ProofChange AI Change Verification

THE PROBLEM CI answers one question: "Did the configured tests pass?" It does not answer the question that matters at merge time: "Is the newly changed behavior adequately verified?" A pull request can add a new branch, a new execution path, or a new edge case while CI stays entirely green — because the existing test suite never exercises the new code. Those tests were written for the old behavior. No test ever fails. The change ships unverified. This is not a test-quality problem. It is a test-coverage blindspot at the point of change, and every team that treats a green CI check as its only safety signal has it. The failure mode is silent and expensive: an untested authorization branch ships on a Friday, and the incident lands on Monday. THE SOLUTION ProofChange is an AI-powered verification layer that closes the gap between "CI passed" and "this change is verified." Its core output is a Change Evidence Package — a structured, machine-readable artifact produced automatically for every pull request. The key insight is ordering. Test generation is step 5 of 7, not the product. ProofChange first proves a gap exists (steps 1–4) and then proves the gap is closed (steps 6–7). The generated test is evidence, not the deliverable. The 8-stage pipeline runs: 1. Diff Analysis — parses the unified diff, extracting changed files, line ranges, and added conditionals. 2. Code Analysis — Python AST walk mapping functions, branches, return paths, and source file paths. 3. Test Mapping — links existing tests to affected functions by name heuristics and docstring scan. 4. Gap Detection — finds branches with no mapped test scenario; promotes security-keyword branches to HIGH severity. 5. Test Generation — IBM Bob produces focused pytest scaffolds targeting each detected gap. 6. Execution — runs real pytest against generated tests, capturing pass/fail/skipped/duration. 7. Impact Analysis — classifies affected paths as verified / partial / unresolved, deduplicated by (source_path, fn_name). 8. Evidence Package — aggregates all outputs into a scored, timestamped JSON + Markdown artifact. TARGET USERS & INTERACTION Backend developers shipping urgent fixes, new developers working in unfamiliar legacy code, and compliance/security teams needing audit evidence. Users interact through a Streamlit dashboard (8 pages) or automatically via a GitHub App webhook that posts a Check Run on every PR — no manual step required. Every PR receives a verdict: STRONG (all gaps addressed, ≥70% paths verified, all tests passed), PARTIAL (some gaps or paths unresolved), or INSUFFICIENT (tests failed or gaps remain). Critically, the level is computed by explicit, auditable rules — not an LLM opinion — and every level carries a plain-language rationale string. WHAT MAKES IT UNIQUE Unlike generic AI test generators that work speculatively across a whole repo from an arbitrary prompt, ProofChange is anchored to the diff itself. It detects gaps before generating, runs tests as a mandatory step, and issues a scored verdict. AI assists the pipeline; the engine runs deterministically without it. IMPACT ProofChange prevents the untested Friday deploy, helps new developers ship safely in unfamiliar code, and gives compliance teams a byproduct artifact — the EvidencePackage JSON is generated on every PR, so audits need no retrospective authoring. Live at proofchange-demo.streamlit.app with a working STRONG-evidence VIP-discount demo, live GitHub PR analysis (App ID 5079526, Check Run posted), 27/27 passing tests, and a green GitHub Actions pipeline.