# Jira Integration — Practical Implementation Guide

### Introduction

This guide provides a narrative walkthrough for integrating Jira with the RAIA agent. The primary objective of this integration is to synchronize issues from your Jira projects directly into the AI Agent's knowledge base. This connection provides the agent with real-time project information, enabling it to support automated workflows and deliver more accurate, context-aware responses regarding your projects.

### The Integration Process Overview

The integration is built on a streamlined Extract, Transform, Load (ETL) framework. The process begins with the **extraction** of issues from your Jira instance using a custom JQL (Jira Query Language) query. This data, including issue details and comments, is then **transformed** into a structured JSON format. A key part of this stage is leveraging the Manus API to generate a derivative knowledge base, which enriches the raw issue data. Finally, the processed information is **loaded** into a PostgreSQL data lake hosted on Supabase. The RAIA agent accesses this data, and the entire workflow is automated to run monthly, ensuring the agent's project knowledge remains current.

### Roles and Responsibilities

Two key roles are essential for a successful integration. The **n8n Workflow Developer** is responsible for configuring and deploying the n8n workflow that powers the ETL process. The **RAIA Agent Engineer** provides support by assisting with the agent's configuration and ensuring the synchronized data is correctly ingested and utilized by the AI.For more technical details on the n8n-Jira connection, you can refer to the native n8n integration documentation at <https://n8n.io/integrations/jira/>.

#### Phase 1: Planning and Preparation

The initial phase, typically requiring 2-4 hours, is dedicated to planning the integration. The Workflow Developer will start by identifying your Jira instance URL and generating an API token for secure access. A critical step in this phase is to define the scope of the issues to be synced by creating a specific JQL query. The developer then maps the Jira issue fields, including comments, to the target schema of the data lake. This planning stage concludes with the creation of an integration architecture diagram, a list of required APIs and credentials, and a risk mitigation plan.

#### Phase 2: Data Extraction and Transformation

This phase, estimated to take 3-5 hours, focuses on the technical implementation of the data extraction and transformation. The Workflow Developer will configure a single, comprehensive `Jira Issues ETL` workflow. This workflow is responsible for fetching issues from Jira based on the JQL query defined in the planning phase. Within the workflow, data shaping logic is applied to convert the raw issue data into a structured JSON format, and the Manus API is used to generate a derivative knowledge base. The deliverable for this phase is the completed n8n workflow and a sample of the transformed JSON data for validation.

#### Phase 3: Loading, Automation, and Synchronization

The final phase, requiring approximately 3-5 hours, involves loading the data and activating the automated synchronization. The `Jira Issues ETL` workflow is configured to orchestrate the entire process. It uses an "upsert" operation to efficiently load the transformed data into the PostgreSQL database. Once the data is loaded, the Raia API is triggered to process the new information and add it to its vector store. The process concludes by scheduling the workflow to run automatically each month. The final deliverables include the completed workflow, confirmation of a successful data load, and the configured monthly execution schedule.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.raiaai.com/integrations/training-integrations/jira-integration-practical-implementation-guide.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.