Skip to main content
Test mode lets you see how the Customer Agent would handle your support before it replies to any customer. The Customer Agent runs on your real threads but sends nothing. Instead it adds a timeline entry showing what it would have done: the reply it would have sent, or why it would have handed off to your team. Your team keeps handling every thread the same way they do now. The Customer Agent only adds its private timeline entry, which customers never see. It doesn’t message the customer or act on the thread in any other way, like leaving notes or changing its status or priority. This lets you check the Customer Agent’s behavior, and build trust, on your own threads without affecting the customer experience.

​
Live and test mode

You choose the mode each time the Customer Agent is assigned to a thread, through a workflow or manually, so the Customer Agent can reply on one queue while it runs in test mode on another:
  • Live: the Customer Agent replies to customers. It becomes the thread’s main assignee.
  • Test: the Customer Agent sends nothing and adds private timeline entries showing what it would have done. It joins as an additional assignee, so whoever owns the thread keeps it and your queues and assignment rules stay the same. A thread with no other assignee still shows in Not assigned.

​
What you’ll see

On threads where the Customer Agent is in test mode, the Customer Agent adds private timeline entries when new customer messages are added to a thread. Each entry starts with the agent’s display name, and you’ll see one when:
  • It would have replied, along with the draft answer it would have sent;
  • It would have handed off, along with the hand-off reason; and when
  • It would not have responded.
These entries are internal, so customers never see them. Once the Customer Agent would have handed a thread off to your team, it stops adding entries to that thread, the same as when the Customer Agent is operating in live mode. A test mode entry where Customer Agent would have replied

​
Choosing live or test mode

​
In workflows

Every workflow action that assigns threads to the Customer Agent has its own mode. Pick Live or Test when you assign the Customer Agent in a workflow. Choosing Live or Test for Customer Agent in a workflow's assign step Workflow conditions decide which threads the Customer Agent picks up, so you can scope each step by any condition workflows support, such as tier, label, channel, or business hours. One workflow can have several Customer Agent assignments, each with its own mode. When you’re happy with the Customer Agent’s drafts, switch its assignment to live.
If you used the now-deprecated workspace-wide Live or Shadow setting, your existing workflows kept the mode your workspace was set to.

​
Manually

You can also pick Live or Test when you assign the Customer Agent from a thread’s assignee picker. Choosing Live or Test for Customer Agent in a thread's assignee picker

​
Tracking live and test mode assignments

Two places in Plain AI show how your workflows use each mode. Customer Agent overview: the Customer Agent status card shows how many of your workflows assign the Customer Agent in live mode and how many in test mode. Live and test mode workflow counts on the Customer Agent status card Customer Agent preferences: hover a workflow row to see how many of its Customer Agent assignments are live and how many are in test mode. Live and test mode step counts when hovering a workflow on Customer Agent preferences

​
Knowledge gaps in test mode

When the Customer Agent would have handed off because it couldn’t find an answer in your knowledge sources, it records a knowledge gap exactly as it does live. The gap is grouped with repeat questions and raises a task for your team once a second thread asks it, so you can fill the holes in your documentation before the Customer Agent starts replying to customers. The test mode entry on the thread doesn’t mention the gap. Find it under Customer Agent → Knowledge → Knowledge gaps or as a task linked to the thread.

​
Reading via GQL

In test mode the Customer Agent writes its outcome to the thread’s timeline as a Thread Event. Read it like any other timeline entry, filtering to events:
Test mode events are identified by their externalId, which starts with ari-dry-run. When the Customer Agent would have answered, the drafted reply is the ComponentText inside the event’s ComponentContainer.

​
Testing a new version of your setup

Test mode uses the instructions and knowledge saved in your workspace. To compare a new version before it reaches customers, see test changes to the Customer Agent.