Self-directed project
AI-Assisted Code Modernization with IBM
Junior Software Engineer · Software Engineering · September 2026
Based on a public IBM case study · not affiliated with IBM
Built a complete legacy-code modernization for a fleet service tool: fixed the wear calculation, handled missing service readings safely, repaired the nightly report, corrected a hidden helper-module mileage bug, and added the missing regression test. Also delivered a data-driven breakdown-risk analysis that follows the fleet history data rather than the misleading mileage assumption, with clear notes documenting what the AI agent got wrong and how the work was verified.
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
- Caught and fixed the quiet km-to-miles conversion bug in the helper module
- Kept the 15,000 km interval and 80% threshold unchanged in both code and settings.cfg
- Added the missing no-reading report test and verified the report no longer crashes
- Produced a data-driven breakdown-risk analysis that uses km_since_service, avg_daily_km, and load_factor
- Leakage-Free Feature Engineering
- Honest Model Evaluation
The deliverable
The work I submitted17 tasks
9 tasks · 1.7k characters · 8 written answers · 207 words
- Division Predict70 characters
- Diagnose Line130 characters
- Diagnose Why149 characters
- Audit Findings158 characters
- Audit Why203 characters
- Acceptance Checklist220 characters
- Exec Pitch366 characters
- Bob Bonus310 characters
- Repo URL60 characters
- Division Predict1 word
- Diagnose Line10 words
- Diagnose Why28 words
- Audit Findings1 word
- Audit Why27 words
- Acceptance Checklist32 words
- Exec Pitch58 words
- Bob Bonus50 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.