For Learning Chronicles' Brain Mosaic project, Kydos built an admin platform that lets the team author, test and serve AI-driven NPC scenarios for a children's social-skills app without embedding scenario logic directly inside the game.
The product team needed to edit scenes, objectives, characters and scoring rules, test them against the real AI and make the resulting behaviour available to Unity through a stable API.
Kydos handled the authoring/testing layer, Azure AI integration, production APIs, safety logic and deployment workflow.
The dashboard lets authorised users create and edit the scene setup, objective, NPC behaviour and scoring configuration that define each conversation.
Author the setup, objective, character and exchange rules that make up a scenario.
Run a scenario against the real AI and see the score and NPC reply before it is used in the game.
Expose scenario data and evaluation through REST endpoints that Unity can call during gameplay.
Speech-to-text and text-to-speech stay on the Unity side. The dashboard handles the scenario rules, AI evaluation, score and written NPC response.
The player responds aloud inside the game.
The transcribed response is sent to the dashboard evaluate endpoint with the scenario ID.
Scenario rules and Azure AI evaluate the response and create the NPC reply.
The scored reply returns to the game, where Unity handles text-to-speech.
A response only becomes shippable if it passes all configured checks. Otherwise the system uses a safe fallback.
Scenario-specific prohibited language is blocked.
Swearing is rejected.
Replies are kept suitable for a young child.
Language is checked for age suitability.
Medical or therapeutic claims are prevented.
The reply must stay aligned with the scene and objective.
The delivered project documents the dashboard reading from the cloud database, two Unity endpoints verified from external machines, real Azure AI evaluation in production, a login gate for the authoring dashboard and in-app guidance across the editor.