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 an end-to-end modernization of the KM-Waechter service: corrected the wear calculation, handled missing service readings safely, fixed the nightly report’s average and crash path, repaired the hidden mileage-conversion helper bug, and added the missing regression test. Also delivered a data-driven breakdown-risk analysis and documented the agent review process in clear 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 and fixed the quiet km-to-miles helper bug that no test directly exposed.
- Added the missing no-reading report test and verified the repo with both pytest and verify.py.
- Produced a breakdown-risk analysis that follows the data instead of the misleading mileage/age assumption.
- Leakage-Free Feature Engineering
- Honest Model Evaluation
- Directed AI Agent Auditing
The deliverable
The work I submitted20 tasks
12 tasks · 2.3k characters · 8 written answers · 138 words
- Division Predict73 characters
- Diagnose Line130 characters
- Diagnose Why238 characters
- Scope Prompt66 characters
- Audit Findings158 characters
- Audit Why324 characters
- Acceptance Checklist213 characters
- Bob Trial Click74 characters
- Template Repo Click152 characters
- Verify Report71 characters
- Exec Pitch488 characters
- Bob Bonus279 characters
- Division Predict1 word
- Diagnose Line10 words
- Diagnose Why43 words
- Scope Prompt1 word
- Audit Findings1 word
- Audit Why49 words
- Acceptance Checklist32 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.