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 a full legacy-code modernization for a fleet-service tool: fixed the wear calculation, handled missing service readings safely, repaired the nightly report’s average and crash path, corrected a hidden mileage-conversion bug, and added the missing regression test. Also produced a data-driven breakdown-risk analysis that follows the labeled fleet history 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
- Caught and corrected the missing-reading default so a car is treated as just serviced instead of falsely flagged
- Found the quiet fleet_utils.km_to_miles inversion that no test directly covered
- Wrote a real breakdown-risk analysis that identifies km_since_service and avg_daily_km as the meaningful signals
- Verified the work with pytest and verify.py before accepting it
- Leakage-Free Bug Diagnosis
- Directed AI Agent Auditing
The work I submitted19 tasks
11 tasks · 3.2k characters · 8 written answers · 298 words
- Diagnose Line130 characters
- Diagnose Why239 characters
- Scope Prompt66 characters
- Audit Findings158 characters
- Audit Why123 characters
- Acceptance Checklist126 characters
- Template Repo Click82 characters
- Exec Pitch1.7k characters
- Bob Bonus263 characters
- Bob Ready61 characters
- Bob Trial Click266 characters
- Diagnose Line10 words
- Diagnose Why39 words
- Scope Prompt1 word
- Audit Findings1 word
- Audit Why21 words
- Acceptance Checklist25 words
- Template Repo Click1 word
- Exec Pitch200 words
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.