Survey
Agents for each reviewer read the diff and the code around it, and propose concerns. A concern your team already ruled out in a past discussion or a memory is skipped here.
AI review is cheap to generate and expensive to trust. Baz splits every review into proposing and proving: agents survey the change for concerns, then a separate verifier must confirm each one with evidence before it reaches your pull request. Requirements from the ticket and design get the same treatment, checked against the code and the running application.
Bugs and requirements are verified on separate tracks, each with its own verdicts, and both land in one session you can inspect.
Agents for each reviewer read the diff and the code around it, and propose concerns. A concern your team already ruled out in a past discussion or a memory is skipped here.
A dedicated verifier investigates each concern across files, history, and related repositories. It must confirm it with evidence or close it as refuted, suppressed, or incomplete.
A confirmed finding states the entry point, the runtime condition, the failure, how far it reaches, and how certain the verifier is. Severity is scored from that evidence, not from tone.
A finding posts only when the trigger is shown to be reachable on the changed path. Claims that rest on what might happen are dropped before anyone reads them.
The Verification Agent pulls requirements from the linked ticket in Jira, Linear, Azure DevOps Boards, and other trackers, and marks each one met, partially met, not met, or unverified.
With a sandbox or a preview environment, the agent signs in, opens the app in a real browser, and compares it to the Figma design or ticket images.
Annotated screenshots mark where each requirement lives on screen, in the Spec Reviewer Report on the pull request and in the session.
Your test suites, fuzzers, and formal proofs keep running in CI. Baz verifies what they cannot express: intent, reachability, and how the app actually looks. Security Review applies the same proof bar to exploitability.
One pull request, followed from the first concern to the sandbox that ran it.
Survey agents propose concerns without commenting. Overlaps fold into one, then a verifier investigates each and returns a verdict. The session keeps every verdict and its reason, including the ones that never reached the PR.
How sessions record a reviewusage/format.ts:31routes/export.ts:18UsageTable.tsx:44usage/range.ts:12UsageTable.tsx:1usage/csv.ts:9Only confirmed concerns become PR comments. The rest stay in the session with the reason.
A confirmed finding states where it enters, when it fails, what breaks, and how far it reaches, with the commit it was verified at. Here the consumer that breaks lives in another repository.
What each review agent coversformatCredits() now returns a formatted string. billing-service still sums its result, so invoice totals concatenate instead of add.
GET /api/usage/export calls buildUsageRows()formatCredits() now returns a string; invoice.ts:88 adds it to a numberbilling-service at its pinned commit, outside this PR- return Math.round(credits * 100) / 100;+ return credits.toLocaleString(locale);The Verification Agent reads the linked ticket and design, then checks each requirement against the code and the running app. When it cannot check one, it says unverified instead of guessing.
Connect a ticketing integration9f3c2a1CR-4611Figma · UsageCheckout in BazThe agent opens the change in a real browser, signs in, and compares what renders with the Figma frame. Screenshots come back annotated, so the reviewer sees the drift instead of reading about it.
Connect FigmaEach repository defines how to set up, start, and sign in to the app. Baz builds a short-lived sandbox from the branch, waits for the health check, verifies, stores the evidence, and deletes the sandbox.
Configure sandboxed application reviewpnpm install --frozen-lockfilepnpm dev3000/healthzAPI_URL SESSION_TOKEN ••••••9f3c2a1Each example is a concern or a requirement, and the verdict Baz returns instead of a guess.
Proposed The survey flags a missing null check on a new parameter.
Verified Every caller passes a validated value. The concern is refuted and never posts.
Proposed A response field is renamed in a shared API.
Verified The verifier finds a consumer in another repository still reading the old name, and confirms it with the file and line.
Proposed A style concern your reviewers rejected last month.
Verified Skipped during the survey, because a memory says the team chose this pattern.
Proposed The ticket asks for export to CSV and PDF.
Verified Partially met: CSV is wired, PDF is not. The verdict points to the lines.
Proposed The Figma frame shows the primary action on the right.
Verified The browser screenshot shows it on the left. Not met, with the annotated screenshot attached.
Proposed The empty state should appear for new workspaces.
Verified Checked in the running app with a fresh account, or marked unverified when no environment is available.
Verification is a stack. Baz takes the layers a test runner or a prover cannot, and leaves the rest where it already works.
| Where it runs | What Baz does | |
|---|---|---|
| Unit and integration testsMerge Automation | Your CI | Weighs CI results in the merge verdict; review agents do not run your suite |
| Fuzzing and property tests | Your CI, with cargo-fuzz, libFuzzer, proptest, and similar | Recognizes the fuzz and property tooling a repository already uses |
| Formal verification | Your toolchain: TLA+, Coq, Lean, Dafny, Kani | Recognizes the formal tooling a repository already uses; Baz does not run proofs |
| Bug claims from AI reviewReview accuracy | Usually posted as generated | Surveyed, then confirmed or refuted by a separate verifier with evidence |
| Speculative findings | Posted with a hedge | Dropped unless the trigger is shown to be reachable |
| Requirements from the ticketSpec review | A human reads the ticket next to the diff | A verdict per requirement: met, partially met, not met, or unverified |
| UI against the designApplication review | Manual QA on a preview | Opens the app in a browser and compares it with Figma, with annotated screenshots |
Keep your tests, fuzzers, and provers. Baz verifies the change against intent and the running app.
No. Those stay in CI. Baz recognizes the tooling a repository uses and verifies what it cannot cover: intent, reachability, and the UI.
A ticketing integration. Add Figma for visual checks, and a sandbox or preview environment to open the running app.
The requirement could not be checked from the code or the app available. Baz says so instead of guessing.
Yes. The session records what ran and what each agent read.
Connect a repository and a ticketing integration, and see verified findings and requirement verdicts on your next PR. Want UI checks in a sandbox? Talk to us.