Projects / content-reporting-platform
Platform for reviewing and flagging online content
A platform that helps operators review content found online, report it to the platforms that host it and follow up on each report.
- Period
- 2025–2026
- Role
- Sole full-stack and GenAI developer
- Context
- Confidential
- Cloud
- Azure
[ Architecture ]
How it works
Run a scenario to follow it through the system, step by step. Select a component to read its role and see what it connects to.
message
the intake channel
Screenshot + link to a post
A post found online is sent for review.
screenshot.png
ConsoleSimulated run · illustrative data
- Press Send a post for review to watch each step run through the system.
- 01SourceScreenshot and link sent for review
- 02Intake & scoringItem stored · scoring job queued
- 03Multimodal LLMScore and description returned
- 04Intake & scoringScore and description validated
- 05Operator appItem listed by score
- ✓The item is scored and waiting for an operator.
- 01Operator appOperator edits the drafted report · clicks Report
- 02Flagging botReport filed
- 03Online platformsReport received
- 04Flagging botFollow-up check · status recorded
- 05Operator appStatus updated on the item
- ✓The report is filed and its status stays visible on the item.
Problem
Operators review content found online, report it to the platforms that host it, then follow up on each report. Every platform has its own forms, and each step must stay traceable.
Approach
- A multimodal model scores each item, with versioned prompts.
- The model drafts each report, and an operator edits it before anything is sent.
- Browser automation files the reports, and a scheduled job follows up on them.
My role
Sole full-stack and GenAI developer: API, operator web app, scoring, report automation, follow-up checks, Azure infrastructure, and the hand-over.