Media Agents: Follow The Money Series
Live link https://mediaagents.up.railway.app/ Follow the Money is a series featuring two (agent) hosts who investigate who owns corporate media.
Core trick
Two persona agents with live web search and cross-referenced ownership data generate a voiced debate on media ownership.
Description
Live link https://mediaagents.up.railway.app/
Follow the Money is a series featuring two (agent) hosts who investigate who owns corporate media. Discussing their findings on the money trail, ownership data, and biases of the top 6 publications, using real-time data to highlight current events and historical data for a full investigation.
In this edition "Who funds corporate media?" with your favorite hosts (two agents) Andrew (investigative reporter) and FJ (industry veteran) investigate, discuss and debate their findings.
What makes this special?
- Characters have real personalities, are opinionated and converse naturally between each other
- Conversations reference real-time events from this week via live web search (lots happened in the corporate media space this week if you follow the news like huge Washington Post layoffs)
- Ownership data cross-referenced from curated dataset, Notion database and web
- Bias and factuality ratings sourced from Ground News
README excerpt
# Follow the Money Series **"Who funds corporate media?" with your favorite hosts.** Two agents, Andrew (investigative reporter) and FJ (industry veteran) investigate the ownership structures behind major news publications using real-time data, then debate what it means for journalism and democracy. Built for the [Cartesia x Anthropic Voice Agents Hackathon](https://cerebralvalley.ai/e/cartesia-voice-agents-hackathon) (SF, Feb 2026). --- ## What It Does Pick a publication. Two AI characters investigate who really owns it — pulling live ownership data, government contracts, recent controversies — then discuss their findings with distinct voices and personalities. **6 publications covered:** The Washington Post, Fox News, CNN, The New York Times, The Wall Street Journal, Los Angeles Times **What makes it different:** - Characters have real personalities with selected voice from Cartesia's library - Conversations reference events from *this week* via live web search - Ownership data cross-referenced from curated dataset + Notion database + web - Bias and factuality ratings sourced from [Ground News](https://ground.news/) ## Stack | Layer | Technology | Role | |-------|-----------|------| | Reasoning | **Claude API** (claude-sonnet-4-20250514) | Agent personalities, web search, conversation generation | | Voice | **Cartesia TTS API** (sonic-2) | Text-to-speech with distinct voices per character | | Data | **Notion** database + JSON | Structured ownership data, queried