Pick the job. We’ll show you the worker.
Each capability is one job your app can hand to a worker, and it returns a structured result your app can use. One has a working demonstration of how installing works — it has not been measured and we do not sell it as an agent. The rest are honestly marked as coming next — no fake buttons.
“Can an AI add points, levels, streaks, quests and badges without making my app childish?”
Gamification Builder
Describe what users do in your app. Get the game loop, rules, events, data shape and UI-ready copy.
- — Events and point rules
- — Levels, streaks, quests, badges
- — Data objects and UI copy
Grouped by the job each one does. None of these is installable yet, and none of them is measured.
Games
“Can an AI turn my app into an adaptive challenge or riddle game?”
Challenge Designer
Difficulty curves and puzzle sets that adjust to how a user is actually doing.
- — Challenge ladder
- — Difficulty rules
- — Hint and failure handling
Personalization
“Can an AI add safe characters that react to each user?”
Character Builder
A cast with fixed boundaries, so a friendly guide never drifts somewhere it shouldn’t.
- — Character sheets
- — Reaction rules
- — Boundary and refusal rules
“Can an AI design onboarding that changes based on what a user does?”
Adaptive Onboarding
A first-run path that branches on real signals instead of a fixed five-step tour.
- — Branch conditions
- — Step content
- — Drop-off recovery
Evaluation
“Can an AI score user-created work consistently?”
Submission Scoring
A rubric that gives the same answer twice, with the reasoning attached.
- — Rubric and bands
- — Score payload
- — Disagreement handling
Safety
“Can an AI check my app’s copy and rules for harm before users see them?”
Safety Review
A review pass over the mechanics and words your users will actually meet.
- — Flagged rules
- — Rewritten copy
- — Reasons for each flag
Feedback
“Can an AI turn the feedback my users send into something I can act on?”
Feedback
Turn your feedback button into a weekly list of what to fix
- — Category and severity
- — The screen it is about
- — A one-line summary
Audio
Audio is one governed family, not a pile of separate experiments. Every part of an audio job is fixed by the installation and owned by a server: which character speaks, which narrator reads, which cue keys exist, what a microphone may be used for, how long an asset is kept and what rights it was cleared under. An app never picks a voice, never sends words for a machine to compose against, and never holds a credential. They are grouped by wave below because they arrive in that order, not all at once.
Wave 1 — being built now
The bounded jobs whose input is already owned by a server: an approved reply, a fixed cue key, a saved summary.
“Can my app speak an approved reply in a consistent character voice?”
Character Voice
Renders a persisted character reply as private audio. The character is fixed by the installation: no arbitrary voice selection, no voice cloning, and no provider to name in your app.
- — Speech render
- — Short-lived playback authorization
“Can my app play a consistent sound when something happens in the game?”
Game Sound Cues
A fixed cue pack your app can play back: success, near miss, unlock, warning and reveal. The cue keys and the way each one is made are owned by the server, not by a prompt from the browser.
- — Fixed cue pack
- — Cue key allowlist
- — Private playback authorization
“Can my app read back the summary instead of making someone read it?”
Voice Briefing
Turns a summary or decision brief your app already saved into a private spoken recap, with one fixed narrator.
- — Spoken recap
- — Fixed narrator
- — Short-lived playback authorization
Wave 2 — next
Each one needs wave 1 first: an authorized capture, an asynchronous render, or an existing render to align against.
“Can someone speak their answer instead of typing it?”
Speak to Play
Short microphone input becomes text your existing gameplay already understands. The audio is not kept by default, and your game rules stay in charge of what the text means.
- — Transcribed text
- — Server-authorized capture
- — No audio retention by default
“Can my app turn an approved script into a scene with more than one speaker?”
Scene Dialogue
An approved, bounded multi-speaker script becomes a cinematic dialogue render. It is produced asynchronously and it is not an open-ended live agent.
- — Multi-speaker render
- — Bounded approved script
- — Private playback authorization
“Can my app highlight the words as they are spoken?”
Audio Timing
Aligns an approved script with the audio your app already rendered and returns the timing map behind word highlighting and captions. Timings only: nothing about how the audio was made comes back.
- — Word and phrase timing map
- — Caption-ready segments
Wave 3 — experimental
Each carries an open rights, cost or safety question, and none of them ships without its own written gate.
“Can my app have a short music bed that matches the mission?”
Adaptive Score
A short, server-owned music bed generated from a fixed mood key and cached as one asset. The browser never sends words to compose against, and nothing starts playing on its own.
- — Short music bed
- — Fixed mood-key allowlist
- — Cached private asset
“Can my app reach people who do not read English?”
Localization Dub
Translates an approved audio or video asset into a chosen set of supported languages. The job runs asynchronously and the installing app attests, per asset, that it holds the rights.
- — Translated asset
- — Language selection
- — Recorded rights attestation
“Can an authorized adult perform a character instead of typing it?”
Creator Performance
An authorized adult creator records their own delivery and it is transformed into a rights-cleared designed character. There is no arbitrary target voice and this is never offered to learners.
- — Transformed performance
- — Rights-cleared designed character
- — Operator-only access
“Can my app hold a spoken back-and-forth that can be interrupted?”
Live Voice Engine
Experimental. A governed spoken agent with turn taking and interruption, wrapped around a model you bring. It is bounded by a purpose and a time limit, and it is explicitly not a persistent companion for a child.
- — Turn-taking session
- — Bounded purpose and time limit
- — Full session audit
Where these are aimed
Direction, not delivery. The catalog above is the only statement of what exists.
- Mentor
- Character replies, fixed reward, near-miss and reveal cues, spoken answers, multi-speaker scenes, synchronized captions, multilingual dialogue and short mission mood beds.
- Mission Control
- Click-to-hear briefing, decision and outcome cues, an adult voice note to update a record, multilingual briefing, a synchronized transcript and an optional radio mode.
- Adapter Hub
- The installation itself: rights and retention policy, fixed allowlists, usage you can see, revocation and an audit trail.
Coming-next capabilities have no sign-up and no waitlist yet. They are here so you can see the direction, not to collect your email.
Read the measurement before you rely on it.
Our published reference check covers an earlier agent — banking request routing — and shows the method: trial tasks, a declared standard, and the misses printed next to the passes. Gamification Builder’s own check is not published yet.