Workflow · workflow
Duolingo Roleplay: multi-prompt LLM orchestration for personalized language practice
A naive single prompt telling an LLM to practice a language with a learner does not produce a targeted, level-appropriate, or structurally satisfying learning experience.
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 · Learner starts Roleplay session
The learner begins a back-and-forth conversation with a Duolingo world character in a Roleplay session.
Tools used
LLMs
Outcome
Duolingo's Roleplay feature uses a multi-prompt LLM architecture to deliver targeted, CEFR-aligned, character-consistent language practice that dynamically adapts to whatever the learner says.
Grounding & classification
Source type: technical build writeup
14 fields verified against source quotes.
content generationconversational aipersonalizationchat transcriptbuilder submittednamed customertools describedworkflow describededucationcustomer satisfactiontechnical build writeupagentic task execution