Product Concept · Duolingo

Duolingo City

A city that remembers you back.

A product concept exploring what happens when language practice stops resetting every time you close the app. Designed end-to-end, competitive research through prototype and metrics, the way I'd bring it into a roadmap review.

Role
Product Strategist · Concept & UX
Timeline
Self-directed · 2026
Platform
Mobile · Feature Concept
See the concept → How I'd measure it
"I'd pass every exercise in a unit and still freeze the one time I needed to order a coffee for real."
Where this concept started
3 / 42
languages Duolingo's Adventures feature actually supports as of its most recent public update
Duolingo Wiki, 2025
56.5M
daily active users this concept is designed to deepen engagement for, not chase growth from
Duolingo Q1 2026 shareholder letter
5M+
users hold a Duolingo streak of a year or longer, proof the habit mechanic already works. The question this project asks: can a relationship be as sticky as a streak?
Duolingo engineering blog, 2025
Why I started here

I went looking for a gap. Duolingo already knew about it.

I'm a longtime Duolingo user, and the thing that's never quite worked for me is the gap between finishing a lesson and actually being able to say something out loud in French. I'd pass every exercise in a unit and still freeze the one time I needed to order a coffee for real.

So I went looking for whether Duolingo had already noticed this. They had. Adventures, shipped in 2024, drops you into a Duolingo character's shoes to complete one scenario per course unit. Speaking Adventures, rolling out through 2026, pushes the same idea into voice. Both are genuinely good. Both are also, by design, disposable. You finish the scenario, and it's gone. There's no record you were ever there.

That disposability shows up directly in how people talk about the app. Two complaints come up again and again in reviews and analyst breakdowns: recognition isn't production, picking the right answer out of a list is a different skill than generating language under pressure. And the same few scenarios repeat, with nothing changing if you play them again.

65%
of college language learners report high anxiety specifically around speaking, the highest of any of the four language skills measured.
PMC, foreign language classroom anxiety study
FLSA
Foreign Language Speaking Anxiety is a documented, named phenomenon, distinct from general anxiety. The research points to a specific fix: repeated, contextualized practice that feels like spontaneous real use, not graded drills.
The gap

Two complaints. One narrower question.

I stopped asking "what's a fun new scenario" and started asking: what if the place itself remembered you?

①
Recognition, not production
Picking the right answer out of a list is one skill. Generating language on your own, under pressure, is a completely different one, and it's the one Duolingo doesn't really train, even at the highest paid tier.
②
The same few scenarios, over and over
Adventures is one mini-game per unit, in a handful of course pairings, and nothing changes if you play it again. There's no sense of progression within a scenario, only across units.
"What if the place itself remembered you?"

There's a real psychological reason this matters, not just a UX one. Foreign Language Speaking Anxiety research points to a specific fix: repeated, contextualized practice that feels like spontaneous real use. That's what actually lowers the fear of speaking, not more vocabulary.

The concept

A persistent world where the people remember you.

Duolingo City is a persistent world, living in its own tab, where the locations you've practiced in stay open, and the people in them remember you. Go to the café once. Come back next week, and the barista's first line isn't generic. It references how long it's been since you last came by, pitched to how you've actually been performing in conversation, not just which grammar unit you checked off.

It's not a new character system, a new economy, or a new social feature layered on top of Duolingo. It's the smallest version of "a city that remembers you" I could design that's still honest, buildable, and worth trusting with someone's data.

Design principle
Keep coming back, and the relationship visibly warms, not because you unlocked anything, but because that's what a recurring relationship with someone actually feels like.
🧍
Using the avatar Duolingo already built
Duolingo's custom avatar system, launched in 2023, replaced photo uploads outright. The feedback since has had two threads: people upset they lost their old photo, and people asking the avatar to actually do something beyond sit on a profile page. I didn't want to design a second character creator. I wanted to give the one that already exists a job. Your avatar walks into the café. That answers a request that's been sitting in Duolingo's own feedback for two years.
Walking through it

Three moments, not a flow. The whole concept lives in the second.

First visit
A true first meeting
From the City tab, the map shows one open location, the café, everything else previewed but locked. A short intro, a vocabulary warm-up, a conversation. The barista's greeting is written as a true first meeting.
"I don't think I've seen you here before."
Coming back, days later
The moment everything else is designed around
You reopen the café, not because a new mission is waiting, but for the same reason you'd swing by a coffee shop you liked once. The barista's opening line reflects time elapsed and how you've actually done in past conversations. Nothing is unlocked or rewarded. It just feels remembered.
Settling into a routine
From checklist to relationships
Once two or three locations are active, the city stops being a checklist and starts being a short list of people you have some history with. The pull to return stops depending on new content and starts depending on the relationships themselves.
What I cut here
A "Friend tier" that unlocks content or cosmetics as the relationship deepens. The moment warmth is tied to a reward, it becomes a second streak counter, and Duolingo's existing streak-loss notifications are already criticized by users as guilt-driven. I wanted City to feel like being recognized, not like managing one more meter. The relationship is observable, never transactional. The barista being friendlier isn't a reward. It's just flavor.
What it remembers, and what it deliberately doesn't

A constraint, not a feature list.

This ended up being the most important design decision in the whole concept.

