back_office_ops · saas · workflow
Duolingo achieves 5x ROI, saving 500+ hours monthly with Glean's AI-powered knowledge tools
Duolingo employees wasted time hunting for information scattered across Google Drive, Slack, Confluence, and Zendesk, and frequently had to ask colleagues or redo work that already existed elsewhere. An internally built search tool called Metasearch failed to solve it because it lacked advanced filtering and ranking.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Employee seeks knowledge
Duolingo employees need to find knowledge, documents, or past discussions to do their work.
Tools used
GleanGlean Chat
Outcome
With Glean, Duolingo saves 500+ hours every month — worth more than $1.1 million in yearly time savings — delivering a 5x return on investment from improved knowledge access. Over 3,400 Glean agents were created in total.
What failed first
Duolingo's internally built Metasearch tool lacked advanced filtering and ranking and could not deliver fast, reliable results, leaving teams still spending too much time searching.
Results
Time saved5x
Volume500
Cost replaced>$1.1M
Grounding & classification
Source type: vendor customer story
25 fields verified against source quotes.
ai agentconversational aienterprise searchknowledge searchknowledge basefailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwarecost reductionemployee productivitytime savedvendor customer storyback office opsrag answering