By sending out customer satisfaction (CSAT) surveys, you enable your customers to rate their experience with your service. In this article, we’ll show you how to set up a CSAT survey.

Adding a CSAT survey

Follow the steps below to add a customer satisfaction survey to your Trengo account.

1. Navigate to Settings > Automation > Customer Satisfaction;

2. Click ‘Add new survey’, give your survey an internal name, and further set it up.

Survey text

First, you’ll configure what the actual message looks like that customers receive, wherein you ask them to review their experience with your company.

Follow the steps below to set up your survey text.

1. Your company / Brand name: Add the name of your company, which will be displayed on top of your survey, and in the signature.

2. Survey title: Give your survey a title.

3. Question: Add the question that you’d like to ask your customer, which will be displayed in bold text above the emojis.

4. Button text: The text in the button your customers click to be redirected to the actual survey.

Follow up question

When your customer clicked the button in your first message, they’ll be redirected to the follow-up, where they can leave their actual review.

Add the follow-up question and move on to the next step.

Thank you message

After giving their review, customers are redirected to your ‘thank you’ message, to which you can also add a button with an URL attached to it.

Set up your ‘thank you’ message as stated below.

1. Thank you message: Add the text your customer will see after filling out their survey.

2. Enable button below text field: Enable this feature to add a button to the page.

3. Button text: Add the text displayed on the button.

4. Button URL: Add the URL your customers will be redirected to when clicking the button.

When you’ve set up all of the above, it’s time to set up a rule, that will trigger the CSAT to be sent out when the customer conversation has met your conditions. Please continue to the next page to learn how to set up this rule.

Adding a flowbot to Trengo

Let’s automate your customer communication flow, by adding a flowbot to your Trengo inbox. In case you’re not familiar with the use of flowbots, feel free to read more about the anatomy of a flowbot in Trengo.

Add a flowbot

If you like to add a flowbot to Trengo, feel free to follow the steps below.

1. Navigate to Settings > Automation > Flowbots and click the ‘plus’ icon or ‘Add flowbot’;

2. Design your flowbot;

1. Steps overview: Here you’ll find an overview of all the steps you added.

2. Add step: Click this button to add a step to your flowbot.

3. Step #: The name of the selected step.

4. Copy step: With this button, you can duplicate the step.

5. Delete step: Delete your selected step.

1. Add content: Here you can add content to your step.

2. Buttons to steps: Add buttons to the selected step.

3. Actions: Click here to add actions to your flowbot step.

4. Step overview: Here you’ll find an overview of the buttons or actions you’ve added to the step.

When you’re done designing your flowbot, including content, buttons, and actions, it’s time to configure your flowbot.

Adding a greeting to your widget

After adding a web widget to your Trengo inbox, adding channels to it, and adding the web widget to your website, you’re able to set up a ‘greeting’ for it. In this article, we’ll show you how to do this.

Add a greeting to your widget

Follow the steps below to set up a greeting for your web widget.

1. Navigate to Settings > Automation > Widget automation;

2. Select ‘Add automation’ and click ‘Greet the website visitor’;

3. Set up your greeting;

1. From: Choose who will greet your customers. You can choose ‘Team’, ‘User’, ‘Random user from team’, or set up a custom greeting.

2. Select team/user: Select your team or user, or set up your custom greeting.

3. Compose greeting: Add the text your customer will see when the greeting shows.

After setting up your greeting, continue by clicking ‘Ready? Choose audience’.

Choose the target audience for your web widget greeting. You can choose to show the greeting to all customers, or choose a specific audience using different conditions.

After choosing your target audience, click ‘Ready? Set page targeting’ to continue setting up your page targeting.

1. Delivery method: Choose if you’d like the greeting to show up immediately, or after a specific amount of time.

2. Page selection: Select which pages you’d like to show the widget greeting on.

After choosing your page targeting, click ‘Ready? Go to next step’ to publish your widget automation.

1. Start date: Choose when you’d like the greeting to start showing on your website.

2. End date: Select if there is an end date to your widget greeting.

3. Select widget: Choose the web widget on which the greeting will be active.

4. Active: Toggle this button to activate your widget greeting.

Click ‘Save’ to publish your greeting.

