EduAgent Platform
AI tutoring agents for education
Software Engineer2026 — Present6 engineers
0k+
learner sessions / day
0%
questions auto-resolved
<0.0s
p95 first-token latency
−0%
token cost via caching
OVERVIEW
An AI agent platform for education at SiliconPrime: LLM-powered tutoring agents answer learner questions over course materials using RAG, orchestrate tools (quiz generation, progress lookup, curriculum search), and stream responses in real time to web and mobile clients.
CHALLENGES
- Answering course-specific questions accurately without hallucinating beyond the curriculum.
- Keeping streaming latency low while agent runs involve multiple tool calls and retrieval rounds.
- Controlling LLM token spend as daily sessions grew past 5k.
SOLUTIONS
- Built a RAG pipeline over versioned course materials with pgvector embeddings and metadata filtering per course and grade level.
- Designed an agent orchestration service with parallel tool execution and an SSE streaming gateway that flushes first tokens before slow tools finish.
- Added Redis-backed prompt/response caching and context-window pruning keyed on curriculum version.
RESULTS
- 85% of learner questions resolved without human tutors, measured over 5k+ daily sessions.
- p95 first-token latency held under 1.2 seconds during peak evening study hours.
- Token cost per session cut ~35% after caching and pruning rollout.
TECH STACK
- Node.js
- NestJS
- PostgreSQL
- pgvector
- Redis
- LLM APIs
- SSE
- WebSocket
- Docker
- AWS
ARCHITECTURE
PROCESS
- 013 weeks
Agent & RAG design
Modeled agent tools, retrieval flows, and curriculum embedding strategy.
- 02Ongoing
Platform build
Implemented orchestration services, streaming gateway, and evaluation harness.
- 03Continuous
Cost & latency tuning
Caching, pruning, and load testing against session growth.