Meadow
Deliverable Review
Incorrect. Try again.
Meadow Portal · M1 Deliverable · Tier 3 Vocabulary

The Sentence Engine

Grammar-aware predictions that help children build sentences faster — and a world that grows with them.
Tier 3 vocabulary paradigm
Sentence predictions · World map expansion
Replaces SCS templates · Offline · Rule-based
May 2026
01 The Problem
Vocabulary at scale

A child who can build sentences needs words — fast.

By Tier 3, a child is constructing 3–4 word sentences. They know what they want to say — “I don’t want the blue one” — but finding each word across a large vocabulary is slow and frustrating.

Proloquo2Go solves this with 200+ folders. But folders are a taxonomy — abstract, hierarchical, hard for young children to navigate. Meadow needs a different answer.

πŸ“
Proloquo2Go
200+ folders
vs.
🌍
Meadow
Scenes + predictions
02 Two Innovations

Meadow’s Tier 3 paradigm

Instead of matching Proloquo2Go folder-for-folder, Meadow delivers rich vocabulary through two innovations that play to its strengths.

Innovation 1

The Sentence Engine

Grammar-aware predictions appear inside the speech bubble as the child builds a sentence. The app understands what kind of word comes next — a verb after a pronoun, a noun after a verb — and surfaces the most likely options. Fewer taps. Faster sentences.

  • Rule-based, fully offline
  • Ranked by scene context + usage
  • Replaces rigid SCS templates
Innovation 2

World Map Expansion

Every vocabulary domain maps to a place on the world map. Animals live at the zoo. Body parts are at the doctor’s office. Clothes are in the bedroom. The map replaces folder hierarchies with spatial memory — children remember where words are.

  • Max 2 taps to any word
  • 15–20 illustrated scene locations
  • 700–1,500+ words V1
03 The Bubble

The speech bubble becomes a sentence builder

At Tier 2–3, the speech bubble does double duty: it shows the words the child has composed and predicts what comes next. One unified surface for sentence construction — works in both scene view and grid view.

Example: Child taps “I” then “want” in the kitchen
πŸ‘€ I
🀲 want
🍌 banana
πŸ₯› milk
πŸ§ƒ juice
πŸ‘ more
πŸ†˜ help
πŸ₯£ cereal
Speak button — tap to say the full sentence Composed words — solid tiles, what the child has built Predictions — dashed tiles, grammar-ranked suggestions

Always optional

Predictions never replace manual word selection. The child can ignore predictions entirely and tap any word on the compass edges, scene, or grid — it gets added to the bubble just the same. Predictions are a shortcut, not a requirement.

04 In Action

How it feels to build a sentence

Four scenarios showing the engine responding to different sentence starters and contexts.

🍽️ Kitchen

“I don’t want…”

Child taps I → don’t → want. Engine predicts nouns because Negation+Verb+Object is the pattern. Kitchen foods surface first.

πŸ‘€I
πŸ™…don’t
🀲want
πŸ₯£cereal
πŸ₯›milk
🍌banana
🦁 Zoo

“big dog!”

Child taps big → engine predicts nouns. In the zoo scene, animals surface first. “Dog” ranks high because this child uses it frequently.

🐘big
πŸ•dog
🦁lion
🐘elephant
πŸ› Bathroom

“no!”

Child taps no. Engine predicts verbs (the child is protesting an action). Bath-context verbs rank first.

🚫no
πŸ›bath
🀲want
πŸ‘like
🚢go
🏠 Living Room

“where mommy?”

Child taps where. Engine predicts nouns and pronouns — the child is asking about a person or thing. Family members rank high.

πŸ—ΊοΈwhere
πŸ‘©mommy
πŸ‘¨daddy
πŸ•dog
⚽ball
05 The Grammar Engine

Rule-based. Offline. No machine learning.

The engine uses the Fitzgerald Key color of each word as its grammar role. A small transition table maps what’s in the bubble to what category of word probably comes next. The entire system runs on-device with zero latency.

After… Predict next Example
Empty bubble Pronoun Verb Noun “I…” “want…” “banana”
Pronoun Verb Descriptor “I want” “mommy happy
Verb Noun Descriptor Function “want banana” “want more” “want to
Noun Descriptor Social Function “banana yummy” “cookie please” “ball and
Negation Verb Noun “don’t want” “no banana
Question Noun Verb Pronoun “what that” “where daddy

Grounded in Brown’s Stages II–IV

These transitions map to the documented sentence patterns for children ages 24–48 months (MLU 2.0–4.0): Agent+Action, Action+Object, Negation+Verb+Object, and early question forms. The transition table will be validated by SLP review before implementation.

06 How Words Are Ranked

Context-aware, personalized, diverse

Once the grammar engine selects a category (e.g. “show nouns”), the ranking system decides which nouns appear. Four layers, highest priority first.

1

Scene context

Words from the current scene location rank highest. In the kitchen, kitchen objects appear first.

2

Usage frequency

Words this child taps often rank next. If “ball” is their most-used noun, it appears even in the kitchen.

