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 and verified an end-to-end modernization of a legacy fleet-maintenance service: corrected the wear calculation, handled missing service readings safely, fixed the nightly report’s average and crash path, and swept helper code to catch a silent mileage-conversion bug. Also added the missing regression test, preserved the business rules, and produced a data-driven breakdown-risk analysis grounded in the actual fleet history rather than assumptions.
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 silent fleet_utils.km_to_miles conversion bug that no test directly covered
- Added the missing no-reading fleet report test and verified the report no longer crashes
- Kept the service interval and warning threshold unchanged while fixing the logic
- Built a data-driven risk analysis that explicitly rejects odometer_km and age_years as predictors
- Leakage-Free Feature Engineering
- Honest Model Evaluation
The deliverable
The work I submitted16 tasks
8 tasks · 1.7k characters · 8 written answers · 178 words
- Bob Trial Click74 characters
- Diagnose Line130 characters
- Diagnose Why150 characters
- Audit Findings149 characters
- Template Repo Click82 characters
- Exec Pitch711 characters
- Bob Bonus340 characters
- Repo URL53 characters
- Bob Trial Click1 word
- Diagnose Line10 words
- Diagnose Why27 words
- Audit Findings1 word
- Template Repo Click1 word
- Exec Pitch90 words
- Bob Bonus47 words
- Repo URL1 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.