Custom Instructions

Overview

Custom Instructions let you customize your AI Agent’s behavior by adding rules that guide how it speaks to end users. Custom Instructions provide flexibility to shape your AI Agent’s responses while working within defined constraints.

Limitations

Custom Instructions have the following constraints.

• You can have up to 10 active Custom Instructions in your AI Agent. In addition to these active Custom Instructions, you can also have inactive drafts that you’re working on.

  You may see as many as 40 active Custom Instructions if your AI Agent was created before January 7, 2025. This state will be expected if your AI Agent previously relied upon the older version of Custom Instructions, Guidance. Please note that AI Agents in this state will continue to work as expected, however you can improve performance by re-creating your contextual Custom Instructions as Coaching.

• Each Custom Instruction can be up to 300 characters long.

• Your Custom Instructions must be in English.

Additionally, keep the following in mind to ensure that your Custom Instructions perform well:

• Make sure your Custom Instructions don’t conflict with each other. For example, you could have two Custom Instructions to tell end users about both a spring and summer sale. If both of them are live at the same time, you can’t guarantee that the correct Custom Instruction will apply when an end user is talking with your AI Agent.

• The AI Agent notifies you if a newly added Custom Instruction conflicts with any existing Custom Instruction.

Use cases

Custom Instructions help you shape your AI Agent’s behavior and communication style.

• Response style guidelines: Define how your AI Agent should communicate, such as maintaining a formal tone or avoiding certain phrases.
• Promotional messaging: Instruct your AI Agent to mention current sales, promotions, or announcements during conversations.
• User-specific rules: Apply different instructions based on end user attributes, such as providing premium support messaging only to VIP customers.

Capabilities & configuration

Custom Instructions support the following options.

• Availability rules: Apply Custom Instructions to all end users or restrict them to specific users based on variable conditions.
• Draft mode: Save Custom Instructions as drafts to refine them before publishing.
• Testing: Test Custom Instructions in a chat window before making them active.
• Conflict detection: The AI Agent notifies you if a new Custom Instruction conflicts with an existing one.
• Active/inactive toggle: Publish or unpublish Custom Instructions at any time.

Quick start

Get a Custom Instruction up and running in minutes.

To add a Custom Instruction:

Your AI Agent immediately starts applying the Custom Instruction when generating responses. For more options, including restricting Custom Instructions to specific users, see Create a Custom Instruction.

Implementation & usage

Create, manage, and review Custom Instructions to control how your AI Agent communicates with end users.

Create a Custom Instruction

As soon as you publish a Custom Instruction, your AI Agent can start considering it when generating responses to end users.

If required, you can restrict Custom Instructions to certain users, based on information your AI Agent collects about your users and saves in variables.

To add a Custom Instruction:

1. On the Ada dashboard, go to Config > AI AGENT > Settings, then on the Custom instructions tab, click New custom instruction.

   The Add Custom Instruction page opens.

2. Under Title, add a title for your new Custom Instruction.

3. Under Instruction, add the new rule you want your AI Agent to follow.

4. Under Set availability, choose which end users you want the Custom Instruction to apply to.

   • To make the Custom Instruction available to all users, select Everyone.

   • To restrict the Custom Instruction to certain users, select Based on the following rules. A section expands where you can enter the logic your AI Agent uses to decide whether to apply the Custom Instruction.

     1. Under Where, in the Choose a variable list, select a variable.
     2. In the next dropdown, select an operator so you can define a relationship between the variable and the value you want to target.

     Understand comparison operators

     Comparison operators are logic statements that tell your AI Agent to match end user information that’s captured in the variable you’re using. The available operators vary based on the variable type you’re using:

     Operator	Variable types	Description
     Begins With	- All text variables (including phone and email)	Match information in the variable that begins with certain text (partial match).
     Ends With	- All text variables (including phone and email)	Match information in the variable that ends with certain text (partial match).
     Contains	- All text variables (including phone and email) - List variables	Match information in the variable that contains certain text in any position (partial match).
     Is	- All text variables (including phone and email) - Number variables	Match information in the variable that equals specific text exactly (exact match).
     Is Not	- All text variables (including phone and email) - Number variables	Match information in the variable that does not equal specific text exactly (exact match).
     Is Not Set	- All text variables (including phone and email) - Number variables - List variables	Match if there is no information contained in the variable.
     Is Set	- All text variables (including phone and email) - Number variables - List variables	Match if there is any information contained in the variable.
     Greater Than	- Number variables	Match if the information in the variable is greater than a specific value.
     Less Than	- Number variables - List variables	Match if the information in the variable is less than a specific value.
     Is True	- Yes/No variables	Match if the information in a variable is Yes (or True).
     Is False	- Yes/No variables	Match if the information in a variable is No (or False).
     Does Not Contain	- List variables	Match if none of the selected items contains this value.
     Is Equal To	- List variables	Match if the end user selected a particular number of options in a List Option block.
     Is Greater Than	- List variables	Match if the end user selected more than a particular number of options in a List Option block.
     Is Less Than	- List variables	Match if the end user selected fewer than a particular number of options in a List Option block.

     3. In the Value field, enter or select a value for the variable that you want to use to target users.
     4. If required, add additional conditions.

     • To add a new top-level condition, click Add .

       If you’re adding your first additional top-level condition, in the dropdown that appears, choose And or Or as the operator for all of your top-level conditions.

     • To create or add to a group of conditions, click the Add to group icon beside a condition you want to include in the group.

