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 a fleet service system: fixed the wear calculation, handled missing service readings safely, repaired the nightly report, corrected a hidden mileage-conversion bug in helper code, and added the missing regression test. Also produced a data-driven breakdown-risk analysis that follows the fleet history rather than the misleading mileage/age assumption, and documented the agent review process in NOTES.md.
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 quiet fleet_utils.km_to_miles bug that no test directly exposed
- Added the missing no-reading report test and verified the repo with verify.py
- Kept the 15000 km interval and 80% threshold unchanged while fixing the logic
- Wrote an analysis that identifies km_since_service and load_factor as the meaningful signals
- Leakage-Free Bug Diagnosis
- Directed AI Code Review
The work I submitted20 tasks
12 tasks · 2.5k characters · 8 written answers · 102 words
- Division Predict73 characters
- Diagnose Line130 characters
- Diagnose Why221 characters
- Scope Prompt66 characters
- Audit Findings158 characters
- Audit Why96 characters
- Acceptance Checklist178 characters
- Bob Trial Click74 characters
- Template Repo Click82 characters
- Bob Ready60 characters
- Verify Report71 characters
- Exec Pitch1.3k characters
- Division Predict1 word
- Diagnose Line10 words
- Diagnose Why38 words
- Scope Prompt1 word
- Audit Findings1 word
- Audit Why17 words
- Acceptance Checklist33 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.