on real conversations

Escalation rate

The Escalation rate shows the percentage of conversations that Hugo escalated to your support team over the selected period.

It helps you understand how often customer requests require human intervention and how this evolves over time.

This is especially useful to:

• Track whether your escalation rate is increasing or decreasing
• Spot unusual increases in conversations handed over to human support
• Measure the impact of changes to your training resources, Instructions, Routing, or escalation configuration
• Combine escalation data with your Conversation Funnels and Topics to understand where human handovers are coming from

A higher escalation rate is not automatically a problem. Some requests may require human judgment or be intentionally configured to escalate.

If you notice an unexpected increase, use Hugo Observability to inspect individual escalated conversations and understand what happened before the handover.

To review how Hugo should transfer conversations to your team, read How to configure escalation with Hugo AI Agent.

Workflow heatmap

The workflow heatmap gives you a visual overview of how your workflows perform in real conditions.

It highlights the most triggered paths and steps in your workflows based on real conversations.

This allows you to quickly identify:

• Which parts of your workflows are used the most
• Where users drop or get stuck
• Which paths might need optimization

By analyzing this, you can simplify your workflows and improve the overall experience.

Topics volume

This value indicates what topic have been triggered the most and the data associated. If you want to find out how to set up a Topic, you can refer tothis article.

Here as well, you can hover each of the topics to have an insight on the numbers and percentage for each value.

You can also click on a topic to access more details. From there, you can download the conversations associated with this topic to analyze them more deeply.

This is especially useful to:

• Understand what users are actually asking for this topic
• Identify gaps in your knowledge base or training data
• Improve Hugo’s responses based on real conversations

In a nutshell 🌰

Which data can you monitor thanks to the AI Analytics?

• Track your escalation rate and its evolution over time
• View the topic recurrence of conversations received
• Review the steps and routings taken by Hugo when handling those conversation
• Download and review real conversations handled by Hugo
• Visualize workflow usage with the heatmap
• Compare the data on the topics
• Analyse which workflows are the most triggered by your users

Updated on: 05/09/2026