       If you’re creating a group, in the dropdown that appears, choose And or Or as the operator for all of the conditions in that group.

5. To save your new Custom Instruction as a draft, click Save. If you save it as a draft, it won’t affect your AI Agent content until you publish it.

6. To test your new Custom Instruction, click Test.

   A chat window opens, where you can type prompts and test whether the Custom Instruction returns the kinds of responses you want, even if it’s still a draft.

   If you haven’t saved your Custom Instruction yet, testing it saves it as a draft.

   If your new Custom Instruction conflicts with any existing Custom Instruction, your AI Agent notifies you when you click Test. Conflicts are checked against both active and inactive Custom Instructions.

7. To publish your Custom Instruction, at the top of the page, enable the toggle (changing it from Inactive to Active).

   Your AI Agent starts using your new Custom Instruction in the responses it writes to end users.

View in Conversations

You can review which Custom Instructions were considered during past Conversations. On the Ada dashboard, when you go to Conversations, you can see transcripts of Conversations that end users have had with your AI Agent. In the Details pane, under Custom instruction considered, you can see a list of Custom Instructions that were active at the time of any given Conversation, and use that information to fine-tune your Custom Instructions. For more information, see Improve your AI Agent’s responses by viewing past Conversations.

Edit or delete Custom Instructions

You can modify or remove a Custom Instruction at any time.

To edit or delete a Custom Instruction:

1. On the Ada dashboard, go to Config > AI AGENT > Settings, then open the Custom instructions tab.

2. Click the Custom Instruction you want to manage.

   The Edit Custom Instructions page opens.

3. Make your required changes to the Custom Instructions

   • You can edit the existing Custom Instruction and then click Save to update it and keep it active.

   • You can click Convert to draft to stop an active piece of Custom Instruction from affecting end user Conversations, without deleting the Custom Instruction from your AI Agent.

   • You can make changes to the piece of Custom Instruction and then click Test to try it out in a conversation. Testing a Custom Instruction automatically saves it, but doesn’t change whether it’s a draft or active.

   • You can click the Delete button to permanently delete the Custom Instruction from your AI Agent.

Manage Custom Instruction availability

You can select multiple Custom Instructions and quickly change whether they’re available to all of your users, to only some of them, or delete your selected Custom Instructions altogether.

To change availability for multiple Custom Instructions:

1. On the Ada dashboard, go to Config > AI AGENT > Settings, then open the Custom instructions tab.

2. Select the Custom Instructions you want to manage. Some options appear at the bottom of your screen:

   • To make the selected Custom Instructions available to only some of your users, click Set availability.

     The Set Availability window opens.

     • To make the Custom Instruction available to all users, select Everyone.

     • To restrict the Custom Instruction to certain users, select Based on the following rules. A section expands where you can enter the logic your AI Agent uses to decide whether to apply the Custom Instruction.

       1. Under Where, in the Choose a variable list, select a variable.
       2. In the next dropdown, select an operator so you can define a relationship between the variable and the value you want to target.

       Understand comparison operators

       Comparison operators are logic statements that tell your AI Agent to match end user information that’s captured in the variable you’re using. The available operators vary based on the variable type you’re using:

       Operator	Variable types	Description
       Begins With	- All text variables (including phone and email)	Match information in the variable that begins with certain text (partial match).
       Ends With	- All text variables (including phone and email)	Match information in the variable that ends with certain text (partial match).
       Contains	- All text variables (including phone and email) - List variables	Match information in the variable that contains certain text in any position (partial match).
       Is	- All text variables (including phone and email) - Number variables	Match information in the variable that equals specific text exactly (exact match).
       Is Not	- All text variables (including phone and email) - Number variables	Match information in the variable that does not equal specific text exactly (exact match).
       Is Not Set	- All text variables (including phone and email) - Number variables - List variables	Match if there is no information contained in the variable.
       Is Set	- All text variables (including phone and email) - Number variables - List variables	Match if there is any information contained in the variable.
       Greater Than	- Number variables	Match if the information in the variable is greater than a specific value.
       Less Than	- Number variables - List variables	Match if the information in the variable is less than a specific value.
       Is True	- Yes/No variables	Match if the information in a variable is Yes (or True).
       Is False	- Yes/No variables	Match if the information in a variable is No (or False).
       Does Not Contain	- List variables	Match if none of the selected items contains this value.
       Is Equal To	- List variables	Match if the end user selected a particular number of options in a List Option block.
       Is Greater Than	- List variables	Match if the end user selected more than a particular number of options in a List Option block.
       Is Less Than	- List variables	Match if the end user selected fewer than a particular number of options in a List Option block.

       3. In the Value field, enter or select a value for the variable that you want to use to target users.
       4. If required, add additional conditions.

       • To add a new top-level condition, click Add .

         If you’re adding your first additional top-level condition, in the dropdown that appears, choose And or Or as the operator for all of your top-level conditions.

       • To create or add to a group of conditions, click the Add to group icon beside a condition you want to include in the group.

         If you’re creating a group, in the dropdown that appears, choose And or Or as the operator for all of the conditions in that group.

     • To make the selected Custom Instructions available to none of your users, click Set as inactive.

     • To make the selected Custom Instructions available to all of the users configured in its availability settings, click Set as active.

     • To delete the selected Custom Instructions, click Delete.

Related features

Extend your AI Agent’s behavior with complementary capabilities.

• Coaching: Provide contextual guidance to help your AI Agent handle specific topics or scenarios more effectively.