Case studyI / V

A newsroom that shipsverified truth, faster.

We built the editorial workflow, claim database, and LLM-assisted verification pipeline behind a leading Bangla fact-check organization — turning a multi-day claim cycle into a same-day one, in Bangla and English.

Visit live site

Client: FactWatch
Sector: Fact-checking · News
Year: 2025
Services: Product · Web · ML

12hAvg. claim turnaround

94%Editor approval rate

3.2×Daily output uplift

I.The brief

A multi-day claim cycle was the bottleneck — and disinformation moves in hours.

Editors were drowning in screenshots, chat-app forwards, and contradictory sources, with tooling that amounted to a shared drive and a spreadsheet. Claims took days to verify; the most viral ones spread long before a fact-check ever published.

They needed one platform that ingested public submissions, helped editors triage and assign, accelerated source-checking with AI, and produced a public claim record in Bangla and English — without compromising the editorial standard their reputation rests on.

II.The approach

The decisions behind the work.

Discovery

Embedded with the editors for a week.

We watched the actual workflow — inbox triage, source-checking, the back-and-forth with experts. The bottleneck wasn’t writing; it was finding the original claim across five chat apps.

Architecture

Claim database first, UI second.

A schema with claim, source, expert, and verdict as first-class entities. Every surface reads and writes through this single source of truth — no copy-paste between systems.

AI assist

LLM as a research intern, not a writer.

The model pulls candidate sources, flags duplicates against past claims, and drafts the timeline. Editors approve or reject every line. It accelerates the human; it never publishes.

Bilingual delivery

Bangla-first, English-second.

Bangla search, paired headlines in both languages, and structured-data markup so each verdict surfaces correctly in Google’s fact-check carousel.

Launch

Migrated years of archives in a weekend.

Thousands of historical claims imported, deduplicated, and back-tagged so the platform launched with the credibility of an established archive on day one.

III.In the wild