How Duolingo's English Test team automated chat support with Decagon
The Duolingo English Test support team replaced its previous AI vendor with Decagon to handle live chat inquiries. According to Decagon's customer story, the agent went live within a month and resolved most chats without human involvement.
The problem
The Duolingo English Test serves test-takers who often need results quickly for academic deadlines, so support has to be fast and accurate. The earlier AI vendor deflected some email tickets but was still not ready for live chat after a year, leaving agents to handle chat volume by hand. Updating FAQ articles also required manual refreshes in the vendor's backend, with no bulk update option.
How they did it
- Duolingo started talks with Decagon in August.
- Decagon was live and handling chat inquiries about one month later.
- FAQ content is synced automatically every hour instead of being refreshed by hand.
- The team uses Decagon's backend tools to add content snippets and QA responses.
- The team is building a scalable QA process to keep answers consistent and accurate.
Results
- As reported by Decagon: 80% chat deflection from the start, with a majority of chat inquiries fully resolved.
- As reported by Decagon: the previous vendor deflected about 30% of email tickets and still could not support live chat after a year.
- The Senior Operations Manager said that, with the previous vendor, at least half of his week went to maintaining the system, and that Decagon made a night-and-day difference.
- Agents now focus on more complex inquiries; email support and playbooks are planned as next steps.
As reported by the source (Decagon customer story); AgentGid did not measure these figures.
This suits a support team with steady chat volume, an existing FAQ library and someone to own QA, since Duolingo still reviews answers and adds snippets itself. Decagon has no public pricing and requires a sales conversation, and the 80% deflection is Decagon's own figure. If you want to start cheaper, Chatwoot Captain (Free + $19/mo) can be self-hosted.
The agent used here
Similar use cases
How Chime scaled chat and voice member support with Decagon
Chime, a US fintech, picked Decagon to automate member support on both chat and voice after comparing several vendors. The company reports high resolution rates, lower support cos…
As reported by Decagon: 70% chat and voice resolution, a 30 sNPS, and a 60% decrease in customer support costs.
How 1-800-Flowers.com improved customer care CSAT with Decagon chat and voice agents
1-800-Flowers.com ran a live proof-of-value pilot of Decagon against another finalist and selected it to automate customer care across chat and voice. The pilot closed with CSAT n…
As reported by Decagon, the pilot closed with CSAT nearing 93%, double-digit points higher than previous automation.
How Faire used Decagon AI to scale customer support and cut operational drag
Faire, a wholesale marketplace connecting brands and retailers, worked with Decagon to automate repetitive support contacts and give its team better AI knowledge tools. The vendor…
As reported by Decagon, support became more efficient and operational costs fell, with savings reinvested in customer experience.