Project reportPLXN WorldSep 2024 – Apr 2026
CLUE AI: a syllabus-aware tutor grounded in the student’s textbooks and their own past lessons
1Founding engineer, PLXN World · New Delhi, India · 1406srinath@gmail.com
Abstract
IB students don’t need a chatbot that knows everything. They need one that knows their syllabus, their textbooks, and what happened in last Tuesday’s lesson. I built CLUE AI to be that tutor. It parses textbooks with layout-aware PDF parsing[1], transcribes hours-long 1-on-1 sessions[2], and embeds both into one vector store[3]. A ReAct agent[4] answers with a three-tier memory and checks itself against textbook citations before it replies. Vector search returns in ≤ 10 ms; the first token arrives in under 120 ms.
Keywords retrieval-augmented generation · agent memory · education · speech recognition · model routing
1Introduction: the problem
IB students spend hours in 1-on-1 lessons. Between lessons, they’re on their own with a textbook and a general-purpose chatbot. The chatbot didn’t know which syllabus they were on, which edition of the book they used, or what their teacher had already explained — so it would answer correctly and still be no help.
I wanted a tutor with three properties. It should be grounded: every explanation traceable to the student’s own textbook. It should remember: the lesson recordings and past chats are part of the context. And it should be fast enough to feel like a conversation.
This report describes the system I built as the founding engineer at PLXN World¹, from September 2024 to April 2026.
2System overview
The front end is Next.js 16[7]. The back end is FastAPI[8], with long jobs pushed through Redis to Celery workers[5] and files kept in MinIO[6].
Two ingestion paths feed one store. Textbooks go through Docling, which keeps headings, tables and figures in reading order. Lesson recordings — hours long, files up to 200 MB² — go through Whisper v3 Turbo. Both are chunked and embedded into pgvector (Figure 2).
3The agent and its memory
The tutor is a LangChain ReAct agent[4]. It decides when to search the textbook, when to search past lessons and when to just answer. Its context C is assembled from the three tiers of Figure 1:
where Wtok is the token-aware window, Sprog the progressive summary, Mped the cross-session pedagogical memory and R(q) the passages retrieved for question q.
3.1Grounded self-correction
Before an answer reaches the student, the agent checks its own draft against textbook citations, and revises until every claim is supported (Algorithm 1).
Algorithm 1 Grounded self-correction
- draft ← agent(q, C)
- cites ← retrieve(textbook, draft)
- while not supported(draft, cites) do
- draft ← revise(draft, cites)
- cites ← retrieve(textbook, draft)
- end while
- return draft with cites
4Multi-model routing
No single model was best at everything a student asks. A router sends each request to Gemini, Claude or GPT-4.1 — GPT-4.1 for step-by-step maths written out in LaTeX (Figure 3).
4.1Latency budget
A tutor that pauses feels like it’s thinking about you instead of with you. I held the system to a budget:
5Results
6Plates
Placeholder photographs. Screenshots of the tutor chat, the citation view and the lesson library go here.





AImplementation details
- Front end
- Next.js 16
- API
- FastAPI
- Jobs
- Redis · Celery workers
- Storage
- MinIO · PostgreSQL + pgvector
- Parsing
- Docling (layout-aware PDF)
- Speech
- Whisper v3 Turbo
- Agent
- LangChain ReAct · 3-tier memory
- Models
- Gemini · Claude · GPT-4.1
BCode availability
The code belongs to PLXN World and is not public. I’m glad to walk through the design.
References
- [1]Docling. Layout-aware document conversion: keeps headings, tables and figures in reading order.
- [2]Whisper large-v3 Turbo. Speech recognition, used to transcribe hours-long 1-on-1 lessons.
- [3]pgvector. Vector similarity search inside PostgreSQL; one store for textbooks and lessons.
- [4]LangChain ReAct agent. Interleaves reasoning with tool calls: search textbook, search lessons, answer.
- [5]Celery on Redis. Background workers for parsing and transcription jobs.
- [6]MinIO. S3-compatible object storage for uploads up to 200 MB.
- [7]Next.js 16. The student-facing web app.
- [8]FastAPI. The Python API that hosts the agent.
