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 complete legacy-code modernization for KM-Waechter: fixed the service-wear calculation, handled missing readings safely, repaired the nightly report, corrected a hidden mileage conversion bug, and added the missing regression test. Also produced a data-driven breakdown-risk analysis that used the actual fleet history signals instead of the misleading mileage assumption, and verified the work with an acceptance script before handoff.
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 hidden fleet_utils.km_to_miles conversion bug that no test covered
- Kept the 15000 km interval and 80% threshold unchanged while fixing the service logic
- Wrote a data-driven breakdown analysis that explicitly rejects the unsupported mileage/age assumption
- Documented the agent review process and verification steps clearly in NOTES.md
- Leakage-Free Feature Engineering
- Honest Model Evaluation
The work I submitted20 tasks
12 tasks · 2.0k characters · 8 written answers · 48 words
- Division Predict72 characters
- Diagnose Line130 characters
- Diagnose Why124 characters
- Scope Prompt66 characters
- Audit Findings158 characters
- Audit Why48 characters
- Acceptance Checklist80 characters
- Bob Trial Click74 characters
- Bob Ready60 characters
- Template Repo Click82 characters
- Exec Pitch676 characters
- Bob Bonus388 characters
- Division Predict1 word
- Diagnose Line10 words
- Diagnose Why18 words
- Scope Prompt1 word
- Audit Findings1 word
- Audit Why5 words
- Acceptance Checklist11 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.