Adding a help centre to search results

After creating your own help centre via Trengo and adding content to it, you’re able to have your articles show up in Google and Bing search results. In this article, we’ll show you how to do this.

Enable search results

Follow the instructions below to have your articles show up as Google and Bing search results.

1. Navigate to Help Centre and select your help centre;

2. Select ‘Settings’ and scroll down to ‘Advanced settings’;

3. Set ‘Disable search indexing’ to ‘No’;

Don’t forget to click ‘Save changes’.

Adding a help centre to your Trengo account

With Trengo, you’re able to host your own help centre to help your customers find answers to their questions quickly, and with that take pressure off your customer support team so that they can focus more on incoming queries. In this article, we’ll show you how to add a help centre to your Trengo account.

Add a help centre to your Trengo account

Follow the instructions below to add a help centre.

1. Navigate to Help Centre and click the ‘plus’ icon or ‘Add Help Centre’;

2. Create your help centre;

1. Company name: Add your company’s name.

2. Languages: Choose the language(s) you’d like your help centre in. Do note that articles will not be translated automatically.

3. Default language: In case you added multiple languages, choose the default language of your help centre.

Click ‘Create help centre’ to add the help centre to your account.

Adding a help centre to your web widget

By adding your help centre to your web widget, you're allowing your site visitors to quickly find the answers they are looking for, before reaching out to you. In this article, we’ll show you how to do this.

Add a help centre to your web widget

You can add your Trengo help centre to your web widget by following the steps below.

1. Navigate to Settings > Settings > Web widgets and select your web widget;

2. Click ‘Help centre’ from the list of possible channels you can add;

3. Set up your help centre;

1. Enabled: Enable your help centre for the web widget here.

2. Channel: Select the help centre you want to connect to your web widget.

ℹ️ In case you’re hosting your help centre on a custom domain, make sure to send us an email to get your SSL certificate. Help centres without one won't appear in your widget.

Don’t forget to update your widget, by clicking ‘Update widget’.

Instruct your AI Agent

Table of contents

Instruct your AI Agent

This article explains how to write effective instructions for your AI Agent using the Behaviour and Scenarios tabs.

Clear instructions ensure your AI Agent responds correctly, takes the right actions, and escalates when needed.

The three layers of instruction

Your AI Agent works with three layers of instructions. Each layer has a specific role:

Layer 1 — Behaviour settings

Defines who your AI Agent is. This applies to every conversation.

Job description
Tone of voice
Company context

Layer 2 — Handover criteria & Additional instructions

These are your default rules. They apply when no Scenario is active.

Think of this as your fallback layer.

Layer 3 — Scenarios

These are process-specific instructions for handling particular situations.

Important: Scenarios always take priority over all other instructions.

If no Scenario applies, Layer 2 is used instead.

Behaviour: define how your AI Agent operates

The Behaviour tab controls how your AI Agent communicates, makes decisions, and handles conversations by default.

Job description

Define the role and responsibilities of your AI Agent.

Best practices

Be specific about what the AI Agent should handle
Clearly describe key tasks

Example

"Assist customers with order questions, returns, and product information."

Company context

Provide background information about your business.

Include:

What your company does
Who your customers are
Your products or services

This helps the AI Agent give more relevant responses.

Tone of voice

Define how your AI Agent communicates.

Best practices

Be explicit (e.g. friendly, professional, concise)
Include what to avoid

Example

"Friendly and helpful, but professional. Keep answers concise. Avoid slang or overly casual language."

Handover criteria

Handover criteria define when the AI Agent should escalate a conversation to a human.

By default, the AI Agent escalates when:

It cannot answer a question
The customer asks for a human

You can add additional rules that apply across all conversations.

Examples

E-commerce: Escalate on payment disputes or chargebacks
Hospitality (THL): Escalate on safety issues or emergencies

Important: If a Scenario defines escalation rules, the Scenario takes priority.

Collect customer details before handover

Define what information the AI Agent should collect before handing over.

The AI Agent will only ask for missing information. It won’t ask customers to repeat themselves.

Examples

E-commerce: order number, email, issue description
Hospitality: booking reference, guest name, request details

This ensures your team has full context immediately.

