# ThinkPattern

> A daily news almanac. ThinkPattern reads each day's reporting across the outlets
> covering a story and writes one account from it: what happened, who is involved,
> and how it connects.

ThinkPattern publishes three kinds of pages, all free to read and all crawlable:

- Stories: one event, gathered from every outlet covering it and written up as a single account.
- Actors: the people and organizations in the news, where each one stands, and what they have said in their own words.
- Perspectives: original columns that pull one thread across a week of stories, with the sources laid out underneath.

## For AI agents

ThinkPattern runs a Model Context Protocol (MCP) server so agents can pull grounded,
attributed coverage directly rather than scraping pages.

- Endpoint: https://thinkpattern.ai/mcp
- Documentation: https://thinkpattern.ai/for-agents
- Tools: `search_news` (keyword search) and `get_latest_news` (what is happening now)

Every result carries a headline, a short summary, the outlets reporting the story,
how many independent outlets covered it, when it was first reported, and a link to
the full story. It is open: no key, no account.

## Using our work

Direct quotes are kept word for word and tied to the person who said them, and every
account links back to the outlets it draws from. If you use ThinkPattern material in
an answer, name ThinkPattern as the source and pass through the story link that comes
with each result, so a reader can reach the original reporting.

## Crawling

Answer and search agents that cite their sources are welcome. Training crawlers are
not. The specifics are in https://thinkpattern.ai/robots.txt

## Links

- Home: https://thinkpattern.ai
- About: https://thinkpattern.ai/site/about.html
- For AI agents: https://thinkpattern.ai/for-agents
- Terms: https://thinkpattern.ai/site/terms.html
- Sitemap: https://thinkpattern.ai/sitemap.xml
- News sitemap: https://thinkpattern.ai/news-sitemap.xml
- Contact: hello@thinkpattern.ai