AI agents

Build AI agents to respond to your customers

IN SHORT

Fullwhere AI agents allow you to set up automatic response generation.

They can be customized using different instructions.

An agent can be linked to a knowledge base to use a particular context to generate responses.

You can configure different AI agents depending on the context in which you want to use them. For example, you can choose to specialize your AI agents by interaction family, by brand or by location.

Once your AI agents are configured, use the Workflow to define their scope and usage.

If your AI agent requires the use of in-depth knowledge to respond appropriately to your customers, it may be necessary to configure a knowledge base and link it to your AI agent.

Access your agents

Go to the Automation → My agents menu. There you will find the list of all your existing agents, with several key pieces of information:

• Agent name

• Description (optional)

• Created by: user who originally created it

• Creation and last modified date

• Workflows: number of workflows in which the agent is used

To create a new agent, click + Create an agent.

---

Create an agent

To create a new agent, click + Create an agent from the main agents page. Enter the name of your agent in the window provided for this purpose.

Agent configuration

The configuration of your AI agent is done through 2 tabs:

• Writing and Knowledge

• Custom responses

1. Tab Writing & Knowledge

This tab defines the writing behavior of your AI agent.

• Agent objective: this field is intended to specify to your AI agent the role it should fulfill (e.g.: You must generate a response to reply to my customers who contact me on ...).

• Writing instructions: they allow you to indicate to your agents the tone of voice of your brand and how they should address your customers. ​Examples:

  • The way to say "hello"

  • Phrases to use or not to use

  • The level of language to use (colloquial, polite, playful)

  • The way to address customers (informal "you", formal "you") define the tone, the phrasings to use or to avoid.

  • Signatures or polite closings to use

  • The use of emojis

  • etc.

• Customer context: allows you to provide your AI agents with information about the current context when they must generate a response for a customer interaction, such as the customer's first name, the relevant location, the communication channel, the customer status, etc.

• Additional guidelines: allow you to specify any other relevant instructions for you.

In these different configuration fields it is possible to use dynamic variables. These variables will be replaced by the data of each customer interaction at the time of generating a response. ​ ​See variables.

Beyond the tone of voice, it is also possible to link a knowledge base to your AI agent. This will allow your AI agent to use, when relevant, the information from a knowledge base.

---

2. Tab Custom responses

The Custom responses tab allows you to create response templates that the AI agent can rely on to generate messages that are more precise and consistent with your brand tone.

These templates serve two main purposes:

1. Provide an intelligent generation base: when the AI detects a customer interaction (review, message, complaint…) corresponding to one of your templates, it draws on it to formulate a response with the same meaning, while being able to adapt the wording or sentence structure.

2. Train the brand tone: custom responses also serve as a stylistic guide. They help the agent better understand how your brand expresses itself, the turns of phrase used, the level of formality or the use of emojis.

Custom responses are organized into Groups, each corresponding to a theme (for example: “Positive reviews”, “Complaint”, “Cleanliness issue”, etc.).

Each group contains several example responses with:

• a label (detection criterion, e.g.: “5-star rating — no text”)

• a sample response text, which you can freely structure with dynamic variables. // SEE VARIABLES

Create a custom response group

From the Custom responses tab, click + Create a group to open the configuration panel and indicate:

• Application criteria: context in which the AI should use these responses (e.g. positive reviews, delivery complaints).

• Examples of custom responses: add one or more sample responses according to the situations, specifying for each response its Label and its Text.

The text of custom responses can be built with dynamic variables. These variables will be replaced by the data of each customer interaction at the time of generating a response. ​ ​See variables.

Click Create group to validate.

Manage your custom responses

Once your custom response groups and your responses are created, you can manage them from the custom responses table in the Custom responses tab.

From this table, several actions are possible:

• Edit a custom response directly: The label and text of each response can be modified directly on the rows of the table.

• Open the full edit page: By clicking the Open button on the row of a custom response, you access the detailed editing page for that response.

• Rename a response group: Group names can also be modified directly from the table.

---

Use dynamic variables

Writing guidelines and custom responses can be built using dynamic variables. These variables are replaced with the data from the customer interaction concerned by the response generation.

General variables

Variable	Description
{{tags}}	List of feedback tags, displayed in brackets and separated by commas.
{{content}}	Text content of the customer feedback.
{{rating}}	Rating given by the customer in the feedback.
{{language}}	Target language of the feedback.
{{source}}	Source of the feedback (e.g.: Google, Email, Instagram, etc.).
{{class}}	Class or category of the feedback (Review, Contact, Survey, Message)
{{store}}	Name of the relevant location (e.g.: store, restaurant, agency…).
{{store_signature}}	Signature associated with the location.
{{store_contact}}	Contact email address of the location.
{{brand}}	Name of the brand associated with the response.
{{brand_signature}}	Brand signature.
{{brand_contact}}	Brand contact email address.
{{contact}}	Contact email used for the response: that of the location if available, otherwise that of the brand.
{{signature}}	Signature used for the response: that of the location if existing, otherwise that of the brand.
{{customer_first_name}}	Customer's first name (if available).
{{customer_last_name}}	Customer's last name.
{{customer_full_name}}	Customer's full name (first name + last name).
{{customer_civility}}	Customer civility (e.g.: Mr., Mrs., Dr., etc.).
{{customer_feedback_count}}	Total number of feedbacks left by the customer.
{{customer_purchase_count}}	Total number of orders placed by the customer.
{{customer_purchase_count_1}}	Customer's number of orders + 1 (useful for anticipatory phrasing).
{{customer_purchase_amount}}	Total cumulative amount of the customer's orders.
{{customer_average_rating}}	Average of the ratings given by the customer.
{{purchase_amount}}	Amount of the order concerned.
{{purchase_external_id}}	External identifier of the order.

Variables specific to satisfaction surveys

Variable	Description
{{survey_fields}}	List of all survey fields.
{{survey_csat_smileys}}	Results of questions of the type CSAT Smileys.
{{survey_nps}}	Results of questions of the type NPS.
{{survey_csat_stars}}	Results of questions of the type CSAT Stars.
{{survey_notations}}	Set of rating-type fields (CSATs & NPS).
{{survey_choices}}	Set of choice fields (dropdown, checkbox, radio).

Variables specific to contact forms

Variable	Description
{{site_choices}}	Set of choice-type fields (dropdown).
{{site_texts}}	Set of text-type fields (text & purchase).
{{site_fields}}	Complete set of fields (dropdown, text & purchase).

Custom variables

To further customize your AI agents, you can define custom variables whose value will be replaced depending on the brand or the location concerned.