| What it does | Validate and monitor AI and LLM models for accuracy, robustness, and governance
| On-device moderation that flags hateful, abusive and threatening text in 23 European languages, before the message is sent.
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | IL
| NL
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Not given
| Free up to 100k monthly active devices with unlimited inference. Custom licenses available.
|
|---|
| Key features | - Real-time monitoring and alerts for model mistakes
- Comprehensive validation metrics for stability and accuracy
- Model explainability at global and local levels
- Detection of anomalies and model vulnerabilities
- Bias and fairness analysis
- Governance tools for regulatory compliance
- Automated real-time reporting for stakeholders
- Actionable mitigation steps and risk reduction
- Production monitoring to prevent performance deterioration
- Real-time prediction explanation with error and certainty metrics
| - Three separate scores: hateful, abusive, threat
- Ten target signals under the hate score: race, color, religion, descent, national or ethnic origin, sexual orientation, gender, disability, age, other
- Runs fully on device with no server calls
- Supports 23 European languages from one model file
- 80MB model size optimized for iOS, Android, and browser
- 0.847 macro F1 accuracy on Multilingual HateCheck
- Warn before message is sent
- Comment triage without infrastructure
|
|---|
| What makes it different | - Outperforms international explainability benchmarks like SHAP and LIME
- Unique ability to dive into local samples in real time
- Patent-pending proprietary methodology
- Comprehensive solution covering development and deployment
- 82% faster time to production
| - Multilingual support across 23 European languages in a single 80MB model
- Complete privacy with no data leaving the device
- Free access up to 100k monthly active devices with unlimited inference
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 25 ● no change since last check | 37 ● no change since last check |
|---|
| Trust Flow (Majestic) | 6 | 20 |
|---|
| Citation Flow (Majestic) | 16 | 39 |
|---|
| Referring domains (Majestic) | 77 | 616 |
|---|
Citrusˣ
Toxic