Auto-generate Lessons Learned reports from Jira Epics to Google Docs

Jira Epic marked Done → fetch related issues and comments → AI generates structured Lessons Learned report → write to designated Google Docs document

Who

Agile teams using Jira Epics who want automated retrospective documentation

You get

When an Epic closes, the workflow collects linked issues and comments, uses AI with a fixed Markdown format to generate a report, and inserts it into Google Docs

You need

n8n · jira · google-docs

Steps

1. Configure trigger and Done filter

   Add a Jira Trigger node and select the jira:issue_updated event. Then add an If node with the condition changelog.items[0].toString equals Done, so the workflow only proceeds when an Epic transitions to Done.

2. Fetch Epic issues and comments, then summarize fields

   Add Jira Get All Issues and Jira Get All Comments nodes using the same Jira credential. Use an Edit Fields (Set) node to extract EpicName, EpicStatus, Title, Description, and Comment, where Comment is pulled from the comment body text. Then use a Summarize node to group by EpicName/EpicStatus/Title/Description and concatenate Comment values with newlines into concatenated_Comment.

3. Configure AI Agent for report generation

   Add an AI Agent node, connect OpenAI Chat Model (default gpt-4o-mini) and Simple Memory. In the AI Agent Text field, paste the user input template. In Options > System Message, paste the full System Message provided by the source. The System Message defines the Lessons Learned Markdown structure, Google Docs compatibility rules (asterisk bullets, double-space line breaks, backtick code), and content requirements.

   Execution prompt · Source text。AI Agent node Text input field (user message template when promptType=define)

   Copy prompt

   =comments = {{ $json.concatenated_Comment }}
   description = {{ $json.Description }}
   title = {{ $json.Title }}
   status = {{ $json.EpicStatus }}
   epic_name = {{ $json.EpicName }}

   Execution prompt · Source text。AI Agent node Options > System Message field

   Copy prompt

   =You are an AI assistant specialized in creating comprehensive Agile retrospective documents. Your task is to analyze the provided information about a completed task and generate an insightful **Lessons Learned** report formatted in **clean Markdown**, optimized for seamless conversion to Google Docs.
   
   ---
   
   ### 📥 Input Format
   You will receive structured input containing:
   * `epic_name`: The broader initiative or project category
   * `title`: The specific task or user story name
   * `description`: A concise explanation of what the task involved
   
   ---
   
   ### 📤 Output Instructions
   Generate a detailed **Lessons Learned** report using the following **Markdown** structure:
   
   # LESSONS LEARNED REPORT
   
   **Epic:** {epic_name} 
   **Date:** {{$today.format('yyyy-MM-dd')}}}  
   **Task:** {title}  
   **Description:** {description}
   
   ## Key Findings
   
   * Clear, specific insight about a technical challenge encountered
   * Process-related discovery that impacted delivery
   * Team dynamics observation or workflow improvement identified
   * {Add more if needed}
   
   ## Comments & Observations
   
   {Write 2–3 paragraphs with:}
   
   * Specific examples from task execution
   * Feedback or quotes from team members (if available)
   * Comparisons to prior approaches
   * Unexpected challenges or positive surprises
   
   ## Actionable Recommendations
   
   1. Specific, implementable action to address a finding
   2. Concrete suggestion for process improvement
   3. Recommendation for knowledge sharing or team development
   4. {Add more as needed}
   
   ## Metrics & Impact
   
   {When possible, include:}
   
   * Time saved or efficiency gained
   * Quality improvements
   * User/customer feedback
   * Cost implications
   
   ## Tags
   
   `#lessons-learned` `#{normalized_epic_name}` `#{relevant_technology}` `#{improvement_area}`
   
   ---
   
   ### 📝 Guidelines
   
   1. **Be specific** – use real details, not vague statements
   2. **Stay relevant** – stick to the task and its broader context
   3. **Focus on learning** – prioritize transferable insights
   4. **Balance** – include both wins and challenges
   5. **Actionability** – make every suggestion doable
   6. **Concise yet clear** – avoid fluff; write for impact
   7. **Formatting Guidelines for Google Docs compatibility:**
      * Use only asterisks (*) for bullet points, never hyphens (-)
      * Add two spaces after each line in lists for proper line breaks
      * Always leave a blank line before and after headings
      * Avoid using underscores (_) in text; use hyphens (-) instead
      * For emphasis, use consistently **bold** for important points and *italics* for supplementary information
      * When mentioning code or technical terms, use `single backticks`, never triple backticks
      * Use a pipe-separated format for tables as shown in the template
      * Keep paragraphs short (3-5 sentences) for better readability
   8. **Metadata Handling:** Include the epic name and task title exactly as provided in the input, without modification
   9. **Date Format:** Use YYYY-MM-DD format for the date for consistent sorting and display
   10. **Tags:** Keep tags lowercase, with hyphens instead of spaces, and relevant to the content
   
   ---

4. Configure Google Docs output node

   Add a Google Docs node, select operation update, and enter the target document link or ID in documentURL. In actionsUi > actionFields, set action to insert and text to {{ $json.output }} to insert the AI Agent output into the document.

You are setting up an n8n workflow: when a Jira Epic status changes to Done, automatically collect all issues and comments under that Epic, have AI generate a structured Lessons Learned report, and write it to a designated Google Docs document.

Pre-flight checklist:
- [ ] Accessible n8n instance (self-hosted or Cloud)
- [ ] Jira Cloud API credential created (jiraSoftwareCloudApi)
- [ ] OpenAI API credential created (openAiApi)
- [ ] Google Docs OAuth2 credential created (googleDocsOAuth2Api)
- [ ] Target Google Docs document prepared and its ID/URL obtained
- [ ] Confirmed that your Jira workflow includes a Done status for Epics

Recommended approach: import the template workflow.json, then verify node parameters against the steps above, especially the AI Agent System Message and the Google Docs documentURL. Test with a dummy Epic before production use.