Skip to main content

How to detect and report on personal agent conversations

Use Personal agent likelihood to spot conversations started by personal AI agents, route them with audiences, and report on them.

Use this article to identify conversations that a personal AI agent started in the Fin Messenger, route them with audiences, and report on them.


What is personal agent detection?

Personal agent detection is a feature that rates every new Fin Messenger conversation on web with a Personal agent involved attribute: No, Likely, or Yes. The rating tells you how likely it is that a personal agent started the conversation instead of a person.

Personal agents are AI assistants that act for a person. They open your website, open the Messenger, and chat with Fin the way a person would.

Why use personal agent detection?

Personal agent detection helps you separate these conversations from your human ones. You can:

  • View the personal agent rating on conversations in Fin.

  • Use Fin audiences to send likely personal agents to your own procedures.

  • Review how Fin handles them in reports, including resolution and escalation rates.

Note: Nothing changes for your customers. They never see the rating, and the Fin Messenger works as before. Fin only behaves differently if you set up an audience or procedure that uses the rating.


How does Fin rate a conversation?

When a visitor starts a new conversation in the Fin Messenger on web, Fin rates it. Fin saves the rating on the conversation in the read-only Personal agent involved attribute.

Rating

When Fin assigns it

Yes

Fin is confident that a personal agent started the conversation.

Likely

Fin thinks a personal agent probably started the conversation.

No

The default rating, when neither of the above applies.

Fin sets the rating when the conversation is created, before Fin's first reply, so it's ready when audiences are matched.


How to choose your personal agent detection setting

The Personal agent detection setting controls if Fin detects whether a personal agent, rather than a person, is contacting you through the Fin Messenger. The result is saved on each new conversation so Fin and reports can use it.

  • Enabled: Fin detects personal agents and saves the rating on each new conversation.

  • Disabled: No detection runs. Ratings already saved on past conversations are kept.

To configure this setting:

  1. Go to Settings > Security > Data.

  2. Scroll to the bottom of the page to the Personal agent detection section.

  3. Open the dropdown and select Enabled or Disabled.

  4. Click Save.


How to use the Personal agent involved rating

View the rating on a conversation

You can see the Personal agent involved attribute when you view a conversation in Analyze > Conversations. Open a conversation and look for Personal agent involved in the Conversation attributes panel. The attribute is read-only, so you can't edit it.

A conversation in Analyze > Conversations. The Conversation attributes panel on the right is filtered to Personal agent, and shows Personal agent involved with the value Yes.

Use the rating in audiences

You can build Fin audiences from the Personal agent involved attribute and apply them to Fin. For example, you can set up a procedure that only runs for Likely or Yes conversations by selecting that audience in the procedure's audience targeting.

Use the rating in reporting

You can filter any report by Personal agent involved, or use it to break down any chart, including:

  • Fin resolution rate

  • Fin escalation rate (conversations that Fin routed to your team)

  • New conversations

  • Open conversations

  • New conversations compared with conversations replied to, over time

Note:

  • The rating is an estimate. Expect some people rated Likely and some personal agents rated No.

  • Only conversations started in the Fin Messenger on web are rated. Conversations from the iOS and Android SDKs (software development kits), email, and other channels aren't rated. Voice isn't supported yet.

  • Only new conversations are rated. Fin sets the rating once, when the conversation is created, and it doesn't change later.

  • Older conversations aren't rated. Only conversations created after November 13th, 2026 have the attribute (there's no backfill).


FAQs

Will personal agent detection change how Fin answers my customers?

Personal agent detection doesn't change how Fin answers your customers by default. Fin and routing only act on the rating where you use it in an audience or procedure.

Can customers see the Personal agent involved rating?

Customers can't see the Personal agent involved rating. The Fin Messenger behaves exactly as before. Your team can see the rating on a conversation in Analyze > Conversations, but can't edit it.

Can I edit or clear the Personal agent involved attribute on a conversation?

You can't edit or clear the Personal agent involved attribute on a conversation. The attribute is read-only.

Why is the Personal agent involved attribute missing from some conversations?

A conversation has no Personal agent involved attribute if it didn't start in the Fin Messenger on web, if it was created before November 13th, 2026, or if Personal agent detection was set to Disabled when it started. Fin doesn't rate conversations from the iOS and Android SDKs, email, or other channels, and it doesn't backfill older conversations. Reports also leave these conversations out of any Personal agent involved breakdown.

Why was a person rated Likely or Yes, or a personal agent rated No?

A person can be rated Likely or Yes, and a personal agent can be rated No, because the rating is an estimate. It isn't proof that a personal agent did or didn't start the conversation.

How do I turn off personal agent detection?

To turn off personal agent detection, go to Settings > Security > Data, scroll to the bottom of the page, set Personal agent detection to Disabled, and click Save. No detection runs while the setting is Disabled, and ratings already saved on past conversations are kept.


💡Tip

Need more help? Get support from our Community Forum
Find answers and get help from Intercom Support and Community Experts


Did this answer your question?