A Journey of Transforming Developer Productivity at Bank Islam
Sometimes the biggest innovations start with the smallest commits
The Be U Commit dashboard: Transforming raw git data into actionable team insights
It was a warm August morning in Kuala Lumpur when I walked into Bank Islam's Digital Banking division as a fresh-faced intern. Armed with nothing but my laptop and an unhealthy addiction to coffee, I was ready to take on the world - or at least try not to break the production environment.
Little did I know that within two months, I'd be building something that would change how one of Malaysia's largest banks thinks about developer productivity.
From Documentation to Discovery
Using an open-source AI approach, I transformed what was typically a time-consuming, error-prone documentation process into something more efficient. Instead of manually writing README files, I developed an injection script that could analyze repositories and generate comprehensive documentation automatically. What used to take a full day could now be completed in hours.
The same principle worked for our API documentation. Rather than having developers run separate libraries each time they needed to access API lists, we created a centralized system that made documentation accessible across all repositories. Small wins, but they hinted at bigger possibilities.
The Turning Point
Around day 25 of my internship, after swimming through oceans of README files and API docs, I noticed something. Our teams were scattered across different locations, working remotely, and no one had a clear picture of what was happening. AWS CodeCommit was being sunset, and our tech leads were struggling to track developer productivity.
"How do we know if our teams are truly productive?" I asked En. Hatta during one of our daily standups.
His response? "Why don't you figure it out?"
Building the Magic Machine
That's when Be U Commit started taking shape. I dove deep into research from Google's DevOps teams and Microsoft's assessment frameworks, but reading papers wasn't enough because we needed something real.
Developer productivity metrics framework based on Google's DevOps research and Microsoft's assessment methodology
Starting with rough sketches that turned into wireframes, I designed three core interfaces:
- A Dashboard page showing total commits and pull requests
- A Developers page displaying team metrics and rankings
- Individual Developer profiles tracking personal growth
As a Product Engineer, I wasn't just designing but I need to build. Every component had to work seamlessly in our AWS infrastructure. The pipeline wasn't just about moving data but it was about transforming it into something meaningful.
From git commits to actionable insights: Be U Commit's data pipeline
Making Magic Happen
Bringing the MVP to life was like solving a puzzle where the pieces kept changing shape.
We needed to:
- Process git logs in real-time
- Calculate efficiency scores that actually meant something
- Present data in a way that inspired rather than intimidated
The interface had to be more than just pretty charts where it needed to tell stories. Pull requests that used to take 16 hours started taking 9, not because we were pushing harder, but because we could see the bottlenecks clearly.
We built something special. Developers could see their impact in real-time. Team leads could identify who needed help before they even asked for it. The dashboard became less about metrics and more about mentorship.
The End (Or Is It?)
They say the best solutions come from really understanding the problem. In my case, it came from documenting hundreds of repositories and drinking way too much coffee. But isn't that how all good tech stories start?
Remember: Every git commit tells a story. We just built the storyteller.
Written by Irfan Ghapar, who went from being terrified of git merge conflicts to building a productivity dashboard that even git would be proud of.
P.S. No repositories were harmed in the making of this story. :)
Top comments (0)