Set up and deploy automated FAQs
Not sure what an FAQ model is? Read our tutorial on creating an FAQ model before you start.
What you'll need
At least one FAQ topic
For each FAQ topic, at least three example questions
For each FAQ topic, at least one answer
Step one: Set up your FAQ model
Go to Automate work > AI Hub > Generate FAQ Answers.
Click Create new FAQ model.
In the Model name’ field, enter a descriptive name for your model, such as ‘Shipping’.
In the ‘Set up FAQs’ section, click + Add new FAQ. A panel will open on the righ-hand side of your screen.
Click + New matching phrase.
In the text field, enter a question.
Click + New matching phrase and add another question. Continue this process until you have added all of your question variations.
If you want to delete a question variation, click the ‘delete’ icon next to the question.
In the Answer field, enter the answer that corresponds to the example questions you have provided.
Click Save.
[Optional] In the ‘Irrelevant content’ section, click Irrelevant content. Click +New matching phrase and enter the irrelevant content that you want to exclude. Click Save.
If you have more than one FAQ topic that you would like to include in this FAQ model, repeat steps 4-10.
To publish your FAQ model and begin training the model, click Publish.
You've just created a new FAQ model!
Step two: Train and test your model
Once you’ve published an FAQ model, you’ll have to wait for the model to be trained before you can use it. The training process happens automatically when you publish an FAQ model - you don’t need to do anything else.
Training a model is typically a quick process, but it will take longer if you have lots of FAQs, and/or lots of question examples.
You can see the status of your FAQ model by going to Automate work > AI Hub > Generate FAQ Answers and looking under the ‘Status’ column.
When you first publish an FAQ model, its status will be ‘Training’.
If you edit and publish an FAQ model, its stats will be ‘Retraining’.
When your FAQ model is ready to use, its status will be ‘Ready’.
Test your model
Before you use your FAQ model, you’ll first need to test it to make sure that it works as expected.
Go to Automate work > AI Hub > Generate FAQ Answers and select the model that you want to test.
Click View.
In the top right-hand corner, click Test model. A panel will open.
In the text field, type a question, then click Reply.
If the question you ask is recognized and a matching answer is found, this will be returned here.
If the question you ask isn’t recognized, or is matched to an irrelevant question that you’ve provided, this will be returned here.
The model will ask you if it has provided you with the correct answer to your question. If it has provided the correct answer, click Yes, then click Finish and train. The question will be added to the list of example questions that you provided for that FAQ.
If it has provided an incorrect answer, click No. Select the correct answer from the drop-down, then click Finish and train. The question will be added to the list of example questions that you provided for that FAQ.
Step three: Deploy your model
Now that you’ve created, tested, and trained your generate FAQ answers model, you can deploy this model using the Agent Assistant FAQ Answers feature or the generate FAQ answers action for Flows.
Success! You've just deployed automated FAQs!
Edit model
You can edit model at any time by going to Automate work > AI Hub > Generate FAQ Answers, selecting the model that you want to make changes to, and clicking Edit.
Make your changes, then click Publish to retrain your model.
Versioning
When you make changes to your model, we create a new version of that model and archive the previous version.
Go to Automate work > AI Hub > Generate FAQ Answers and select the model you want to download.
Click View.
Click the Versions tab.
Download a model
Models can be downloaded as YAML (.yml) files.
Go to Automate work > AI Hub > Generate FAQ Answers and select the model you want to download.
Click View.
Click the Actions button, then click Download.
Last updated