Skip to content

docs: rewrite What's Novel → What Makes This Different #50

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
BaseInfinity merged 2 commits into from
Feb 17, 2026
Merged

docs: rewrite What's Novel → What Makes This Different #50

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f6bbb0a
docs: rewrite "What's Novel" as "What Makes This Different"
BaseInfinity Feb 17, 2026
67927fc
Merge branch 'main' into docs/readme-whats-different
BaseInfinity Feb 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 8 additions & 10 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,18 +39,16 @@ You want Claude Code to follow engineering discipline automatically:

The wizard auto-detects your stack (package.json, test framework, deployment targets) and generates bespoke hooks + skills + docs.

## What's Novel
## What Makes This Different

| Innovation | Status |
| Capability | What It Does |
|---|---|
| E2E scoring of AI agent SDLC behavior in CI | Nobody else does this |
| Before/after wizard A/B testing in CI | Nobody else does this |
| SDP: normalizing scores against external benchmarks | Nobody else does this |
| Robustness ratio (SDLC resilience vs model quality) | Nobody else does this |
| CUSUM drift detection for AI behavior | Borrowed from manufacturing QC |
| Pre-tool hooks enforcing TDD on AI agents | Guardrails exist for safety, not discipline |

**What exists elsewhere:** LLM eval frameworks (Promptfoo, DeepEval), code quality (SonarQube), LLM monitoring (Arize, Langfuse), AI benchmarks (SWE-bench). **The unique value = the integration into a self-improving loop.**
| **E2E scoring in CI** | Every PR gets an automated SDLC compliance score (0-10) — measures whether Claude actually planned, tested, and reviewed |
| **Before/after A/B testing** | Compares wizard changes against a baseline with 95% confidence intervals to prove improvements aren't noise |
| **SDP normalization** | Separates "the model had a bad day" from "our SDLC broke" by cross-referencing external benchmarks |
| **CUSUM drift detection** | Catches gradual quality decay over time — borrowed from manufacturing quality control |
| **Pre-tool TDD hooks** | Claude can't write code without writing tests first — enforced at the hook level, not just guidance |
| **Self-evolving loop** | Claude proposes process improvements from friction it encounters — you approve, the system gets better |

## How It Works

Expand Down