ProofForge

01 · Creation

Kane CLI Hack Day

A browser test can pass while a booking disappears after sign-out. ProofForge uses OpenAI and Kane CLI to show what its evidence actually establishes.

A browser test can correctly pass while verifying only part of the actual product requirement. For example, a booking confirmation can appear successfully while the booking itself disappears after

01 / 05 · ProofForge

02 · See it work

Kane CLI Hack Day

See it work

1Start with an independently versioned product contract.
2Run a baseline Kane test and inspect what its passing evidence actually establishes.
3Use OpenAI to identify missing observations and propose stronger checks.

02 / 05 · ProofForge

03 · The harness

Kane CLI Hack Day

The intelligence behind shipping

ProofForge uses an independently versioned contract, BOOKING-PERSISTENCE 1.0.0. After sign-out and fresh authentication, the same customer must be able to retrieve the original booking ID and matching details within six seconds of the retrieval request. The previous session must be invalidated. The baseline Kane CLI test verifies booking confirmation and passes, but does not establish persistence. OpenAI analyzes the missing requirement-level observations and proposes stronger browser actions and seven atomic DOM conditions. Kane executes isolated browser journeys against three controlled behaviors: correct server-side persistence, session-only booking loss, and an admissible retrieval delay. The original Kane navigation verdicts are preserved. Separate condition evaluations on the retained browser pages provide actual boolean results. ProofForge correlates these with independent fixture observations, authentication state, booking identity, timing, and validated navigation evidence packs. The deterministic classifier accepts the correct and admissibly delayed cases, rejects the corroborated session-loss violation, and retains unrelated automation failures or insufficient observations as inconclusive. Actual outcomes return to OpenAI for feedback. Each evidence receipt preserves source identity, execution provenance, original verdicts, and the limits of the supported conclusion.

01Define the contract
02Inspect the passing baseline
Calibrate with OpenAI + Kane

04 · Proof

Kane CLI Hack Day

What Kane actually verified

VerifiedKane run passed: Open [local fixture] Verify the ProofForge title, select Calibrate and assert all three controlled behavior cards are visible, select Prove and assert Established, Not Established, and Remaining Limitations sections are visible. Open Contract in the left sidebar and verify the authoritative booking requirement and version 1.0.0 are shown. Close the dialog. Select Inspect and assert Run baseline is visible. Do not start any paid execution or modify the contract.run 187 · passed · commit 312c9222fd · kane_run:mcp
VerifiedKane run passed: Navigate to [local fixture] Sign in as alex using Sign in. Click Confirm booking. Click Sign out. Sign in again as alex using Sign in again. Click Retrieve booking once. Wait exactly 7 seconds once. Finish. Finish after the fixed wait; a separate Kane condition check will evaluate retrieval. Do not assert or analyze the retrieval result in this navigation phase.run 88 · passed · commit e7afc66961 · kane_run:mcp
Verified

05 · Outcome

Kane CLI Hack Day

What improved

A browser test can pass while a booking disappears after sign-out. ProofForge uses OpenAI and Kane CLI to show what its evidence actually establishes.

https://github.com/beyond-time/proofforge · Mykyta Kharkevych

kaneclihack.sh/ship/proofforge