Connect an AI Agent to Jira tickets

Introduction

In this blog post, I will show you how to connect your AI Agent to Jira. We will be using:

• a Jira account
• a Quickchat’s AI Agent (sign up here)

It will enable your Quickchat AI Agent to:

• be able to search through your Jira tickets, and
• answer questions based on them

We will use Quickchat’s AI Actions (custom HTTP actions) to let your Agent call the Get issue picker suggestions endpoint of the Jira (Atlassian) API.

How it works

Here is how it will work during conversation:

1. User asks your AI Agent a question like “what’s up with project mercury?”
2. AI Agent fetches relevant information from the Jira API using a query like “project mercury”
3. AI Agent replies to the user based on the information fetched from the API

Please follow the steps below. The whole setup shouldn’t take longer than 10 minutes!

Step 0 - create a Jira account and project

1. Go to id.atlassian.com/signup, create and verify your account.
2. Add Jira to your Atlassian apps (the free plan will be enough to start).
3. Set up your first project and create tickets like in the example below.

Step 1 - Jira API authentication token

Go to id.atlassian.com/manage-profile/security/api-tokens and create your API token which will look something like this:

ATATT3xFfGF01sKUl0HEW2-_-u9umfLSz7jeblmeLzEHZ1DLcdLbKeVF137iTHGkKhPuNMSKX8mkbwLpHXT4-qXEn-xNEnfiK8_XDVW6XXvGd_SBV3HD4kJInGNjfg2_yEoJFN6uwy4NRqeuhV2tjmyzxozLBRn35OhXkDA6QGfLFvf2_PKuNtA=8DA704E4

You are now ready to quickly test the search API endpoint by running this command:

curl -u your_email@example.com:ATATT3xFfGF01sKUl0HEW2-_-u9umfLSz7jeblmeLzEHZ1DLcdLbKeVF137iTHGkKhPuNMSKX8mkbwLpHXT4-qXEn-xNEnfiK8_XDVW6XXvGd_SBV3HD4kJInGNjfg2_yEoJFN6uwy4NRqeuhV2tjmyzxozLBRn35OhXkDA6QGfLFvf2_PKuNtA=8DA704E4 -G --data-urlencode 'query=mercury -H 'Accept: application/json' https://your-domain.atlassian.net/rest/api/3/search

Make sure to include the exact email address you used to set up your Atlassian account

Make sure to use your Atlassian domain (you’ll see it in the URL in your browser)

In order to be able to use your Atlassian API token in Quickchat AI Actions, you need to base64-encode it.

You can use a simple online tool like base64encode.org. Make sure to use the Live mode which guarantees the encoding happens entirely in your browser.

Alternatively, here is how to do it on your machine in a simple python script:

import base64

email = "your_email@example.com"
api_token = "ATATT3xFfGF01sKUl0HEW2-_-u9umfLSz7jeblmeLzEHZ1DLcdLbKeVF137iTHGkKhPuNMSKX8mkbwLpHXT4-qXEn-xNEnfiK8_XDVW6XXvGd_SBV3HD4kJInGNjfg2_yEoJFN6uwy4NRqeuhV2tjmyzxozLBRn35OhXkDA6QGfLFvf2_PKuNtA=8DA704E4"

credentials = f"{email}:{api_token}"
b64_credentials = base64.b64encode(credentials.encode("utf-8")).decode("utf-8")

print(f"Basic {b64_credentials}")

The above script will give you a ready-to-use header with the encoded token which looks something like this:

Basic eW91cl9lbWFpbEBleGFtcGxlLmNvbTpBVEFUVDN4RmZHRjAxc0tVbDBIRVcyLV8tdTl1bWZMU3o3amVibG1lTHpFSFoxRExjZExiS2VWRjEzN2lUSEdrS2hQdU5NU0tYOG1rYndMcEhYVDQtcVhFbi14TkVuZmlLOF9YRFZXNlhYdkdkX1NCVjNIRDRrSkluR05qZmcyX3lFb0pGTjZ1d3k0TlJxZXVoVjJ0am15enhvekxCUm4zNU9oWGtEQTZRR2ZMRnZmMl9QS3VOdEE9OERBNzA0RTQ=

Step 2 - create a Quickchat AI Action

In the Quickchat AI app, go to Actions & MCPs and add an action:

Name: Look up current issues

Description: Use this action when the user wants to check the status of one of the currently ongoing issues

Step 3 - set AI Action headers

1. Select GET as the Action Type
2. Action endpoint URL (make sure to use your Atlassian domain name)
3. Include Accept and Content-Type headers
4. Include the previously generated header including the encoded token as the Authorization header

Step 4 - set AI Action parameters

Include query as the only API request parameter:

1. Set its location to URL query (?=) to correctly include the parameter in the URL
2. Set description to: Generate a short search query based on user’s input to make sure that the issue ticket the user is searching for will be fetched.

Step 5 - test your API request

In the final step you can test your API request to make sure that it fetches your Jira tickets.

Step 6 - test the AI conversation

That’s it! You can now go back to the AI Preview and see your Jira tickets being looked up in real time during conversation:

BONUS

The above blog post was written by a human (yours truly) but could have just as well been written by AI. For example, by pasting a prompt like this one into ChatGPT (the o4-mini-high model):

I need an API endpoint that allows me to search through my Jira tickets.

Guide me through the process step by step so that it is accessible to a moderately technical person:
- Provide links to documentation describing the endpoint
- Any necessary account creation and initial setup
- If any paid account is needed, indicate that clearly
- If any authentication such as API tokens is needed, guide me through the process of creating them and show me exactly every step needed to be able to use them as an HTTP request header. For example, if base64 encoding is needed, show a script or another way of achieving that.
- Show to me exactly what header keys and values I need for the HTTP request (show me header keys and values in a table)
- Show to me exactly what payload parameters I need for the HTTP request (show me payload parameter name and example values in a table)

In the future, perhaps rather than search through Jira tickets you would like to:

• send messages to a Slack channel?
• fetch information from a Notion page?
• perform an action via Zapier?

Say that in the first sentence and run the prompt again! You will obtain perfectly good instructions to add the exact AI Action you need!