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 and verified a full legacy-code modernization for KM-Waechter: fixed the wear calculation, handled missing service history safely, repaired the nightly report’s averaging and crash path, and found a hidden mileage-conversion bug in the helper layer. Also added the missing regression test, documented the review in NOTES.md, and produced a data-driven breakdown-risk analysis that ranks cars by service urgency using the signals the dataset actually supports.
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
- Correctly identified the whole-number division bug and explained why it suppressed a nearly-worn car to 0%
- Caught the agent’s subtle missing-reading mistake and insisted on an explicit key check instead of a misleading default
- Swept the helper module and fixed the quiet km_to_miles conversion bug that no test directly covered
- Built a sensible breakdown-risk analysis that follows the data rather than the tempting mileage/age assumption
- Leakage-Free Bug Diagnosis
- Directed AI Code Review
The work I submitted16 tasks
8 tasks · 1.3k characters · 8 written answers · 140 words
- Division Predict73 characters
- Diagnose Line130 characters
- Diagnose Why146 characters
- Scope Prompt66 characters
- Audit Findings158 characters
- Audit Why433 characters
- Acceptance Checklist174 characters
- Bob Trial Click74 characters
- Division Predict1 word
- Diagnose Line10 words
- Diagnose Why25 words
- Scope Prompt1 word
- Audit Findings1 word
- Audit Why73 words
- Acceptance Checklist28 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.