Home AI agent

AI agent

Speed up your support with AI
6 articles

Enable AI agent without blowing up your support inbox

The AI agent should be enabled gradually and with careful monitoring. What we recommend is to start with a 1-3 well-tested intents, and expand only once you’ve verified that everything works as expected. Avoid letting the AI handle everything in your inbox from the start. 1. Restrict responses to enabled intents only Use the "Restrict to enabled intents" setting to control which requests the AI agent can respond to: - When checked: The agent will only respond to requests that match the enabled intents - When unchecked: The agent may attempt to answer any incoming message, even if no instructions exist. This can lead to unexpected or incorrect replies. Check that you've this checkbox selected and max. 1-3 well-tested intents enabled when starting out, and only add more once you those work as expected. You can enable and disable intents from the Intent rules section: 2. Only enable intents that have been tested in the Playground Before enabling the AI agent and any intents, test it thoroughly in the Playground using real customer conversations. Use the Replay feature to see how the AI responds to specific tickets. This allows you to confirm that it behaves as expected before going live. The AI model cannot guess what you want it to say—it will only follow the instructions you provide. Start small with simple intents. Monitor performance for a few days before expanding to more complex use cases. 3. Use a clear AI agent name and signature We recommend configuring the agent’s name and signature to make it obvious that responses are coming from an AI, not a human. This helps set expectations for your customers and reduces confusion if the AI responds incorrectly. It also encourages customers to ask for human help when needed. 4. Disable business hours and auto-reply automations Before enabling the AI agent, make sure to turn off any business hours settings and “Send message” automations (such as auto-replies). These features can trigger unnecessary messages and confuse customers when used alongside the AI agent. Good to know - Complex multi-step instructions are not yet fully supported. Improvements are coming soon. - Shopify actions, such as changing customer addresses or cancelling an order, don't work reliably yet. Improvements coming in the same update!

Last updated on Jun 09, 2025

AI agent and Playground explained

The AI agent is your automated support assistant, designed to handle customer inquiries by pulling information from various knowledge sources and responding accordingly. The Playground is where you test and refine your AI’s performance in a controlled environment. AI Agent: What It Does - Responds to customer queries based on knowledge sources like AI training responses, canned responses, help articles and Shopify pages & products. - Uses intent rules to ensure specific instructions are followed when detecting key customer intents. - Can take actions like assigning agents, tagging conversations, and resolving tickets based on predefined rules. - Continuously improves by learning from AI training responses and updated knowledge sources. Learn more about training your AI agent Customizing Your AI Agent You can personalize your AI agent on the AI agent settings page by - Defining the Agent persona to set tone and communication style. - Naming your AI agent to match your brand voice. - Adding a profile picture for a more personalized touch. - Creating a signature that appears in every AI message. - Setting up a fallback message for when the AI doesn’t recognize an intent, ensuring seamless escalation to a human agent. Playground: A Safe Testing Environment The Playground allows you to test and debug your AI agent before deploying it in real customer interactions. You can: - Chat with your AI to see how it responds in different situations. - Replay past conversations to check how your AI would handle real customer messages. - Edit intent rules and training responses in real time to fine-tune performance. - Debug AI replies using the sources modal (</>), which shows what data the AI used to generate a response. Learn how to use the Playground Debugging and Optimization If the AI response isn’t ideal, you can: Open the Sources modal (</>) to see what knowledge the AI used. Adjust intent rules or AI training responses to guide future replies. Exclude outdated or misleading information from the Knowledge page. By understanding how the AI agent and Playground work together, you can ensure your AI delivers accurate, helpful, and consistent customer support.

Last updated on Jun 09, 2025

Training your AI agent

Your AI agent learns from different types of data to effectively answer customer queries. You can see all the data AI has access to by navigating to AI agent -> Knowledge sources (requires admin rights). The AI agent uses these sources to dynamically understand and respond to customer questions. AI training responses Responses you can save from good human-agent interactions. These provide the AI agent with examples of how to handle various customer questions, improving its ability to respond effectively. How to add an AI training response You can find an "Add AI training response" button by hovering over any message sent by a human agent. It opens a popup where you can edit the response (it is automatically polished by AI) and save it to your knowledge library. In Playground, you will see a "Revise answer" button when you hover over any message sent by the AI agent. You can give AI the expected correct response and save it to the training responses: Other knowledge types AI has access to: - Canned responses: your saved pre-written response templates your support team regularly uses. - Help articles: Information directly from your help center. - Shopify data: Information from your Shopify store’s pages and products. Intent rules Intent rules give your AI agent specific, pre-defined responses and actions when it recognizes certain customer requests or scenarios: - For example, if a customer asks about a refund, your AI agent can automatically provide your pre-written refund instructions. - You can also define specific actions like assigning conversations to particular agents, adding labels, or automatically resolving issues. - Regularly updating these intent rules helps your AI agent handle common requests efficiently, saving your team valuable time. How to edit intent rules: You can also add actions to intent rules, similarly to automations, and instruct AI when certain actions should be executed: Debugging AI responses Hover over any AI-generated response and click </> View prompt & knowledge used to see all the information and context the AI agent considered. Managing your AI training data You can manually enable or disable specific data sources. Disable outdated or irrelevant content to ensure your AI agent provides accurate responses. Best practices: - Regularly audit canned responses, help articles, and response examples. - Spend time on Playground testing how the agent responds to different queries - Clearly define intent rules for frequent customer inquiries. - Add AI training responses to give additional context and improve your AI agent's replies. Following these guidelines ensures your AI agent delivers accurate, helpful, and consistent customer support.

Last updated on Jun 09, 2025