It remembers
  • How many times you've visited
  • How long since your last visit
  • Your usual order
  • A rolling sense of how well you've performed in past conversations there
It doesn't remember
  • Anything personal you shared in dialogue, your job, your relationships, anything biographical
  • Anything that carries between locations
  • Anything stored as a fact about you, only facts about your visits
Why I cut personal memory
Duolingo's user base includes a lot of minors, and a system that stores and recalls biographical details a kid shared is a fundamentally different product than one that tracks visit timing and a coffee order. Capping memory at functional facts means I never have to design a separate, more careful version of this for younger users, there's nothing sensitive being kept in the first place.
The second problem it removes
A system that remembers "you said you were a student" eventually has to handle you contradicting yourself, and that needs careful, non-accusatory tone work to avoid feeling like a gotcha. A system that only remembers your usual order never runs into that. I think of it as the difference between an NPC with a personality and an NPC with a notebook. I designed the notebook.
How the memory actually works

Less exciting than "an AI that remembers you."

And that's on purpose. It's a structured profile per person, per location, that selects from a small bank of pre-written dialogue variants, not a model generating a fresh conversation from scratch every time.

Each location's dialogue is written as a handful of variants, chosen by simple rules: first visit or returning, short gap or long gap, strong or shaky recent performance. It's the same authoring model Duolingo already uses for branching exercises, it scales with writing time, not inference cost, and every line gets reviewed before it ships.

Where I drew the line
A freely generated, LLM-voiced conversation, grounded in someone's full history, is a real and exciting next step. It's just not what I'd build first. Rule-based memory is the version that proves whether being remembered actually changes behavior, before spending the much bigger engineering and trust budget it would take to do that live.
// Location memory profile
// per user, per location

visit_count
time_since_last_visit
usual_order // set after first visit
rolling_first_try_success_rate
Interactive prototype

Try the concept yourself.

This is a working prototype of Duolingo City. Open the café, metro, or market — each NPC remembers your visit history and adjusts their opening line accordingly. The results screen shows your confidence score and how many responses you gave without using the hint.

Click any unlocked location on the map · Use the hint button to see the translation

What's actually in v1

Three locations. Not six.

Duolingo City as its own tab. Café, métro, market. The existing avatar walking into each scene. A location memory profile per user, per location. Dialogue variants for first-visit, returning-soon, and returning-after-a-gap, adjusted for recent performance. A results screen that shows a confidence score alongside something more honest than accuracy: how many responses you actually produced yourself, without a hint.

Why three locations, not six: Each location needs roughly three visit-recency variants crossed with two performance bands, around six authored dialogue branches before vocabulary or skill differences are even layered in. Three is enough to find out whether persistent memory changes behavior, without committing to a content cost that scales linearly every time a new location gets added.
In scope
  • Duolingo City as its own tab
  • Three locations: café, métro, market
  • Existing avatar system, given a job
  • Location memory profile per user, per location
  • Dialogue variants for first-visit, returning-soon, returning-after-a-gap
  • Results screen showing confidence score and unaided response rate
What I cut, and why
A new avatar system — Duolingo already has one, with real demand for it to be used more.
Relationship tiers that unlock anything — the single biggest risk of turning this into a grind.
Personal memory — not worth the privacy exposure for a feature whose value doesn't depend on it.
Cross-location memory — charming, but compounds the same privacy question for a payoff that isn't the actual bet.
Freeform generated dialogue — the real future version of this, and the wrong place to spend trust and engineering budget before the simpler version proves itself.
How I'd know if it worked

Narrower than "do people come back."

🎯
North star metric
Whether people return to a location that has nothing left to unlock.
Measured by comparing return visits to maxed-out locations against a stateless control, where the same location resets to a generic first-visit script every time. If memory doesn't outperform the stateless version here, the core idea didn't hold, and no amount of polish elsewhere should save it.
Activation
How many people finish a first mission once they open the City tab at all.
Return behavior
Weekly return visits to a location someone's already completed.
Skill curve health
Whether first-try success holds steady on return visits instead of getting harder. A worse adaptive curve on returns would be a real failure, not a feature.
Habit compatibility
Whether City users keep up with the regular lesson path at the same rate as everyone else. This needs to add to the habit, not compete with it.
Conditions that would make me kill it
  • Maxed-location return rate doesn't meaningfully beat the stateless control after a real test window
  • Dialogue-authoring time per location comes in too high to ever scale past three
  • First-try success drops on return visits instead of holding or improving
What I'd tell myself if I were reviewing this as a PM

Which parts of "clever" were load-bearing.

The first version of this concept was bigger: six locations, a full character creator, relationship tiers with real rewards, NPCs that remembered everything you told them. It was also a worse idea, even though it looked more impressive on a slide.

Every cut I made came from the same question: does this make the city feel more alive, or does it just make the feature bigger?

Cutting personal memory wasn't really about privacy law. It was about realizing the version of this that knows your job and your relationship history isn't actually a better product, it's a creepier one wearing a better product's clothes. The smaller, plainer version, an NPC that remembers your coffee order and notices you've been gone a while, does the entire emotional job on its own.

That's the thing I'd want a senior PM to walk away with. Not that I designed a clever memory system. That I knew which parts of "clever" were actually load-bearing, and cut the rest.