The 3 Necessary Triggers
You need at least 3 triggers to make botBrains work in your Zendesk:[botBrains] Assign AI
[botBrains] Assign AI
This trigger is auto-created and by default targets all new tickets created.
You can scope the conditions down as you like. See Configuring When botBrains Should Answer for common customizations.

[botBrains] Escalated by AI
[botBrains] Escalated by AI
This handles how escalations from the botBrains AI are handled in your system. If you want to escalate to different groups based on a field (e.g., Topic annotated by AI), duplicate this rule and add the additional field under ALL conditions and change the target group.

[botBrains] Escalated by Human
[botBrains] Escalated by Human
This handles how escalations by your customers forcing to speak to a human will be handled.

Configuring When botBrains Should Answer
You can configure which tickets botBrains should process with the trigger “Assign botBrains [DO NOT EDIT]”. While the name suggests differently, it is actually intended that you steer in which cases botBrains should run. Common customizations include:-
Exclude automated requestors - Some email addresses are automated systems. Examples include
service@paypal.deandebay@ebay.com. If it’s difficult to exclude them in Zendesk, you can also use Settings > Triggers and configure Block rules in botBrains. -
Limit channels - If you support emails and voice calls, you likely don’t want to respond to empty ticket transcripts. Filter by
Ticket > Channelany ofemailandwebform. -
Limit brands - Use filters like
Ticket > Brand is XYto restrict botBrains to specific brands.
Adding the Legal Disclaimer
In Germany, automated systems must be declared. Edit your trigger “Inform Requestor of Comment Changes” to include a disclaimer when the current group isbotBrains AI.
- With Brands access
- Without Brands access
Add the disclaimer via the brand-specific signature text:
Understanding the Processing of Tickets
1
Show the ticket to botBrains
You can trigger the execution of botBrains on a ticket by assigning it to the
botBrains AI group. Adding comments (public or private) will also trigger a rerun.2
Decide Response
botBrains will only respond to tickets where the last comment is authored by the requestor. This is also true for metadata prediction.
3
Generate Response
botBrains will first predict the ticket form and then the relevant custom fields for that ticket form. It will then generate a comment. The configuration and a different system decide if that answer will be a public or a private comment (note).A ticket that is processed by botBrains will receive the
processed_by_botbrains tag. If botBrains decided that it should be a private comment, the ticket will always be escalated.Tags Used by botBrains
All changes from botBrains via API are made by the User AgentbotBrains Agent.
| Tag Name | Meaning |
|---|---|
processed_by_botbrains | The ticket was successfully processed by botBrains. |
escalated_by_botbrains | The ticket was escalated by the botBrains AI. |
escalated_by_botbrains_failsafe | An error occurred (at least partially) during processing by botBrains. botBrains does not keep any ticket in status Open or New for more than 2 hours and will always escalate these. |
blocked_by_botbrains | The ticket was processed by botBrains but rules prohibit generating a response. |
botbrains_force_private_mode | Activates Private Mode for individual tickets. Allows disabling Preview Mode, but can be annotated by triggers so that some tickets are always processed in Preview Mode only. |
How to Escalate
botBrains will escalate all tickets that are in status New or Open after generation. This can happen through:- The AI agent calling
escalate_to_human- The AI decides escalation is needed - Custom Field Prediction - When choosing Custom Status setting to
Openas the next correct step
Ticket Field Prediction
botBrains can automatically categorize tickets and fill custom fields using AI. The Field Predictor selects ticket forms, sets priorities, fills custom fields, and adds tags based on ticket content. To configure field prediction:- Click the Predictor button on your integration card
- Enable the predictor and configure which fields to predict
- Provide instructions for each field
- Test with historical tickets
