What ishita demonstrated

Built and verified a full legacy-code modernization for a fleet service tool: corrected the wear calculation, handled missing service readings safely, fixed the nightly report’s average and crash path, repaired a hidden mileage-conversion bug in shared helpers, and added the missing regression test. Also produced a data-driven breakdown-risk analysis that follows the fleet history rather than the misleading mileage assumption, with clear acceptance notes documenting what the AI agent got wrong and how the work was checked.

• Leakage-Free Feature Engineering
• Honest Acceptance Verification
• Directed AI Code Review