| What it does | The night watch for apps built with AI that tests checkout on every preview, watches live apps and payments, and identifies the deploy behind a break
| Take your AI support bot from 4/10 to 10/10
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | IN
| Not given
|
|---|
| Pricing model | Freemium
| Free trial
|
|---|
| Pricing | Watch: Free (1 app, 1 journey read-only on production daily, security checks, 1 uptime monitor). Guard: $19/month (5 journeys on every preview and production deploy, business pulse, 20 auto-fixes a month, 10 monitors). Guard + Calls: $49/month (everything in Guard plus 10 journeys per app, Corvis ca
| Free during beta. After beta: $29/month (your own AI keys, unlimited runs) or $59/month (AI included, 50 runs/month).
|
|---|
| Key features | - Journey testing on preview deployments in real browser
- Security checks on every push
- Uptime monitoring
- Leaked key detection and rotation help
- Screenshot and fix brief for failing steps
- Telegram alerts with voice briefings
- Export journeys as Playwright tests
- Supabase row-level security check and auto-fix
| - Bot Score: rates bot performance across five dimensions (rules, facts, solutions, tone, trick resistance)
- Break my bot: 15 adversarial customer scenarios test for vulnerabilities
- Fix it for me: automatically rewrites rule sheet and tests against saved situations
- Train my bot: 30-minute automated training on weak spots with test validation
- GitHub integration: sends improvements as pull requests for engineer approval
- Real chat analysis: identifies problems in actual customer conversations with privacy masking
- Knowledge check: validates bot replies against FAQ and policy documents
- AI comparison: test bot performance across Claude, ChatGPT, and Gemini with costs and speed
- Open source engine: public GitHub implementation of scoring and testing algorithms
|
|---|
| What makes it different | - Tests real customer journeys in a real browser on every preview, not AI-generated tests grading their own work
- Learns your app's normal payment and signup patterns to detect drops when they occur
- Works across Vercel, Supabase and Stripe together for full app visibility
- Calls you on critical issues like stopped payments instead of just sending alerts
| - Nothing ships without engineer approval: all changes go through GitHub pull request review
- Privacy by default: customer data anonymized, keys encrypted, uploads not stored
- Open source testing engine: full algorithm transparency available on GitHub
- Works with your existing AI: supports Claude, ChatGPT, and Gemini with user's own keys
- Unified team experience: one plan covers support, product, and engineering roles
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 0 |
|---|
| Citation Flow (Majestic) | 0 | 0 |
|---|
| Referring domains (Majestic) | 0 | 0 |
|---|
Corvis
Rulebook