LEARNOGAUGE V2.0 — AI-POWERED ADAPTIVE LEARNING PLATFORM
LearnoGauge v2.0 is a ground-up rebuild of the LearnoGauge platform, adopting an AI-first architecture designed for global scale. The existing platform, while functional, was constrained by aging infrastructure, limited AI capability, and no real-time personalisation of content or difficulty. The v2.0 rebuild addresses these limitations comprehensively: it delivers a next-generation intelligent learning and assessment platform that personalises learning experiences in real time, automates assessment creation at scale, maps all content to WAEC and JAMB curriculum standards, and provides actionable role-specific analytics for students, teachers, and institutions. The platform follows a Full-Core MVP strategy — meaning all core systems are included at launch, with each system implemented at a controlled depth before advanced features are layered in. H-SETS is the engineering delivery partner across the full system, working alongside the LearnoGauge product team across a 10–12 week build cycle.
+95%
Learning Personalizaion Capacity
100%
AI Integration
Scope of work
- Full ground-up platform rebuild on a modern, scalable technology stack — React 18/Next.js (TypeScript) frontend, NestJS backend API, FastAPI AI services layer, PostgreSQL primary database, Redis caching
- Adaptive Learning Engine: real-time difficulty adjustment using score-threshold logic (≥80% advances, 50–79% holds, <50% reduces difficulty and flags topic for review)
- Smart Test Engine: full assessment lifecycle management — initialisation, adaptive question serving, state management, result computation, and analytics storage
- AI Question Generator: LLM API integration (OpenAI and Anthropic) producing structured 4-option MCQs by topic and difficulty, with teacher review gate before questions enter the live question bank
- Curriculum Mapping Engine: Subject → Topic → Sub-topic → Difficulty hierarchy aligned to WAEC and JAMB standards, extensible for additional curricula post-launch
- Weak Area Detection and Recommendation Engine: automatic gap identification from performance history, with targeted practice question recommendations surfaced on student and teacher dashboards
- Smart Analytics Dashboard: individual, class, and institutional performance tracking with visual weak-topic trend reporting and cohort-level export-ready data
- Teacher Productivity System: personal and shared question bank management, cohort test assignment and scheduling, automatic MCQ grading, and institutional content sharing with role-based permissions
- AI-Assisted Test Builder: generate complete assessments by topic, difficulty tier, and question count, with manual refinement capability before publishing
- Institutional Content System: centralised, governed content repository with role-based access (read, contribute, admin) and curriculum-aligned content tagging
- Multi-language architecture (i18n infrastructure): localisation-ready across all UI surfaces with English-only content at MVP; structured for future language expansion without rework
- Modular Monolith architecture: five clean service boundaries (Auth, Assessment, AI, Analytics, Content) enabling fast unified deployment now and microservice decomposition as scale demands
- Security and compliance: JWT authentication with token expiry and refresh, RBAC across all endpoints, TLS 1.2+ encryption in transit, data encryption at rest
- Cloud infrastructure: AWS/GCP managed Kubernetes with Redis caching, targeting >99.5% uptime and <500ms API response time at p95
- DevOps: full CI/CD pipeline, infrastructure provisioning, deployment automation, and ongoing monitoring
Outcomes and impact
- Complete ground-up platform rebuild delivered across a 10–12 week engineering timeline
- Real-time adaptive learning engine replacing static content delivery across all student sessions
- AI question generation pipeline dramatically reducing teacher content creation time
- Full WAEC and JAMB curriculum alignment enabling structured exam preparation for Nigerian students
- Institutional analytics dashboard providing cohort-level performance intelligence previously unavailable
- Scalable Kubernetes infrastructure supporting thousands of concurrent user sessions from launch
- Clean modular codebase positioned for microservice decomposition and future global expansion
Technology used
“We needed a stronger and more scalable technology foundation for LearnoGauge, and H-SETS has played a key role in bringing that vision to life. The platform is now being built to support more intelligent learning, better analytics, and a more personalised experience for students”
Let's write your success story
Book a free consultation and tell us what you're trying to achieve.