AI answering machine detection for ViciDial and outbound dialers that keeps 10–20% more live prospects
Stage
Established
Not given
Founded
Not given
2022
Based in
DE
US
Pricing model
Freemium
Not given
Pricing
Not given
Sandbox: Free with 50,000 detections/month, no card required. Starter: $79/month with 500,000 detections included, $0.00025 per detection over included. Growth: $299/month with 5,000,000 detections included, $0.00015 per detection over included. Scale: $999/month with 25,000,000 detections included,
Key features
Hierarchical traces capture every LLM call, tool invocation, and retrieval step
LLM-as-a-judge, heuristic functions, or human review evaluations
Prompt management with one-click deployments and rollbacks
Playground to test prompts on real production inputs and compare models
Experiments with test cases and side-by-side comparison
Human annotation and collaborative human-in-the-loop workflows
Cost and latency monitoring with dashboards and alerts
REST APIs and Query SDK for data access
Langfuse Assistant to automate the AI engineering loop
99% accuracy answering machine detection
Sub-200 millisecond response time
Real-time dashboard with carrier analytics
Detects carrier false-answer supervision (FAS)
Compliance audit logging for TCPA and HIPAA
WebSocket API for all dialers
Unlimited ViciDial servers with no per-server fees
Open-source SDKs for TypeScript, Python, C#, Ruby, and Rust
GDPR-ready compliance exports on Scale plan
What makes it different
MIT licensed open source platform with no data lock-in
Enterprise scale architecture handling billions of monthly events
Works with any language and framework with no framework lock-in
Async by default so tracing never blocks your application
Eliminates ghost calls and dead air from false positives
Works with any carrier and SIP trunk without switching providers
AMDY.IO