Skip to content
AI

Same Story, Three Outlets

See how different outlets frame the same news story side by side.

Intermediate16h1–3 people16/20 fit
TL;DR

Build Same Story, Three Outlets for news readers and media students in ~16h with 1–3 people. Stack: Search API + Embeddings + LLM + Next.js.

Why it wins: Timely, discussion-starting and easy to understand.

Build flow

01 · Problem
Readers get one framing of a story and rarely notice what other outlets emphasise or omit.
02 · Solution
Cluster articles about one event, then have an LLM compare framing, emphasised facts and missing facts, always linking the source articles.
03 · Build
  1. 1Fetch articles from a news search API
  2. 2Cluster by embedding similarity
  3. 3Prompt a comparison with citations
  4. 4Render a side-by-side view
04 · Demo
Pick today's top story and show the framing comparison table.

MVP checklist

  • Story clustering
  • Framing comparison
  • Missing-facts list
  • Source links

Tech stack

TechRole
Search APIWeb search
EmbeddingsSemantic similarity
LLMLanguage model
Next.jsFrontend + API routes

Related ideas

More AI

  • AI

    Support Ticket Auto-Triage

    Incoming tickets get a category, urgency and suggested reply automatically

    Intermediate14h1–3
    EmbeddingsLLMPostgres
    16/20

  • AI

    Ask Your CSV in Plain English

    Upload a CSV, ask a question and get a chart plus the SQL that produced it

    Intermediate14h1–2
    DuckDBLLMCharts
    18/20

  • AI

    Document Q&A

    Lets people ask questions about long documents instantly

    Intermediate24h1–3
    Next.jsRAGLLM
    16/20