Skip to main content
Intents are playbooks for Remark agents. They define which shopper situations should use a playbook, what the agent should do, and which actions the agent can use. Use intents for repeatable processes such as product guidance, returns, order status, warranty questions, shipping policy, or escalation to a human.

​
How intents work

Each intent has four main parts: Each intent also has two switches. Enabled turns the intent on for live conversations on the channels you choose. Enabled in playground turns it on for playground conversations. The switches are independent, so you can test an intent in the playground before turning it on for live conversations.

​
Create an intent

  1. Open Intents in the Remark dashboard.
  2. Select Add intent.
  3. Add an intent name that describes the shopper scenario.
  4. Under Matching criteria, explain when the intent should activate.
  5. Under Instructions, write how the agent should handle the situation. Type @ to reference an action.
  6. In the Actions section, select Add an action for each action the agent needs.
  7. Turn on Enabled in playground, then select Create.
  8. After the behavior looks correct in the playground, turn on Enabled and choose its channels.
Start new intents in playground mode. Test the playbook with realistic shopper messages before enabling it for live conversations.

​
Create intents with Ask Remark

If Ask Remark is available in your workspace, it can help create intents for you. Use it when you want to draft a new playbook from a goal, support scenario, or existing customer question. Ask Remark can turn a request such as “create an intent for returns and exchanges” into an intent with matching criteria, instructions, and suggested actions. It asks for your approval before it creates or edits an intent. Before you approve, check the action setup, policy language, channel targeting, and both switches. After Ask Remark creates or edits an intent, test it in the playground before enabling it for live conversations.

​
Write matching criteria

Matching criteria tell the agent when this intent applies. Describe the shopper’s situation, not just keywords. Good matching criteria are specific about:
  • What the shopper is asking for
  • What edge cases should still match
  • What similar requests should not match
For example:
If two intents have similar matching criteria, make the boundary clear. Overlapping criteria can cause the agent to choose the wrong playbook.

​
Write durable instructions

Instructions tell the agent what to do after the intent is selected. Treat them as process guidance, not a place to store facts that change often. Avoid hardcoding:
  • Current prices
  • Active discount codes
  • Stock levels
  • Temporary shipping cutoffs
  • Product lists that change frequently
Instead, tell the agent how to look up current information using knowledge, product, order, or integration actions.
Avoid absolute words like “always”, “never”, and “must” unless the rule is truly absolute. These words can make the agent too rigid in edge cases.

​
Give recourse

When instructions tell the agent not to do something, also tell it what to do instead. Less useful:
More useful:

​
Add actions

Actions are the tools the agent can use while following an intent. Examples include searching knowledge, looking up products, checking an order, creating a ticket, or using an integration-specific action. To add an action:
  1. Open the intent.
  2. In the Actions section, select Add an action.
  3. Choose the action the agent should be allowed to use.
  4. Configure any required fields.
  5. Reference the action in the instructions when you need the agent to use it at a specific step.
Available actions depend on your Remark setup and connected integrations. For example, Loop Returns actions are only available after Loop Returns is connected. As you edit an intent, the editor can suggest actions the playbook is likely to need. Suggestions appear as dashed rows in the Actions section. Select a suggestion to add the action, or dismiss it.

​
Reference actions in instructions

You can write instructions in plain language, or you can reference a specific action when the exact tool matters. Plain language is best for general guidance:
Use an action reference when the agent needs to run a specific configured action:
An action reference only works if that action is also added to the intent’s Actions section.

​
Configure action fields

Some actions need fields. A field can be filled by the conversation or set to a constant value. Use conversation-filled fields when the agent should collect or infer the value from the shopper conversation. Use constant values when the action should use the same value every time the intent runs. For actions that create cards in the conversation, you can choose whether the generated card should be shown.

​
Attach Encyclopedia articles

If your workspace uses the Encyclopedia, you can attach articles to an intent. When a playbook depends on specific reference content, such as the return policy for a returns intent, attach the article instead of copying its content into the instructions. The agent receives the full published article whenever the intent matches.
  • To attach an article to the whole intent, select Attach article under Attached articles.
  • To reference an article at the step that uses it, type / in the instructions and choose Link article.
The editor can also suggest articles under Attached articles. An article linked inside a channel-specific or medium-specific block applies only to the conversations that block covers.

​
Channel targeting

If your workspace has multiple conversation channels, choose the channels for an intent next to its Enabled switch. The intent runs only on those channels. Playground tests on a channel follow the same selection. When part of a playbook should differ by channel or medium, keep the shared process in the main instructions and add a block for the part that differs:
  1. In the instructions, type /.
  2. Choose Channel-specific instructions or Medium-specific instructions. Both are also on the editor toolbar.
  3. Select the channels, or the mediums (Chat, Email, SMS, Phone, Social), that the block applies to.
  4. Write the guidance for those conversations inside the block.
Content outside these blocks applies to every channel. Channel-specific instructions is available only when your workspace has more than one channel.

​
Test and publish

Use the playground to test intents before they go live.
  1. Enable the intent in playground.
  2. Run realistic shopper messages that should match the intent.
  3. Check whether the right intent was selected.
  4. Check whether the agent followed the instructions and used the right actions.
  5. Update matching criteria or instructions if the result is wrong.
  6. Enable the intent for live conversations when the behavior is ready.

​
Manage intents from the list

The Intents list shows each intent’s name, matching criteria, Production and Playground switches, channels, and actions. Use the switches to turn an intent on or off without opening it. Search intents by name, matching criteria, or instructions. To narrow the list, filter by Channel or by Status: Enabled on site, Enabled in playground, or Disabled. To update several intents at once, select them in the list. You can then change Enabled, Enabled in playground, or channels for all of them, or archive them.

​
Edit or archive an intent

Open an existing intent to update its name, matching criteria, instructions, actions, playground status, live status, or channel targeting. Archive an intent when it should no longer be used. Open the intent’s menu and select Archive intent, or select several intents in the list and select Archive. Archived intents are removed from the intent list and are not available to the agent.

​
Common intent set

Most ecommerce brands should consider intents for:
  • Product guidance
  • Order status and tracking
  • Order changes or cancellations
  • Returns and exchanges
  • Warranty or repairs
  • Shipping and delivery policy
  • General FAQ or account help
  • Escalation to a human
Add category-specific product guidance intents when different product categories need different questions, research steps, or recommendation logic.
Need help planning or testing intents? Contact support@remark.ai.