Skip to content
Budget Reallocation: Reduced over-allocated AI costs ($50K→$40K) and infrastructure ($35K→$31K), added tech support specialist ($18K)Personnel Adjustments: Developer salaries optimized to $9K/month each (market-competitive rate)High-End Development Infrastructure: 2 PCs with RTX 5090s and AMD Ryzen 9950X for maximum Unity 6.1 performanceScope Refinement: 3 core modules with 10-12 lessons each (vs 5 modules with 20-30 lessons) - more realistic for 2 developersEnhanced Support: Added dedicated tech support specialist for DevOps, CI/CD, and infrastructure managementTimeline Adjustment: Removed overly aggressive content creation targets, focused on quality over quantityTesting Optimization: 600 beta testers with rotating A/B/C testing vs exclusive provider groupsExact Budget: Precisely allocated to $300K with no contingency needed due to realistic planning </analysis>
Decomposition - Breaking down complex problems into smaller, manageable partsAbstraction - Identifying and focusing on the essential features while ignoring irrelevant detailsAlgorithmic Thinking - Creating step-by-step instructions to solve problemsPattern Recognition - Identifying similarities, trends, and regularities in data
OpenAI GPT-4: Industry leader, best for complex reasoning and creative contentAnthropic Claude: Superior for educational safety, detailed explanations, and ethical responsesxAI Grok: Real-time information access, humor-based engagement, and cost-effective scalingWhich provides the best Computational Thinking education outcomes for preschoolersWhich students prefer for different CT concepts (Decomposition vs Algorithmic Thinking vs Pattern Recognition vs Abstraction)Cost-effectiveness per CT learning milestone achievedResponse speed and reliability for child-appropriate explanationsSafety and appropriateness for preschool age groups (4-7 years)
2 Mid-Level Unity Developers: Full-stack capable, working in parallel ($9K/month each)Tech Support Specialist: DevOps, infrastructure, and technical troubleshooting supportPart-time Content Creator: Reduces bottleneck on core developersNo dedicated lead: Developers alternate weekly sprint leadershipNo consultant: Direct integration with LLM APIs using documentation
Timeline: 4 months to beta launchBudget: $300,000 (optimized allocation)Team: 2 developers + tech support + part-time content supportDeliverable: Multi-LLM beta with 3 core Jules "School of Fish" modules testing all three AI providersFocus: Computational Thinking and Digital Literacy for ages 4-7
Unity 6.1 LTS (version 6000.1)Universal Render Pipeline (URP) optimized for mobileAddressables for dynamic content loadingNew Input System for cross-platform compatibilityTextMeshPro for high-quality educational text rendering
Set up Unity 6.1 LTS project with URPConfigure Git repository with LFSImplement Supabase authentication systemCreate basic UI frameworkSet up Unity AnalyticsIntegrate all three LLM APIs (OpenAI, Claude, Grok)Set up Convex.dev real-time syncCreate AI router/orchestrator systemImplement response caching layerBuild A/B/C testing frameworkSet up CI/CD pipeline with Unity Cloud BuildConfigure monitoring and logging systems (Datadog, Sentry)Implement automated testing infrastructureManage cloud infrastructure provisioningSet up development environment standardsAudit existing curriculum assetsBegin content planning for 3 core modulesCreate content templates and standards✅ All three LLMs responding to test queries✅ Supabase auth working with student accounts✅ Convex real-time sync operational✅ Basic Unity project structure complete✅ Content roadmap for 3 modules defined
✅ 50% of assets migrated and optimized
Jules Games Unity 6 LTS Beta Development
Last edited 154 days ago by Alexander Holmefjord-Sarabi.
Jules Games Unity 6 LTS Beta Development
Multi-LLM Adaptive Learning Platform - OPTIMIZED PLAN
4-Month Beta Program | $300K Budget | 2-Developer Team + Support
<analysis>
Key Optimizations Made:
Executive Summary
Project Vision
We're building an intelligent Jules "School of Fish" Computational Thinking platform that hedges across multiple AI providers (OpenAI, Claude, and Grok) to determine the optimal solution for personalized learning. This beta will serve as a real-world testing ground to identify which AI performs best for teaching Computational Thinking (CT) concepts to preschoolers (ages 4-7) before committing to a primary provider for production.
