Platform · Education · Assessment content

● In production

Textbooks in, reviewed exam questions and learning cards out, in English and Bahasa Melayu.

A content production platform for Tavis, an online tuition provider for SPM students in Malaysia. Subject teams upload textbooks and past papers, AI extracts and generates questions and learning cards against the syllabus, an AI review stage votes on each one, and editors approve what gets published to the live learning platform.

Client
Tavis
Country
Malaysia
Services
Applied AI and LLM systemsCustom business systemsSystems integrationCloud architecture and DevOps
question-bank / review-jobs
Interface illustration with sample data. No client records are shown.
9,300+
questions generated and tracked
5,600+
learning cards, in English and Bahasa Melayu
475
textbooks and papers read into the knowledge base
1,150+
automated backend tests
01

Knowledge base

Upload textbooks and papers. The system extracts chapters, questions and figures.

02

Generation jobs

Draft questions and learning cards by subject, level, chapter and subtopic.

03

AI review

Independent AI votes on every item, with corrections proposed as diffs.

04

Approve and publish

Editors approve in bulk and push to the live learning platform.

The problem

A good exam question takes a subject expert real time to write, check and tag. A learning platform needs thousands, across subjects, levels and chapters, in two languages, with diagrams, and every one of them has to be right.

  • Writing and tagging content by hand could not keep up with the syllabus
  • Generic AI output drifts off-syllabus and makes confident mistakes
  • Mathematics and science content needs equations and figures, not just text
  • Published content goes straight to students, so review cannot be skipped

What we built

A pipeline with people in charge of it. Uploaded textbooks become a per-chapter knowledge base. Generation jobs draft questions and learning cards grounded in that material. A review job then casts a configurable number of independent AI votes on each item. A strict majority must judge it good for it to pass; anything else goes to a person. Proposed corrections reach editors as a word-level diff they can accept, edit or reject.

  • PDF and image extraction into structured chapters, questions and figures
  • Generation grounded in the uploaded syllabus material, by subject, level and subtopic
  • AI review by vote: a strict majority passes an item, anything else is routed to an editor
  • Suggested corrections shown as diffs, never applied silently
  • Equation editing, and figure redraws with an AI fidelity check against the source
  • One-way publishing of approved items into the client's production database
  • An in-app assistant that answers editors' how-do-I questions and links to the right screen

Why it holds up

Every prompt and model choice is stored in a prompt set that the content team can adjust per subject without a deployment. Long jobs run on a queue and stream their status to the browser. More than 1,150 automated tests cover the backend, because content that reaches students cannot depend on someone remembering to check.

Outcome

Subject experts moved from writing every item to reviewing and approving them. The platform is in production, producing bilingual questions and learning cards for the client's students.

  • React 19
  • TypeScript
  • Mantine
  • Tiptap + KaTeX
  • Django 6
  • Celery + SQS
  • Google Gemini
  • PostgreSQL
  • ECS Fargate
  • Terraform

Inside Question Bank AI

The live system.

Screenshots from production. Names and other personal details are obscured.

Question Bank AI: dashboard
dashboard
Question Bank AI: ai question review
ai question review
Question Bank AI: question editor with ai review
question editor with ai review
Question Bank AI: questions
questions
Question Bank AI: knowledge base
knowledge base

More work

All work
clausework / mortgage-debtors
Legal · Banking litigation

Clausework

From a bank's spreadsheet to court-ready documents, with every step on the record.

Kek Ooi & Lee Hong
iqc / quality-control
Manufacturing · Water reticulation

IQC

Every product traced from the factory floor to the purchaser, with a certificate anyone can verify.

Soon Chuan Hong Hardware Sdn. Bhd.
casework / cases / process
Legal · Case management In development

CaseWork

Every matter as a living graph: what is done, what is due, and which way the case went.

A Pikabyte product for law firms

Start a conversation

Facing something similar?

Tell us what is slowing the business down. You will talk to an engineer, not a salesperson, and get a straight answer on whether software is the right fix.