| What it does | CI/CD testing for AI voice agents that calls your agent and returns pass/fail results
| Independent verification for bug fixes in C, C++ and firmware
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Free
| Not given
|
|---|
| Pricing | 100 free minutes. No credit card required.
| Not given
|
|---|
| Key features | - Real phone calls from real carrier lines for end-to-end validation
- LLM-powered test agent that role-plays as a customer
- Plain English test case descriptions without scripted paths
- Simple two-call REST API integration
- Complete call transcripts in failure notifications for troubleshooting
- LLM as Judge for intelligent pass/fail evaluation
- No SDK or test case repository to manage
| - Reproduces bugs deterministically on base version before applying fix
- Verifies fix removal confirms bug returns
- Scans diffs for masking patterns like disabled sanitizers and weakened tests
- Runs on real hardware via STM32 NUCLEO boards and ST-Link
- Integrates with AI coding agents as MCP tool
- Posts verdicts as GitHub pull request comments
- Provides per-test verdicts: FIXED, BROKEN, FLAKY ON THE BENCH, FLAKY WORSE
- Runs entirely on your machines with no cloud dependency
- Generates reports for change records and regulatory compliance
- Runs builds and tests in Linux container on your machine
|
|---|
| What makes it different | - Real end-to-end validation with actual phone calls covering SIP integration, STT/TTS, and functional behavior
- Intelligent LLM testing that understands intent instead of matching keywords or regex
- Lightweight and unopinionated API design for fast integration
- Complete call transcripts included in test failures for immediate troubleshooting
| - Only verification tool that reverses the fix to prove tests actually catch the bug
- Deterministic verdict with no AI language model in decision logic
- Tests on real hardware boards, not just laptops
- Detects masking techniques that hide bugs while passing tests
- Validated public benchmark showing 4 VERIFIED and 6 REJECTED on real open-source bugs
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 7 ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 3 | 0 |
|---|
| Citation Flow (Majestic) | 22 | 0 |
|---|
| Referring domains (Majestic) | 40 | 0 |
|---|
Unfix