Automate Feature Request Collection & Analysis from Reviews to Jira with AI

This n8n workflow leverages the power of AI to streamline the process of collecting, analyzing, and transforming unstructured feedback (like product reviews) into structured feature requests in Jira. It acts as an intelligent bridge, ensuring valuable user insights are not lost and are efficiently converted into actionable development tasks.

What it does

This workflow automates the following steps:

1. Manual Trigger: Initiates the workflow upon a manual execution, allowing for on-demand processing of data.
2. Edit Fields (Set): This node is a placeholder for incoming data. In a real-world scenario, this would likely be replaced by a trigger that fetches reviews from a source (e.g., app store, survey platform, social media). The "Edit Fields" node would then be used to preprocess or structure this raw review data.
3. Code (Data Transformation): Executes custom JavaScript code to transform or filter the incoming data. This is where you would implement logic to extract relevant text, clean data, or prepare it for AI processing.
4. AI Agent: Utilizes an AI agent (likely a LangChain agent) to intelligently process the extracted review data. This agent is configured with an OpenAI Chat Model and an Auto-fixing Structured Output Parser to understand the intent of the reviews and extract structured information like feature requests, bug reports, sentiment, etc.
5. Jira Software: Creates or updates issues in Jira based on the structured output from the AI Agent. This step automates the creation of feature requests, bug tickets, or other issue types directly in your development backlog.

Prerequisites/Requirements

To use this workflow, you will need:

• n8n Instance: A running n8n instance.
• Jira Software Account: Credentials for your Jira instance to create issues.
• OpenAI API Key: An API key for OpenAI to power the AI Chat Model.
• LangChain Nodes: Ensure the @n8n/n8n-nodes-langchain package is installed in your n8n instance, as it provides the AI Agent, OpenAI Chat Model, and Output Parser nodes.

Setup/Usage

1. Import the workflow: Download the provided JSON and import it into your n8n instance.
2. Configure Credentials:
   • Jira Software: Set up your Jira credentials in n8n.
   • OpenAI Chat Model: Configure your OpenAI API key within the "OpenAI Chat Model" node.
3. Customize "Edit Fields" (Set) Node: Replace or modify this node to fetch your actual review data. This could be a webhook, an HTTP Request node, a Google Sheets node, or any other n8n trigger/node that provides review content.
4. Customize "Code" Node: Adjust the JavaScript code within this node to preprocess your specific review data as needed before sending it to the AI Agent.
5. Configure "AI Agent" and "Output Parsers":
   • AI Agent: Review and adjust the prompt and tools used by the AI Agent to accurately extract the desired information from your reviews (e.g., "Extract feature requests, their priority, and a brief description.").
   • Structured Output Parser: Define the expected JSON schema for the output you want the AI to produce (e.g., { "feature_name": "string", "description": "string", "priority": "string" }). The "Auto-fixing Output Parser" will help ensure the output conforms to this structure.
6. Configure "Jira Software" Node: Map the output fields from the AI Agent (e.g., feature_name, description, priority) to the corresponding fields in your Jira issue creation (e.g., Summary, Description, Priority).
7. Activate the workflow: Once configured, activate the workflow. You can test it by manually executing the "Manual Trigger" node after providing sample data in the "Edit Fields" node.