| What it does | AI-powered autonomous QA platform for web, iOS and Android testing
| Citations, built for AI agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | 2023
| Not given
|
|---|
| Based in | CH
| Not given
|
|---|
| Pricing model | Contact for pricing
| Freemium
|
|---|
| Pricing | Not given
| Free tier for small requests with no API key required; 10 million free tokens to start; $1 per million tokens for pay-as-you-go, with discounts available at volume or with annual commitments; failed requests are never charged.
|
|---|
| Key features | - Multi-agent AI system that plans, verifies, builds, and self-heals tests
- Natural language test creation from plain English instructions
- Automatic test discovery from URLs, PRDs, Jira tickets, and Figma links
- Self-healing tests that repair when UI changes
- Test organization with hierarchical folders and test suites
- Flexible execution: on-demand, scheduled, and CI/CD-triggered
- Parallel execution across browsers and viewports
- Test results delivered to Slack, Teams, or email
- Test data management with variables, secrets, and assets
| - Token-level attribution with confidence scores
- Works with any AI model without access to weights or internals
- Processes documents up to 1 million tokens
- Returns results in under 2 seconds for 20,000-token documents
- On-premise and air-gapped deployment options
- PDF support with character-level mapping
- Supports 23+ languages including Indian languages
- Chrome browser extension for page and PDF tracing
- Raw token-by-token heatmaps available via API
- No data logging or training on request content
|
|---|
| What makes it different | - Tests are created and maintained without code, from plain English descriptions
- Self-healing tests automatically adapt to UI changes without manual rewrites
- Multi-agent system with automatic test planning, generation, verification, and execution
| - Measures attention directly from the model's computation rather than asking the model to cite itself, providing verifiable attribution
- Achieves frontier-grade citation quality at 7x lower cost and 5-6x faster than alternatives
- Never confused by duplicate facts—identifies the exact occurrence the answer used even when values appear multiple times
- Lands on exact tokens down to character level, not just document chunks
- Works on any model's output post-generation without modifying inference pipeline
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 26 ● no change since last check | 2 ● no change since last check |
|---|
| Trust Flow (Majestic) | 8 | 3 |
|---|
| Citation Flow (Majestic) | 31 | 16 |
|---|
| Referring domains (Majestic) | 73 | 36 |
|---|
Klarent
TokenPath