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 tool: fixed the wear calculation, handled missing readings safely, corrected the nightly report, repaired a hidden mileage-conversion bug, added the missing regression test, and produced a data-driven breakdown-risk analysis that follows the actual fleet-history signals. Also documented the review process in NOTES.md and validated the result with an acceptance check.
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
- Fixed the hidden helper-module bug in fleet_utils.km_to_miles, which is the strongest sign they swept beyond the obvious failures
- Added the missing no-reading report test and verified the repo with both pytest and verify.py
- Wrote analyze.py to separate true predictors of breakdown from misleading total mileage and age
- Leakage-Free Bug Diagnosis
- Directed AI Code Review
- Data-Driven Risk Analysis
The deliverable
The work I submitted20 tasks
12 tasks · 1.7k characters · 8 written answers · 48 words
- Division Predict73 characters
- Diagnose Line130 characters
- Diagnose Why70 characters
- Scope Prompt66 characters
- Audit Findings158 characters
- Audit Why45 characters
- Acceptance Checklist112 characters
- Template Repo Click82 characters
- Bob Ready60 characters
- Verify Report71 characters
- Exec Pitch283 characters
- Bob Bonus523 characters
- Division Predict1 word
- Diagnose Line10 words
- Diagnose Why11 words
- Scope Prompt1 word
- Audit Findings1 word
- Audit Why6 words
- Acceptance Checklist17 words
- Template Repo 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.