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 a complete modernization and bug-fix pass for a legacy fleet-service repo: corrected wear calculations, handled missing service readings safely, fixed the nightly report’s average and crash path, and repaired a hidden mileage-conversion bug in shared helpers. They also added the missing regression test, produced a data-driven breakdown-risk analysis, and verified the result with an 11/11 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
- Caught and fixed the hidden fleet_utils.km_to_miles conversion bug that no test directly covered
- Added the missing no-reading report test and preserved the original test coverage after the agent tried to replace the file
- Wrote NOTES.md in their own words, including how they verified the agent's work with verify.py
- Leakage-Free Bug Diagnosis
- Verified AI Output Auditing
- Data-Driven Risk Analysis
The deliverable
The work I submitted20 tasks
12 tasks · 2.0k characters · 8 written answers · 91 words
- Division Predict70 characters
- Diagnose Line130 characters
- Diagnose Why161 characters
- Scope Prompt66 characters
- Audit Findings158 characters
- Audit Why187 characters
- Acceptance Checklist177 characters
- Template Repo Click82 characters
- Bob Trial Click76 characters
- Bob Ready60 characters
- Verify Report71 characters
- Exec Pitch798 characters
- Division Predict1 word
- Diagnose Line10 words
- Diagnose Why26 words
- Scope Prompt1 word
- Audit Findings1 word
- Audit Why26 words
- Acceptance Checklist25 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.