Inkeep light logo
Schedule a callSee it for my content
Support toolsAuto reply

Auto-reply to support tickets with Inkeep AI

Overview

This guide provides instructions for how to setup an AI auto-reply with Zendesk. The template repo can be adapted to work with any support platform.

By default, the auto-responder implementation:

  • Provides an AI generated answer if it is very_confident
  • Leaves an internal note if it is not confident
  • Supports customizing behavior based on ticket tags and attributes

The webhook logic can be customized to your requirements. For example, you can:

  • Customize when to bypass the AI autoresponse based on ticket tags, user attributes, or other criteria
  • Add your own disclaimer language
  • Control the auto-reply flow and response behavior
  • Implement different handling for different types of tickets

Prerequisites

Ensure you have:

  1. A Zendesk account with admin access
  2. Get an Inkeep API key
  3. Access to deploy an API route (e.g., using Vercel Serverless Functions)

1. Deploy the webhook

The fastest way to get started is to deploy the serverless API route to Vercel:

Deploy with Vercel

Simply configure these environment variables:

VariableDescription
ZENDESK_SUBDOMAINYour Zendesk subdomain (e.g., if your Zendesk URL is mycompany.zendesk.com, enter 'mycompany')
ZENDESK_API_TOKENYour Zendesk API token (generate from Zendesk Admin settings)
ZENDESK_API_USEREmail address of the Zendesk user that generated the API token
AUTO_RESPONDER_INKEEP_API_KEYYour Inkeep API key
ZENDESK_WEBHOOK_SECRETA secret key for the Zendesk webhook

Optional:

VariableDescription
AI_AGENT_USER_IDThe User ID you'd like the AI bot to have if leaving internal comments
ENABLE_PUBLIC_RESPONSESSet to true to make AI responses visible to customers (defaults to internal responses only)

2. Configure your local environment variables

Copy the .env.sample file to .env and configure the missing variables with the values you used in the previous step. These variables are used by the scripts you will run in the next step.

3. Configure Zendesk

Now, let's configure Zendesk to send a webhook to your API route when new tickets are created.

  1. Navigate to the webhook_setup folder in your local terminal (cd webhook_setup).
  2. Enable execution of the setup script by running chmod +x setup.sh.
  3. Execute it with ./setup.sh. This will create the webhook and trigger for you.

The script will write the created webhook and trigger IDs to a file named .webhook_resources. You can use these IDs later to clean up the resources by running the cleanup script: chmod +x cleanup.sh and ./cleanup.sh.

  1. In Zendesk Admin Center, go to Apps and Integrations > Webhooks
  2. Create a new webhook with the following settings:
    • Name: Inkeep Smart Replies
    • Endpoint URL: Your deployed Vercel URL + /api/webhook (e.g., https://your-app.vercel.app/api/webhook)
    • Request method: POST
    • Request format: JSON
    • Basic authentication: No
    • Active: Yes
  3. Create a trigger to invoke the webhook:
    • Go to Admin Center > Objects and rules > Business rules > Triggers
    • Click Add trigger
    • Name it Inkeep Smart Reply Trigger
    • Set conditions:
    • Ticket: Is Created
    • Set actions:
    • Notify webhook: Select the webhook you created

4. Test the Setup

To verify everything is working correctly:

  1. Create a ticket:

    • Go to your Zendesk workspace
    • Create and submit a ticket with a test message

  2. Verify answer:

  • Check that an AI-generated response was added as a reply or internal note
  • The note should be from the user specified in your AI_AGENT_USER_ID

Debug Mode

By default, the AI Autoresponder runs in debug mode (internal notes only). In this mode, responses will only be visible to your support team as internal notes and not to the end-users.

To enable customer-facing responses:

  1. Set the environment variable: ENABLE_PUBLIC_RESPONSES=true
  2. Redeploy the application

When ENABLE_PUBLIC_RESPONSES is not set or is set to any value other than "true", the AI Auto Responder will only create internal notes (not visible to end-users) when responding to tickets.

Review the Zendesk webhook activity:

  • In Zendesk Admin Center, go to Apps and Integrations > Webhooks
  • Click on your Inkeep Smart Replies webhook
  • Check the Activity tab to confirm the webhook fired for your test ticket
  • Verify the webhook shows a successful (200) response

Check the Vercel logs:

  • Go to your Vercel dashboard
  • Select your deployed application
  • Navigate to Deployments > Latest Deployment > View Functions Logs
  • Look for logs showing the webhook request was received and processed

Check that your Zendesk Workspace is configured to send emails on public replies to tickets:

  • Look at the Zendesk email tigger guide here.

If your auto-responder is timing out:

  • The default maxDuration on Vercel free plan is 60 seconds. This is the maximum time the AI can take to generate a response. You can increase this by setting the maxDuration parameter on the route.ts file and upgrading to a paid Vercel plan.

Double-check the environment variables are configured correctly

Webhook/Trigger Issues:

If you experience problems with the webhook or trigger:

  1. Manually deactivate them in Zendesk:
    • Visit https://YOUR-SUBDOMAIN.zendesk.com/admin/objects-rules/rules/triggers
    • Replace YOUR-SUBDOMAIN with your Zendesk subdomain
  2. Or run the cleanup script to remove the trigger/webhook pair: 
    chmod +x ./cleanup.sh
./cleanup.sh

You can customize the auto-reply behavior based on Zendesk ticket tags. The webhook receives the full ticket data, including tags, which you can use to control the flow:

  1. First, ensure your Zendesk trigger adds the appropriate tags before the webhook is called
  2. In the webhook code, you can access ticket tags from the API response:
const ticket = await client.tickets.show(ticketId);
const tags = ticket.tags;
  1. Implement your custom logic based on tags:
if (tags.includes('no-auto-reply')) {
  return; // Skip auto-reply
}
 
if (tags.includes('priority-support')) {
  // Custom handling for priority tickets
}

Common use cases include:

  • Bypassing auto-reply for specific ticket types
  • Different response templates based on ticket category
  • Varying confidence thresholds for different types of inquiries
Provide dynamic information to the copilot using a prehookAuto-reply to live chat with Inkeep AI

On this page