Find bugs before
your users do.

Vera, an AI QA engineer, explores your product like a real user — and her 6-stage pipeline reports only verified bugs.

No account required · No credit card · Takes about 30 seconds

View pricing →Read the docs →
2,847
Bugs found
4.2
Avg per session
<3%
False positives
28s
Time to first bug

Tests anything that runs in a browser

ReactNext.jsVueNuxtSvelteAngularRemixAstroWordPressShopifyWebflowSquarespaceReactNext.jsVueNuxtSvelteAngularRemixAstroWordPressShopifyWebflowSquarespace

Vera does the work. Verdict is the answer.

Everything under Verdict

Four products, one agent — Vera powers every surface of the quality lifecycle.

Vera Explore

Autonomous black-box QA agent

Live

Drop a URL. Vera crawls out page by page — login, checkout, onboarding — like a senior QA engineer, and reports only verified bugs in minutes.

  • Goal-driven browser navigation
  • Explore → Plan → Review → Judge → Verify → Report
  • Supports auth, cookies, OAuth
Verdict CLI

CI/CD quality gate

npm v0.2.0

Run Vera inside any CI pipeline. Fails the build when critical bugs are detected on staging — before code reaches production.

$ verdict explore <url> --fail-on critical
  • GitHub Actions / GitLab CI ready
  • Configurable severity thresholds
Verdict MCP

Editor-native testing

npm v0.2.0

Run Vera directly inside Claude Code or Cursor via MCP. Trigger explorations and check credits without leaving your editor.

.mcp.json → "vera": { "command": "npx -y @verdict-npm/mcp" }
  • Claude Code + Cursor support
  • Tools: vera_explore, vera_status, vera_sessions, vera_balance
Vera SDK

White-box quality signals

Phase 2

Instrument your app with the quality-signal SDK for JS and Python. Vera pairs in-app signals with black-box exploration for deeper coverage.

  • JS / Python SDK
  • <10 min integration

How Vera works

A 6-stage pipeline. Verified bugs only.

Each stage has a distinct role — and you can step in at Review to shape the test plan before Vera judges it.

01

Explore

Vera navigates autonomously

Drop a URL. Vera uses an AI browser agent to explore every flow — login, checkout, onboarding — goal-first, without a script.

02

Plan

Test cases drafted

Vera turns what it discovered into a structured test plan — concrete test cases with expected outcomes.

03

Review

Optional human checkpoint

Edit, add, or drop test cases before judging — or skip the checkpoint and let Vera run end-to-end.

04

Judge

AI QA evaluator decides

A separate QA Judge LLM evaluates whether each anomaly is a real bug or expected behavior. Reduces false positives to <3%.

05

Verify

Reproduced before reported

A Verification Agent reproduces each confirmed bug independently (Starter+). Nothing reaches your report unless it's reproducible.

06

Report

Evidence, steps, severity

A clean report with reproduction steps, screenshots, and severity scores — ready to drop into your tracker.

Platform coverage

If it's software, Vera can test it.

Web is live today. Every other surface is on the roadmap, built on the same pipeline through platform-specific adapters.

Live
Web App
URL-based, browser agent
Roadmap
Mobile iOS
XCUITest + vision
Roadmap
Mobile Android
UiAutomator2 + vision
Roadmap
Desktop
Accessibility API
Roadmap
REST API
OpenAPI / HAR replay
Roadmap
CLI
subprocess + stderr
Roadmap
SmartTV
Remote + vision
Roadmap
Electron
CDP + Playwright

Features

Not another test script.

Vera thinks like a QA engineer — building hypotheses, constructing edge cases, proving bugs are real.

Goal-driven exploration

No scripts. Vera sets goals ("complete checkout") and navigates autonomously — finding paths a human tester would.

6-stage pipeline

Explore → Plan → Review → Judge → Verify → Report. A bug isn't in your report unless separate AI agents agree it's real and reproducible.

Auth-aware testing

Provide credentials, session cookies, API tokens, or OAuth refresh tokens. Vera tests behind your login wall.

Developer MCP server

Use Vera directly inside Claude Code or Cursor via MCP. Run tests without leaving your editor.

Vera SDK

Add white-box quality signals to your app with the JS / Python SDK — deeper coverage than black-box exploration alone. Coming in Phase 2.

CI/CD integration

verdict explore <url> --fail-on critical in any pipeline. Fails the build if critical bugs are found.

Pricing

Simple credit-based pricing

1 credit = 1 browser step = $0.02. Pay for what you actually use — quick runs cost less, deep explorations cost more.

Try Vera solo
$0
Credits100 cr/mo
Top-upSmall top-ups available
  • ✓ Web testing
  • ✓ Basic sessions
  • ✓ Community support
Start free
Solo developer
$19/mo
Credits500 cr/mo
Top-upTop-up available
  • ✓ Web + API testing
  • ✓ Bug verification
  • ✓ Email support
  • + Verification add-on
Get started
Most popular
Growing team
$79/mo
Credits2,000 cr/mo
Top-upTop-up available
  • ✓ Web + API + Mobile
  • ✓ Priority support
  • ✓ Team seats (3)
  • + Verification add-on
  • + Deep explore
Most popular
Scaling company
Custom
Credits10,000+ cr/mo
Top-upVolume bundles
  • ✓ All platforms
  • ✓ SSO / SAML
  • ✓ Dedicated CSM
  • ✓ SLA 99.9%
Contact sales
What is a credit?

1 credit = 1 browser step = $0.02. Vision analysis is included on every step at no extra cost. A minimal session costs ~10 cr; a typical session 30–100 cr.

What are add-ons?

Verification (+20 cr per confirmed bug, max 3 bugs) lets a separate agent reproduce each bug before it reaches your report. Starter+ only. Vision analysis is included — never billed as an add-on.

Can I top up?

Yes. Bundles: 50 cr/$1, 100 cr/$1.90 (Free+) · 250 cr/$4.50, 500 cr/$8 (Starter+) · 1,000 cr/$15, 2,000 cr/$28 (Pro+). Purchased credits never expire.

Enterprise: custom credit volumes, on-premise/VPC deployment, white-glove onboarding. Talk to us →

Start shipping with
certainty today.

No signup required for your first analysis. Paste a URL and Vera starts in seconds.