Additional instructions

Additional instructions are always-on rules that apply to every conversation.

Use them for general rules, not step-by-step processes.

Examples

Always address the customer by their first name
Never promise a refund without confirming the order number
Do not discuss competitor pricing
Always ask if there’s anything else you can help with

Important: When a Scenario is active, it overrides Additional instructions.

Scenarios: handle specific situations step by step

Scenarios define how your AI Agent handles a specific process from start to finish.

Use a Scenario when:

There are clear steps to follow
Specific information needs to be collected
Actions need to be taken (e.g. assign, label, API call)
There is a defined escalation path

Tip:
Each Scenario should cover one complete process. Avoid combining multiple use cases.

Common Scenario examples

E-commerce

Return or refund request
Damaged or wrong item
Order status enquiry
Discount code issues
Payment disputes

Hospitality (THL)

Booking modifications
Cancellations
Guest complaints
Late check-in / checkout
Amenity bookings

How to write a good Scenario

A strong Scenario includes:

Trigger — when should the Scenario activate?
Steps — what should happen, and in what order?
Required information — what should be collected?
Actions — what should the AI Agent do?

What the AI Agent can do in a Scenario

Within a Scenario, your AI Agent can take actions in Trengo:

Assign to a team

"Assign the conversation to @Returns Team."

Assign to a user

"Assign to @Sarah."

Apply labels

"Apply the label @damaged-item."
"Apply the labels @refund-requested and @high-priority."

Add internal comments

"Add an internal comment with the order number, issue, and confirmation of photo received."

Use integrations or custom actions

"Use the Shopify Storefront to look up the product and include the price."
"Use the order status action to retrieve the order details."

The AI Agent will only use integrations if instructed or if clearly defined in the action setup.

Using @mentions in Scenarios

Use the @ button to insert:

Team members (e.g. @Sarah)
Teams (e.g. @Returns Team)
Labels (e.g. @damaged-item)

This avoids errors and ensures consistency.

Worked example — damaged item (e-commerce)

When a customer reports a damaged item:

Apologize and acknowledge the issue
Ask for a photo and order number
Confirm the damage after reviewing the image
Add an internal comment with details
Apply the label @damaged-item
Assign to @Fulfillment Team

Worked example — cancellation request (hospitality)

When a guest requests a cancellation:

Ask for booking reference and reason
Explain the cancellation policy
Add an internal comment with details
Apply the label @cancellation-request
If within 48 hours of check-in, assign to @Sarah

Limits to keep in mind

Maximum 10 Scenarios per AI Agent
Maximum 5,000 characters per Scenario
Scenarios do not connect or chain together
The AI Agent only sees the current conversation
It does not know which Journey it belongs to

When to use what

Use the right instruction type for the right situation:

Additional instructions: rules that apply to every conversation
Handover criteria: situations that should always escalate
Scenarios: structured processes with steps and actions

Summary

To instruct your AI Agent effectively:

Use the Behaviour tab to define role, tone, and global rules
Use Scenarios for structured workflows and actions
Use Handover criteria and Additional instructions as fallback rules

Key takeaway: Scenarios always take priority. The clearer your instructions, the better your AI Agent will perform.

‍

Adding a CSAT survey

Survey text

Follow up question

Thank you message

Add a flowbot

Add a greeting to your widget

Enable search results

Add a help centre to your Trengo account

Add a help centre to your web widget

Instruct your AI Agent

Instruct your AI Agent

The three layers of instruction

Layer 1 — Behaviour settings

Layer 2 — Handover criteria & Additional instructions

Layer 3 — Scenarios

Behaviour: define how your AI Agent operates

Job description

Company context

Tone of voice

Handover criteria

Collect customer details before handover

Additional instructions

Scenarios: handle specific situations step by step

Common Scenario examples

How to write a good Scenario

What the AI Agent can do in a Scenario

Assign to a team

Assign to a user

Apply labels

Add internal comments

Use integrations or custom actions

Using @mentions in Scenarios

Worked example — damaged item (e-commerce)

Worked example — cancellation request (hospitality)

Limits to keep in mind

When to use what

Summary

Still having trouble?