Independent journalist dashboard

The Problem

The program team had a long list of independent journalists and creators with just their names and outlets. This was not enough context to review the database with confidence. They needed me to enrich the data and make it easier to browse and assess.

What I Built

I built a local enrichment workflow and a single-file browser dashboard. The pipeline starts with creator names and outlets, runs bounded web searches, extracts evidence, and classifies each record by beat, creator type, geography, confidence, and review status. Source URLs, snippets, rationale, and review flags stay attached to each record so reviewers can see why a classification was suggested.

The dashboard embeds the merged 1,165-record dataset and gives staff summary stats, beat distribution, filters, sortable pagination, a detail drawer, evidence cards, editable classifications, reviewer notes, starring, and annotated CSV export.