Valon, a mortgage servicer, uses Decagon voice AI on inbound calls. Decagon reports 50%+ voice deflection even while onboarding 80,000 loans in a month, CSAT around 90%, and average speed to answer under one minute.
Reported outcomes
Outcomes are reported exactly as stated by the source; we have not independently audited them.
How it works
- Decagon AI agent answers inbound customer conversations.
- Escalates to human agents when needed.
Risks & compliance
- Incorrect answers to customers; escalation paths needed
- Vendor-published results; not independently audited
- Regulated mortgage servicing disclosures
Tools mentioned & how to build it
Disclosure: Some links may earn us a commission; it never affects grades. Tools are listed by fit to this case, never by payment.
Tools mentioned
- Decagon (Decagon)
AI customer-support agents for chat, email and voice.
Build a version yourself
- Retell AI
Build and deploy phone agents for scheduling, intake and call routing. - ElevenLabs
Voice models and a conversational-agent platform behind many voice agents. - n8n
Open-source workflow automation with AI agent nodes; self-host or cloud.
Sources
“Achieved 50%+ deflection on voice for inbound calls, even when onboarding 80,000 loans in a single month.”Valon and Decagon
Grade rationale: Named organization with a quantified outcome from the vendor or the organization itself (self-reported). Automated check on Oct 17, 2026: 1/1 quotes and 2/2 outcome claims matched the source. Compiled by the Agent Casefile research desk (AI-assisted; see methodology). Spot an error? Request a correction.
