A multi-day claim cycle was the bottleneck, and disinformation moves in hours.
A newsroom that ships verified 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.
- Client
- FactWatch
- Services
- Product · Web · ML
- Duration
- 14 weeks
- Team
- 4 people
- Year
- 2025

- 12h
- Avg. claim turnaround
- 94%
- Editor approval rate
- 3.2×
- Daily output uplift
- 14wks
- From kickoff to launch
The project in one minute.
The short version, for anyone who needs the story before the detail.
One editorial workspace where a claim moves from intake to published verdict, with an assistant that drafts the evidence timeline for an editor to approve.
A multi-day cycle compressed to same-day, without an editor-trust regression.
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.
What success looked like
- 01Publish verified claims the same day they surface
- 02Keep every verdict traceable to its sources
- 03Serve Bangla and English readers from one newsroom
Six parts, one product.
Web · CMS · ML pipeline. Everything below shipped in the first release.
- 01
Claim database
Every claim, source and verdict in one searchable, linkable record.
- 02
Editorial workflow
Intake, research, review and publish stages with clear ownership.
- 03
Assisted verification
Drafted evidence timelines that editors accept, edit or reject.
- 04
Bilingual publishing
Bangla-first articles with English versions from the same record.
- 05
Verdict labels
Consistent, shareable rating stamps across web and social cards.
- 06
Archive migration
Years of earlier fact-checks imported with redirects preserved.
The decisions behind the work.
14 weeksfrom kickoff to launch, with a 4-person senior team.
- 01
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.
Discovery - 02
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.
Architecture - 03
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.
AI assist - 04
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.
Bilingual delivery - 05
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.
Launch
Timeline
- Weeks 1–2Discovery
Stakeholder interviews, audit of the existing product and a written scope.
- Weeks 3–5Design
Flows, wireframes and a design system reviewed in weekly sessions.
- Weeks 6–12Build
Two-week sprints with a working demo at the end of each.
- Weeks 13–14Launch
Performance pass, content migration, go-live and hand-over.
Who worked on it
- Project leadFerdous Rahman
- DesignZahid Hasan
- EngineeringMohon Das
- EngineeringShakil Ahmed
See the whole thing.
Each screen is the full page, top to bottom. Open any one to scroll the entire design.
A multi-day cycle compressed to same-day, without an editor-trust regression.
3.2×More verified claims published per editor, per week
- Avg. claim cycle
- 12h
- AI-drafted timelines approved
- 94%
- Archive claims migrated, day one
- 11k
- Editorial corrections post-launch
- 0
“They embedded with our editors instead of pitching us. The platform reads like one of us built it, because effectively, one of us did.”
Editor-in-ChiefEditorial lead · FactWatchWhat we'd tell another team.
Three things this project taught us that we now bring to every engagement.
- 01
Sit with the people doing the work
A week inside the newsroom changed the scope more than any workshop would have.
- 02
Assist, never decide
Editors trusted the assistant because every draft was theirs to reject.
- 03
Migrate early
Moving the archive in the first sprint surfaced the hard data problems while there was time to fix them.
Services on this project
Built with
- Next.js
- TypeScript
- PostgreSQL
- Tailwind CSS
- Bangla NLP
Keep looking.
Marketplace · E-commerceFlipper: buy, sell & exchange electronics.A trust-first marketplace for phones and gadgets: graded catalog, live bidding, trade-in, and local payments.8,000+devices traded on the platform
EdTech · KidsiQQra: gamified Islamic learning for kids.A prophet-story journey map, grade-based chapters, interactive quizzes, and a parent performance dashboard.30interactive chapters per gradeWant results like these?
Tell us what you're building. We reply within 24 hours. No commitment, no sales pitch.
Prefer email? hello@codeflee.com · WhatsApp