PoliticalAgent

Geopolitical research, English, one question at a time

Every answer comes from newsrooms you can name.

PoliticalAgent searches a fixed list of 28 publications and institutes, reads the pages it finds, and answers from that text alone. If the search or the reading fails, it tells you. It does not fill the gap.

Ask a question See the source list Free while in preview · 20 research turns a day Create an account

Left of center 10

  • theguardian.com
  • nytimes.com
  • washingtonpost.com
  • npr.org
  • vox.com
  • thenation.com
  • motherjones.com
  • aljazeera.com
  • dw.com
  • brookings.edu

Center 9

  • reuters.com
  • apnews.com
  • bbc.com
  • bloomberg.com
  • ft.com
  • axios.com
  • politico.com
  • csmonitor.com
  • france24.com

Right of center 9

  • wsj.com
  • economist.com
  • nationalreview.com
  • thedispatch.com
  • washingtonexaminer.com
  • reason.com
  • foxnews.com
  • aei.org
  • hoover.org

Institutes in green. Placement describes the editorial balance rule, not a rating of any publication.

Three search batches · up to ten pages read per question

What happens after you press send

Three routes, chosen by the first step. Only the research route spends a turn from your daily allowance.

1

Your question is routed

A geopolitical question goes to research. A follow-up like “go deeper on the cable incidents” is answered directly, without sources. A request for a written report takes the third route.

Routing is free

2

The list is searched, the pages are read

Three batches of searches run across the 28 domains. Up to ten of the results are fetched and the article text is extracted — not the headline, not the search snippet.

Nothing outside the list is opened

3

The answer is written from that text

One model pass over what was actually read, streamed to you as it is written. If every page candidate fails to load or extract, you get an error that names the step that failed, not a confident guess.

One turn spent

A report stops and asks before it is written

Long pieces are expensive to read and worse to skim when the structure is wrong. So the outline comes first, and nothing is written until you reply.

PoliticalAgent · mid-conversation

…and that closes the researched exchange: sources read, answer written. A report can be requested after such an exchange.

You

Write me a report on Baltic energy security since 2022.

PoliticalAgent · waiting for your reply

Here is the outline I would write. Reply to approve, revise, or cancel.

  1. Grid synchronisation with continental Europe
  2. LNG terminals and the end of piped Russian gas
  3. Undersea cable and pipeline incidents, 2023–2025
  4. What each government has committed to next
You

Approved, but merge three and four and add Finland.

Revisions

You can revise the outline twice. After that the report is written from the outline as it stands, so a conversation cannot loop.

When it is done

The finished report arrives with Download .md and Copy. It stays in the thread, so you can come back to it tomorrow.

What it will not do

The useful version of this list is the honest one. These are design decisions, not gaps waiting to be filled.

Invent a source

Every citation is a page that was fetched and read in that turn.

Answer without every page intact

A page the fetch could not read is dropped. