This tutorial guides you through training and deploying a model using the
Agent Assist Console. You can use the console to train a model and test
its performance, but be aware that all runtime operations must be carried out by
calling the API directly. See the Agent Assist
[how-to guides](https://docs.cloud.google.com/gemini-enterprise-cx/agent-assist/how-to.md.txt) for instructions.

## Create \& train a new model

Navigate to the [Agent Assist Console](https://agentassist.cloud.google.com).
Select the Smart Reply card in the center of the screen and click
**Get started** . The Console tutorial walks you through the process of creating
a dataset, training \& deploying a Smart Reply model, and creating a conversation
profile. You can do this using either a model that you create (trained your own
data or the public conversation dataset), or test the Smart Reply feature using
a demo model. After you have deployed your model, return to this guide for
details about
[allowlist management](https://docs.cloud.google.com/gemini-enterprise-cx/agent-assist/model-training.md.txt#model_allowlist_management).

## Model allowlist management

When a Smart Reply model is created using the Agent Assist console, the creation
process also generates a list of potential suggestions that can be surfaced to
agents during a conversation. This resource is called the **allowlist**. The
allowlist contains all possible suggestions that were generated using your
selected conversation dataset.

To access a model's allowlist, navigate to the **Models** menu, then click on
the model's name. You will be brought to the model's **Details** page. There are
tabs for each of the three sections in the allowlist: **Unreviewed** ,
**Allowed** , and **Blocked** . Each message in the allowlist can belong to one of
these three lists. Blocked suggestions cannot be suggested to agents at runtime.
Only suggestions that appear on the **Allowed** and **Unreviewed** lists are
surfaced during a conversation. By default, all suggestions on the allowlist are
set to **Unreviewed** when a model is created.

### Message grouping

An allowlist might have 50,000+ messages. To make them easier to manage,
Agent Assist automatically groups messages with similar
meaning. You can see a message's similar messages by clicking on the **Show (X)
similar messages** link to the right of the message:

![](https://docs.cloud.google.com/static/gemini-enterprise-cx/agent-assist/images/aa8.png)

### Message search, edits, and creation

You can search all messages in an allowlist using the **search entries** bar at
the top of the page. You can also edit individual messages by hovering over a
message and clicking the pencil icon that appears. A window containing the
message's text appears:

![](https://docs.cloud.google.com/static/gemini-enterprise-cx/agent-assist/images/aa8_1.png)

We recommend that you edit only for spelling and grammar, and do not change the
meaning of the message. The more the edited text deviates from the meaning in
the model, the less likely that message is to be surfaced.

You also have the ability to create a new message by clicking the **+Add a
message** button at the top right of the page. Similarly to edited messages,
created messages are less likely to be surfaced during runtime.

### Allow or block messages

When you select one or more messages in the **Unreviewed messages** list,
**MOVE TO ALLOWED** and **MOVE TO BLOCKED** buttons will appear at the top
right of the page. You can also move individual messages to the allowed or
blocked lists by clicking on the three vertical dots to the far right of the
model's name:

![](https://docs.cloud.google.com/static/gemini-enterprise-cx/agent-assist/images/aa7.png)

## What's next

Use your deployed model to create a
[conversation profile](https://docs.cloud.google.com/gemini-enterprise-cx/agent-assist/conversation-profile.md.txt).