3

Recency

Words used in the last few minutes get a boost. Supports ongoing conversation topics.

4

Pragmatic diversity

At least 2 predictions must serve different communication functions — not all requesting. A child who said “I want” also sees commenting and social options.

On-device, privacy-preserving

All ranking data comes from the existing SwiftData event log. No data leaves the device. No cloud processing. No usage analytics transmitted anywhere.

07 Tier 2 vs Tier 3

One system, two intensity levels

The sentence engine scales with the child. Tier 2 gets a gentle version. Tier 3 gets the full experience.

Tier 2 — Word Combinations

Simplified predictions

  • 3–4 predictions shown
  • First word only — no multi-position chaining
  • Scene nouns only — no cross-scene vocabulary
  • Larger tiles (60pt) for developing motor skills
  • Tapping a prediction speaks the full 2-word phrase and clears
Example: child taps “want”
🀲want
🍌banana
πŸ₯›milk
πŸ§ƒjuice
Tier 3 — Sentences

Full predictions

  • 6–8 predictions shown
  • Multi-position — predictions update after each word
  • Full vocabulary — cross-scene, usage-ranked
  • Tighter tiles (50–55pt) for better motor skills
  • Max 5-word composition with scrollable bubble
Example: child taps “I want banana”
πŸ‘€I
🀲want
🍌banana
πŸ™please
⏰now
βž•and
πŸ‘more
08 The World Map

Every vocabulary domain is a place

Instead of folder hierarchies, Meadow organizes vocabulary as locations on a world map. Children remember where things are. The zoo has animals. The doctor’s office has body parts. The bedroom has clothes. Max 2 taps to any word — flat, never nested.

Routine Scenes — Left-edge navigation
🍽️

Kitchen

60–100 words
πŸ›

Bathroom

30–40 words
πŸ›οΈ

Bedroom

40–50 words
🧸

Living Room

40–50 words
World Scenes — Map navigation (Tier 2–3)
🦁

Zoo

40–60 words
πŸ₯

Doctor

30–40 words
πŸ›

Park

30–50 words
πŸ›’

Grocery Store

40–60 words
πŸ‘΅

Grandma’s House

30–40 words
πŸš—

Car Ride

20–30 words
🎨

Art Room

30–40 words
πŸ•

Restaurant

30–40 words
πŸ–οΈ

Beach

25–35 words
🌻

Garden

25–35 words
14
Scene Locations
94+
Core Words (Compass)
700–1,500
Total Vocabulary V1
2
Max Taps to Any Word
09 Custom Words

The child’s dog lives at the zoo

SLPs and parents can add personal vocabulary — pet names, sibling names, favorite shows — directly into the scene where they belong. No separate “personal board.” The child’s dog appears in the zoo scene alongside “dog,” with a photo of their actual pet.

πŸ“Έ

Parent takes a photo

Camera roll or camera. The real dog, not a generic illustration.

πŸ—£οΈ

Apple TTS speaks it

On-device text-to-speech. Instant, offline, no pipeline needed.

🦁

Appears in the right scene

SLP picks the scene. Custom words have a subtle photo-frame border.

Taylor’s popsicle

In Taylor’s testimonial, specificity was the breakthrough — not “frozen treat” but the exact color popsicle she wanted. Custom words enable this kind of specificity without requiring Meadow to pre-build every possibility.

10 What This Isn’t

Clear boundaries

The sentence engine is a communication tool, not a teaching tool.

🚫🤖

Not AI / ML

Simple rule-based grammar transitions. No neural nets, no cloud calls, no black boxes.

🚫📚

Not a lesson

Predictions help children communicate, not learn grammar. No teaching, no correction, no assessment.

🚫🔒

Not mandatory

Every word is still directly tappable on compass edges, scenes, and grids. Predictions are a shortcut, never a gate.

💬

What it is: the fastest path from thought to speech

A child who knows what they want to say should never be slowed down by the interface. The sentence engine anticipates their next word, surfaces it where they’re already looking, and gets out of the way. The child builds the sentence. The engine just reduces the taps.

11 Looking Ahead

The vocabulary platform (V2)

The world map architecture sets up a platform play that no competitor has built.

🔮 Future Vision

SLP-authored vocabulary packs

SLPs create new scene locations with vocabulary, illustrations, and audio. Packs are shareable through a curated library. Installing a pack adds a new location to the child’s world map. Every SLP who creates a pack makes Meadow more useful for every child.

📋 Curated by AbleNet 🌐 Community sharing 🔒 Quality-gated 👤 2,000+ words possible

Competitive gap validated

No AAC app — including Proloquo2Go, TouchChat, TD Snap, or CoughDrop — has an SLP-authored vocabulary pack marketplace. SLPs currently sell custom materials on Teachers Pay Teachers as a workaround. Meadow would be the first app where the scene-based paradigm makes vocabulary packs genuinely rich (not just a grid layout, but an illustrated world with vocabulary, context, and therapy targets).