Self-directed project
AI-Assisted Code Modernization with IBM
Junior Software Engineer · Software Engineering · August 2026
Based on a public IBM case study · not affiliated with IBM
Built and verified a working modernization of a legacy car-service repo: corrected the wear calculation, handled missing service readings safely, fixed the fleet report’s average and crash path, preserved the 15000 km / 80% rules, and added the missing regression test. Also produced a data-driven breakdown-risk analysis that ranks cars by service wear and driving load rather than falling for the mileage trap.
Graded against
- Fix and extend the repo with the agent35%
- Diagnose the bug20%
- Direct and audit the AI agent25%
- Explain it like an engineer20%
Passed · pass mark 60/100
What stood out6
- Fixed the wear calculation so a nearly-worn car is no longer floored to 0%
- Handled missing last-service readings without crashing the nightly report
- Added the missing regression test for a car with no reading
- Wrote NOTES.md with concrete examples of what the agent got wrong and how it was verified
- Leakage-Free Bug Diagnosis
- Honest Acceptance Checking
The deliverable
The work I submitted17 tasks
9 tasks · 3.0k characters · 8 written answers · 292 words
- Bob Trial Click74 characters
- Diagnose Line130 characters
- Scope Prompt66 characters
- Audit Findings158 characters
- Audit Why118 characters
- Template Repo Click82 characters
- Exec Pitch2.0k characters
- Bob Bonus361 characters
- Repo URL54 characters
- Bob Trial Click1 word
- Diagnose Line10 words
- Scope Prompt1 word
- Audit Findings1 word
- Audit Why20 words
- Template Repo Click1 word
- Exec Pitch191 words
- Bob Bonus67 words
Summarised on purpose — the submitted code and writing stay private so this page cannot be reused as an answer key. The full submission sits behind the verified certificate.