Skip to content
Groundcrew
Talk to a human
All work
Education

Zehaanat

Articles and ePaper pages turned into study material and practice

Candidates preparing for the CSS and MPT examinations, on web and an Android-first mobile app.

2–3–5–7
day review cycle
Zehaanat essay editor with AI examiner grade on a phone
I / The situation
01

I read the news every day, but the useful facts never make it into my revision.

02

Half my sources are ePaper page images that normal tools can't read.

03

I write practice essays with nobody to tell me what's wrong with them.

II / What we built
01

Two source paths

Text articles are fetched server-side; ePaper screenshots go through vision-based extraction, because one method can't handle both well.

02

AI study extraction

GPT-5 nano turns the material into study-oriented content that lands in a tagged factbook organized by subject and theme.

03

Built-in revision

Every saved fact gets a 2-3-5-7 day spaced-review schedule instead of sitting in a notes file.

04

Practice and essays

MPT drills, timed mocks, accuracy history, PEEL outlines, heuristic checks, AI essay feedback, and optional RAG search over past papers.

05

Controlled AI costs

Per-account request ceilings and a usage ledger record tokens, latency, failures, and estimated cost, without storing study content.

III / Results
4
spaced review intervals
2
platforms: web and Android
01

One product connects source intake, extraction, revision, practice, and essay writing.

02

2 source paths, 2 grading paths, and a 2-3-5-7 review schedule in production.

03

Administrators see exactly what the AI features cost, per account.

04

Desktop and mobile covered by Playwright tests, with shared API contracts across web and mobile.

IV / Stack
AI used

GPT-5 nano. Text and vision extraction from articles and ePaper pages, plus essay feedback

AI used

OpenRouter. Model routing for AI requests

AI used

OpenAI. Model provider for extraction and feedback

AI used

RAG search. Optional answers grounded in past examination papers

Frontend

Next.js, React Native, Shared API contracts

Backend

Cheerio article fetching, Account-level AI limits, Usage reporting

Data

MongoDB

AI and automation

GPT-5 nano, OpenRouter, OpenAI, Optional RAG

Infrastructure

Playwright testing

V / This is for you if
01

You need to pull useful information out of both text and image-based documents.

02

You want AI features with clear per-user cost controls.

03

Your product should turn raw reading into structured, reusable records.

Book afree call.

One call about one workflow. We talk through the scope, the timeline and the quote, then you decide.