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 KM-Waechter: fixed the wear calculation, handled missing service readings safely, repaired the nightly report, corrected a hidden mileage-conversion bug in the helpers, and added the missing regression test. Also delivered a data-driven breakdown-risk analysis that uses the fleet history to rank cars by real risk factors rather than the misleading 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
- Correctly identified the floor-division wear bug and explained why it suppressed nearly-worn cars
- Swept the helper module and fixed the quiet km-to-miles conversion error that no test directly caught
- Wrote a substantive NOTES.md and a plain-language exec_pitch that match the repo changes
- Leakage-Free Bug Diagnosis
- Directed AI Code Review
- Data-Driven Risk Analysis
The deliverable
The work I submitted20 tasks
12 tasks · 1.8k characters · JavaScript · 8 written answers · 64 words
- Division Predict73 characters
- Diagnose Line130 characters
- Diagnose Why49 characters
- Scope Prompt66 characters
- Audit Findings136 characters
- Audit WhyJavaScript · 279 characters
- Bob Trial Click74 characters
- Bob Ready60 characters
- Template Repo Click82 characters
- Exec Pitch565 characters
- Bob Bonus206 characters
- Repo URL49 characters
- Division Predict1 word
- Diagnose Line10 words
- Diagnose Why9 words
- Scope Prompt1 word
- Audit Findings1 word
- Audit Why40 words
- Bob Trial Click1 word
- Bob Ready1 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.