Case Study Deskcasestudydesk.com
TechnologySourced

Case Study: Thryv turns directory assistance into a 24/7 channel with Synthflow Voice AI

Thryv Case StudySourced & dated by Case Study Desk
Key facts · TL;DR
Company
Thryv
Industry
Technology
Challenge
Directory assistance ran only in business hours, leaving after-hours demand unserved.
Headline result
Thryv put a Synthflow Voice AI agent into production in about a month, now handling 20,000+ directory-assistance calls monthly with a 100% answer rate.

Key results

20K+
Calls per month handled by AI
directory assistance, production-level volume
100%
Call answer rate
including after-hours and concurrent demand
+4.4%
More calls answered
previously lost after-hours demand captured
~1 month
To production
from initial development to live deployment

The challenge

Thryv (NASDAQ: THRY), which powers marketing and operations for more than 100,000 small businesses, ran its directory assistance service with human agents within standard business hours. Extending to 24/7 was not economically viable with traditional staffing at existing volumes, so after-hours calls went unanswered and demand was untapped.

The solution

After evaluating multiple vendors, Thryv selected Synthflow for platform capability, predictable cost, and speed to production, deploying a Voice AI agent on a deterministic New Zealand directory-assistance workflow. The agent retrieves and delivers information in real time via API integrations and escalates complex requests to human agents, while Thryv's own engineers built and iterated without specialized telephony expertise.

It's a game-changing platform for us. Within a month we were in production - and what started as an efficiency play turned into a revenue opportunity. Synthflow is a genuine strategic partner going forward.

RH
Rob Hayden
Global Manager, AI Innovation, Thryv

The results, in context

Thryv reported that the AI agent handles over 20,000 directory-assistance calls monthly at production-level volume with a 100% call answer rate, including after-hours and concurrent demand. Previously unanswered after-hours calls translated to 4.4% more calls answered, and the system went from development to live deployment in about one month.

Products used

Synthflow Synthflow Voice AI