Jules School of Fish Focus
Building on the award-winning School of Fish curriculum, we're creating an AI-enhanced version that teaches the four core Computational Thinking concepts:
Strategic AI Approach: The Three-Provider Hedge
Instead of betting on a single AI provider, we're implementing all three major LLMs in parallel:
During the beta, we'll A/B/C test these providers to determine:
Optimized Team Structure
Investment Breakdown
Technology Stack: Complete Architecture
Multi-LLM Architecture with Modern Database Stack
┌─────────────────────────────────────────────────────────┐
│ STUDENT INTERFACE │
│ Unity 6.1 LTS Client │
├─────────────────────────────────────────────────────────┤
│ │
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
│ │ Rendering │ │ Learning │ │ AI Router │ │
│ │ Engine │ │ Modules │ │ & Manager │ │
│ │ (URP) │ │ │ │ │ │
│ └──────────────┘ └──────────────┘ └──────────────┘ │
│ │
│ ┌────────────────────────────────────────────────────┐ │
│ │ Intelligent LLM Selection Layer │ │
│ │ (Routes to optimal AI for each task) │ │
│ └────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────┘
↕
┌─────────────────────────────────────────────────────────┐
│ AI PROVIDER LAYER │
├─────────────────────────────────────────────────────────┤
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
│ │ OpenAI │ │ Claude │ │ Grok │ │
│ │ GPT-4 │ │ API │ │ API │ │
│ │ │ │ │ │ │ │
│ └──────────────┘ └──────────────┘ └──────────────┘ │
└─────────────────────────────────────────────────────────┘
↕
┌─────────────────────────────────────────────────────────┐
│ DATABASE & SERVICES │
├─────────────────────────────────────────────────────────┤
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
│ │ Supabase │ │ Convex.dev │ │ Unity │ │
│ │ (Auth + │ │ (Real-time │ │ Analytics │ │
│ │ Storage) │ │ Sync) │ │ │ │
│ └──────────────┘ └──────────────┘ └──────────────┘ │
│ │
│ ┌────────────────────────────────────────────────────┐ │
│ │ Learning Analytics & Progress DB │ │
│ └────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────┘
Core Technology Components
1. Unity 6.1 LTS Foundation
Technical Specifications:
Business Value: Unity's proven stability with 2+ years guaranteed support ensures our educational platform won't need major technical updates during critical school years. Cross-platform deployment from a single codebase saves 40% in development costs.
2. Multi-LLM Integration Strategy
Technical Implementation:
public class MultiLLMOrchestrator
{
private readonly Dictionary<LLMProvider, ILLMService> providers = new()
{
{ LLMProvider.OpenAI, new OpenAIService() },
{ LLMProvider.Claude, new ClaudeService() },
{ LLMProvider.Grok, new GrokService() }
};
public async Task<LLMResponse> GetOptimalResponse(
CTQuery query,
ChildProfile child)
{
// Intelligent routing based on Jules CT concepts:
// - Algorithmic Thinking → GPT-4 (step-by-step reasoning)
// - Pattern Recognition → Claude (detailed explanations)
// - Decomposition → Grok (engaging, playful breakdown)
// - Abstraction → Provider rotation for comparison
// - Cost optimization (Grok for simple concepts)
// - Child's age and learning style
// - Provider availability and response time
var selectedProvider = DetermineOptimalCTProvider(query, child);
return await providers[selectedProvider].GenerateResponse(query);
}
// A/B/C testing framework with Jules CT focus
public async Task<CTComparisonResult> TestAllProviders(CTTestQuery query)
{
var results = await Task.WhenAll(
providers.Select(p => p.Value.GenerateCTResponse(query))
);
return AnalyzeCTResults(results);
}
}
OPTIMIZED Implementation Roadmap
Month 1: Foundation & Multi-LLM Architecture (Weeks 1-4)
Weeks 1-2: Environment Setup & Database Configuration
Developer 1 Focus: Unity & Infrastructure
Developer 2 Focus: AI & Database Integration
Tech Support Specialist Focus:
Part-time Content Creator Focus:
Deliverables:
Weeks 3-4: Asset Migration & AI Training Pipeline
Developer 1 Focus: Asset Pipeline
public class AssetMigrationSystem
{
// Automated asset processing
public async Task MigrateEducationalContent()
{
// 1. Import existing sprites, audio, animations
// 2. Optimize textures for mobile (ASTC compression)
// 3. Generate texture atlases for UI elements
// 4. Process curriculum data into Supabase
// 5. Create Convex schemas for real-time data
}
}
Developer 2 Focus: LLM Optimization
# LLM Response Evaluation System
class LLMEvaluator:
def compare_responses(self, query, responses):
metrics = {
'accuracy': self.evaluate_accuracy(responses),
'appropriateness': self.check_age_appropriate(responses),
'engagement': self.measure_engagement_potential(responses),
'cost': self.calculate_cost_per_response(responses),
'speed': self.measure_response_time(responses)
}
return self.determine_winner(metrics)
Deliverables:
Want to print your doc?
This is not the way.
This is not the way.
Try clicking the ··· in the right corner or using a keyboard shortcut (
CtrlP
) instead.