Vibe coding level UP

Last week my colleague Pieter suggested me a nice article about "Long-term DORA data reveals systemic performance plateaus and shifts, allowing organizations to connect improvements to architectural, cultural, and process changes."

So starting from my current level of Jira Lead Time Analyzer i developed in vibe coding, I tried to improve my report accordingly again using vibe coding.

I tried to ask JitHub Copilot (yes at this time not anymore AmazonQ because of the limitation I got) to create PBC report for the Jira projects we are managing in our Large Scaled Organization.

The powerfull result was that I provided some request to improve for example the duration of the analysis, to reuse the same approach (Flask app in python) accessing jira with JTA but not much about the graph and the rusul was really amazing...

First prompt:

Considering the Lead Time Analyzer I would like to create a new Flask
Application which calculate the Process Behavior Charts for each
projects identified during the retrieval of project connected to the
first input query.
I would like to have a chart which represent for each projects the Medium
Lead time and the 85% lead time threshold calculated.
I would like than to see the real lead time calculated each month
depicted in the diagram starting from august 2024.
My intention like per the article
https://www.infoq.com/articles/DORA-metrics-PBCs/ is to identify trends
and spike so that we can identify and address issues.

Response

It was shared the code:

📦 Created Files:
pbc_analyzer.py - Core analysis engine that:

• Calculates median and 85th percentile lead times per project
• Computes control limits (UCL/LCL) using ±3σ methodology
• Groups data by month starting from August 2024
• Detects special causes (points outside control limits)
• Identifies trends (7+ consecutive increases/decreases)
• Assesses process stability

pbc_web_app.py - Flask application (standalone on port 5500)

templates/pbc_analyzer.html - Beautiful web interface with:

• Interactive Chart.js visualizations
• Monthly trend lines for mean, median, and P85
• Control limit boundaries displayed
• Color-coded stability status
• Special cause and trend alerts

pbc_config.json - Configuration file with defaults

PBC_README.md - Complete documentation

and than this nice report:

🎯 Key Features:
✅ Median & P85 calculations per project
✅ Monthly aggregation starting August 2024
✅ Control charts with UCL/LCL (±3σ)
✅ Special cause detection (outliers)
✅ Trend detection (7+ consecutive points)
✅ Process stability assessment
✅ Multi-project analysis from single JQL query
✅ Interactive visualizations showing all metrics on one chart

Second prompt

In the log I do not see the query executed, can you add some debugging level logs which I can disable to check what query are executed? I know the input query is based on a project which started after the august 2024, but I would like to analyze the projects related to the input one which were existing before. Than I need the calculation for the following months till today

Second response:

**Summary of Changes

I've enhanced the PBC Analyzer with the following capabilities:

🐛 Debug Logging
New checkbox in UI: "Enable Debug Logging" to see all JQL queries being executed
Detailed query logging: Shows every JQL query executed against Jira
Progress tracking: See which projects are being fetched and how many issues found
🔍 Related Project Discovery
The analyzer now works like the PI analyzer:

Executes your initial query (e.g., a project that started after Aug 2024)
Discovers related projects through:
Parent/child relationships
Epic links
Issue links (blocks, relates, etc.)
Fetches data from ALL related projects starting from August 2024, even if those projects existed before
📊 Enhanced Analysis
Monthly calculations from Aug 2024 to today for all discovered projects
Each project gets its own PBC with control limits
Special causes and trends detected per project

Third prompt

I see the analysis is done only on initial project but I would like to see the analysis also to all the connected Jira projects following the whole hierarchy (for each Business initiatives we should collect the related feature and sub-feature and than epics in each other projects like we did in original Lead time analyzer)

Third response

Final graphs

My comments

"Vibe coding" proved to be an excellent way to quickly transform an initial idea into a functional application that can be further refined. The most impressive takeaway was the AI's ability to extract additional information directly from the article without requiring manual data definitions or graph formatting. Achieving such a great result in just a few minutes was truly remarkable.