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 a working modernization of the KM-Waechter service flow: corrected the wear calculation, handled missing service readings safely, fixed the nightly report’s average and crash path, and repaired the quiet mileage-conversion bug in the helper module. They also added the missing report test, preserved the 15000 km / 80% rules, and produced a data-driven breakdown-risk analysis that follows the labelled fleet history rather than the obvious mileage assumption.
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 quiet helper bug in fleet_utils.km_to_miles, which is the strongest sign they swept beyond the obvious failing tests.
- Handled the missing last-service reading in both km_wachter.py and fleet_report.py without changing the service rules.
- Wrote analyze.py to emphasize km_since_service, avg_daily_km, and load_factor while explicitly rejecting odometer_km and age_years as the main predictors.
- Leakage-Free Bug Fixing
- Honest Acceptance Checking
- Data-Driven Risk Analysis
The deliverable
The work I submitted10 tasks
5 tasks · 1.1k characters · 5 written answers · 124 words
- Bob Trial Click76 characters
- Bob Ready61 characters
- Exec Pitch582 characters
- Bob Bonus285 characters
- Repo URL50 characters
- Bob Trial Click1 word
- Bob Ready1 word
- Exec Pitch72 words
- Bob Bonus49 words
- Repo URL1 word
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.