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 full legacy-code modernization for KM-Waechter: fixed the service-flagging logic, handled missing readings safely, corrected the nightly report’s average and crash path, repaired a hidden mileage-conversion bug, and added the missing regression test. Also produced a data-driven breakdown-risk analysis that prioritizes km_since_service, avg_daily_km, and load_factor over misleading mileage/age assumptions.
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 the silent helper bug in fleet_utils.km_to_miles that no test covered
- Preserved the 15000 km interval and 80% threshold while fixing the service logic
- Wrote a real NOTES.md describing what the agent got wrong and how the work was verified
- Leakage-Free Bug Diagnosis
- Directed AI Code Review
- Data-Driven Risk Analysis
The deliverable
The work I submitted20 tasks
12 tasks · 1.5k characters · 8 written answers · 105 words
- Division Predict70 characters
- Diagnose Line130 characters
- Diagnose Why246 characters
- Scope Prompt66 characters
- Audit Findings158 characters
- Audit Why94 characters
- Acceptance Checklist143 characters
- Bob Trial Click74 characters
- Bob Ready60 characters
- Template Repo Click82 characters
- Verify Report71 characters
- Exec Pitch282 characters
- Division Predict1 word
- Diagnose Line10 words
- Diagnose Why47 words
- Scope Prompt1 word
- Audit Findings1 word
- Audit Why17 words
- Acceptance Checklist27 words
- Bob Trial Click1 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.