Generate Lessons Learned Reports From Jira Epics
When a Jira Epic is marked Done, the agent compiles tasks and comments to generate an automated Lessons Learned report in Google Docs.
What it does
Get automated Lessons Learned reports in Google Docs as soon as your Jira Epic is marked Done. The agent gathers tasks and comments from Jira Software to create a structured summary without manual effort.
Step by step
- Configure the Jira webhook or API call to listen for status changes on Epics with a specific key.
- Map the retrieved Epic fields and linked issue comments into a structured JSON payload for the AI model.
- Use the Google Docs API to create a new document and insert the final text output at a specified location.
Where the LLM does the work
- Instruct the LLM to synthesize scattered team feedback from multiple issues into cohesive narrative sections rather than listing raw comments.
- Define specific prompts that guide the model to identify root causes for delays and highlight successful practices mentioned in the thread.
- Format the generated text with clear headings like 'Key Takeaways' and 'Action Items' to ensure readability in the final report.
Watch out for
Sensitive project details might leak into the LLM prompt, so strip out PII or confidential identifiers before sending data to OpenAI.
Google Docs permissions may prevent the script from editing the file, ensure the service account has editor access to the target folder.
Long comment threads can exceed token limits, implement a truncation strategy that keeps the most recent or highest-voted comments first.
Tools that fit
Jira Software Service Trigger and fetch epic data
OpenAI Chat Model LLM Generate report content
The agent brief
Everything your agent needs, including the gotchas. Copy it and go.
You are helping me build the following AI agent workflow. ## Goal Generate Lessons Learned Reports From Jira Epics: When a Jira Epic is marked Done, the agent compiles tasks and comments to generate an automated Lessons Learned report in Google Docs. ## Specification - What it does: Get automated Lessons Learned reports in Google Docs as soon as your Jira Epic is marked Done. The agent gathers tasks and comments from Jira Software to create a structured summary without manual effort. - Trigger: Triggered by an event (Event · on Epic Done status) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - Jira Software: Trigger and fetch epic data - OpenAI Chat Model: Generate report content - Google Docs: Store final report ## Known pitfalls, handle each one explicitly in your implementation 1. Sensitive project details might leak into the LLM prompt, so strip out PII or confidential identifiers before sending data to OpenAI. 2. Google Docs permissions may prevent the script from editing the file, ensure the service account has editor access to the target folder. 3. Long comment threads can exceed token limits, implement a truncation strategy that keeps the most recent or highest-voted comments first. ## Reference implementation https://n8n.io/workflows/3934 (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/generate-lessons-learned-reports-from-jira-epics/ via usecasesforagents.com
Frequently asked questions
Can I use a different Project Management than Jira?
Yes. Jira is only the example project management in this recipe. The same flow works with Asana, Awork, ClickUp and Clockify. Swap the project management connection and keep the rest of the setup as written.
Want this running in your business?
This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.
Who it's for
Built for developers who want the busywork around code automated, not the code itself.