Every commit scored for change-risk against this repo's own history, so 'elevated' means elevated here rather than on some global curve.
Needs review
13 commits sit in this repo's top risk tercile, which is 30% of the 44scored. The cut is drawn against this codebase's own history rather than a global curve, so a quiet repo still fills its top band, and here it starts at 9.5 out of 10. What pushes a commit up is size and spread together: a large change confined to one area scores below a smaller one scattered across a dozen files.
Commit categories over time, read off the subject line. Fixes carry the accent because that is the series this chart exists to show.
Began feature-led, now leaning fix.
Ranked by change-risk, highest first. Priority is a tercile of this repo's own distribution, so a quiet repo still fills its top band.
| # | Commit | Author | When | Lines | Risk | Top driver |
|---|---|---|---|---|---|---|
| 1 | 4867277bUpdated script of latetst IPL 2026 matches | Rajesh | 2mo ago | +26.6K -14 | 97%Elevated | more lines added than baseline |
| 2 | 439af4a6feat: add Claude Code setup, architecture diagrams, and improve README for beginners and several code changes | Rajesh | 4mo ago | +36.5K -4.2K | 97%Elevated | more lines added than baseline |
| 3 | b806ba51feat: initial commit – add 8 AI/ML projects with structured architecture and modular setup | Rajesh | 5mo ago | +69.5K -0 | 97%Elevated | more lines added than baseline |
| 4 | 31ec9d50feat: add multi-agent-anatomy, a runnable companion showing how multi-agent systems fail | Rajesh | 1w ago | +13.0K -0 | 89%Elevated | more lines added than baseline |
| 5 | 2ba11ebcAdded ai-patterns notebooks | Rajesh | 3mo ago | +12.7K -0 | 89%Elevated | more lines added than baseline |
| 6 | 10fb85f7feat: add Smart Claims Processor - multi-agent insurance claims system | Rajesh | 4mo ago | +7.8K -0 | 89%Elevated | more lines added than baseline |
| 7 | acce573eAdd Due Diligence Agent project: 6-agent research system with LangGraph | Rajesh | 5mo ago | +6.6K -0 | 89%Elevated | more lines added than baseline |
| 8 | fd4babd2Added multi-agents-app-on-aws project | Rajesh | 3mo ago | +3.6K -15 | 83%Elevated | more lines added than baseline |
| 9 | 4d9a012dfeat: add IPL 2025 season data (74 matches) and update notebook for URL-based loading | Rajesh | 4mo ago | +1.5K -112 | 81%Elevated | more lines added than baseline |
| 10 | 1e572013Align 5 project notebooks to Kaggle best practices | Rajesh | 5mo ago | +963 -100 | 78%Elevated | more lines added than baseline |
| 11 | 533e788fchore: clean up code and remove unused part | Rajesh | 2mo ago | +636 -636 | 74%Elevated | more lines added than baseline |
| 12 | 38e9fed8feat: add SVG architecture diagrams, replace ASCII art in README | Rajesh | 4mo ago | +620 -66 | 74%Elevated | more lines added than baseline |
| 13 | 18466797feat: update notebook with new features and 2025 data references | Rajesh | 4mo ago | +668 -19.4K | 74%Elevated | more lines added than baseline |
| 14 | 3246e0b3fix: credit-risk serve API + model-serving lint/config, add tests | Rajesh | 1w ago | +680 -57 | 66%Typical | more lines added than baseline |
| 15 | f5474d9ffeat: close 10 gaps between prediction script and repo code | Rajesh | 4mo ago | +520 -9 | 66%Typical | more lines added than baseline |
| 16 | a2b77001feat: add XGBoost and Neural Network classifiers to IPL prediction pipeline | Rajesh | 4mo ago | +578 -190 | 66%Typical | more lines added than baseline |
| 17 | f56d2fceAlign project notebooks to Kaggle best practices | Rajesh | 5mo ago | +552 -85 | 66%Typical | more lines added than baseline |
| 18 | 6c9d73dfClaude code setup | Rajesh | 3w ago | +361 -0 | 60%Typical | more lines added than baseline |
| 19 | ce189d0aUpdated claude code doc | Rajesh | 3mo ago | +140 -0 | 58%Typical | more lines added than baseline |
| 20 | ccfe8633Few fixes | Rajesh | 2mo ago | +150 -150 | 56%Typical | more lines added than baseline |
| 21 | e4fc5517Refectored project codebase with respect to latest gemini model changes | Rajesh | 3w ago | +113 -407 | 52%Typical | more lines added than baseline |
| 22 | 6a794702Fix beginner friction points in due-diligence-agent | Rajesh | 5mo ago | +78 -95 | 52%Typical | more lines added than baseline |
| 23 | d487c24bdocs: update README, docstrings for new features and 2025 data | Rajesh | 4mo ago | +68 -21 | 48%Typical | more lines added than baseline |
| 24 | 7a2e4727Swap Cohere to FlashRank, remove Makefile, simplify setup | Rajesh | 5mo ago | +65 -170 | 48%Typical | more lines added than baseline |
| 25 | 937327eafix: agent projects e2e - ragas eval, test isolation, dynamic IDs | Rajesh | 1w ago | +69 -21 | 43%Typical | more lines added than baseline |
| 26 | eeeb2f00Fixed missing files issues | Rajesh | 2mo ago | +74 -0 | 43%Typical | more lines added than baseline |
| 27 | f32c9a69Swap OpenAI to Google Gemini in RAG Expert Assistant | Rajesh | 5mo ago | +50 -67 | 40%Typical | more lines added than baseline |
| 28 | c0347d46Add .gitignore for due-diligence-agent project | Rajesh | 5mo ago | +31 -0 | 38%Typical | more lines added than baseline |
| 29 | ed9eccb2docs: add "About the Platform" section + FAQ for aimlcompanion.ai | Rajesh Srivastavaclaudeassisted | 4w ago | +27 -0 | 35%Typical | more lines added than baseline |
| 30 | 03ce49caReorder projects by progressive difficulty | Rajesh | 5mo ago | +23 -23 | 33%Below typical | more lines added than baseline |
| 31 | 3110c7d6Add Due Diligence Agent to README, fix stale capstones/ paths | Rajesh | 5mo ago | +22 -10 | 31%Below typical | more lines added than baseline |
| 32 | a2c6ecfdAdd interactive walkthrough links for all 9 projects | Rajesh | 5mo ago | +18 -0 | 27%Below typical | more lines added than baseline |
| 33 | 5e3455cfAdd AI-ML Companion link to all project READMEs | Rajesh | 5mo ago | +20 -0 | 27%Below typical | more scattered than baseline |
| 34 | a943895cAdd Smart Claims Processor as project #10 in README | Rajesh | 4mo ago | +17 -3 | 24%Below typical | more lines added than baseline |
| 35 | 5b021804Add Walkthrough column with module links to projects table | Rajesh | 5mo ago | +11 -11 | 22%Below typical | more focused than baseline |
| 36 | 26b559b1Fix strict Pydantic schemas causing agent fallback on valid LLM output | Rajesh | 5mo ago | +9 -68 | 19%Below typical | fewer lines added than baseline |
| 37 | ce064f81fix: use Huber loss for GBR regression (aligns with educational content) | Rajesh | 4mo ago | +7 -4 | 17%Below typical | fewer lines added than baseline |
| 38 | 5575463fFix Multi-Agent notebook: swap OpenAI to Gemini | Rajesh | 5mo ago | +6 -104 | 15%Below typical | fewer lines added than baseline |
| 39 | 7d6145acFix Windows terminal Unicode and stale model ref in notebook | Rajesh | 5mo ago | +4 -52 | 13%Below typical | fewer lines added than baseline |
| 40 | bdcd48a8fix: soften aggressive ML accuracy claims in IPL predictor | Rajesh | 4mo ago | +3 -13 | 10%Below typical | fewer lines added than baseline |
| 41 | 185dc3ecUpdated link at README | Rajesh | 4mo ago | +3 -0 | 8%Below typical | fewer lines added than baseline |
| 42 | 43fdcf9cUpdate project description in README | Rajesh Srivastava | 5mo ago | +2 -2 | 6%Below typical | fewer lines added than baseline |
| 43 | 647db345Fix deprecated ragas.metrics import to ragas.metrics.collections | Rajesh | 5mo ago | +1 -1 | 3%Below typical | fewer lines added than baseline |
| 44 | 97e5f057Updated link at the README | Rajesh | 4mo ago | +1 -0 | 1%Below typical | fewer lines added than baseline |
Two views of the same model: where the cuts fall, and what commit shape lands you above them.
Every scored commit, binned on the raw 0 to 10 score rather than the percentile. Percentile ranks are uniform by construction, so that axis has no shape to draw. The dashed lines are the tercile cuts behind each row's priority pill.
The 44 most recent commits, on their own recency sample rather than the feed above: that defaults to risk-sorted, so reusing it would plot only the top tercile and call it the spread. Big and scattered is what the model penalises. Click a dot to open it.
genieincodebottle/aiml-companion has 45 commits in its history from 2 contributors, the first of them Mar 1, 2026. In the last 90 days 153 files were touched, 163 times in total, most often app.py. Every commit is scored for change risk from its size, spread and the history of the files it touches.
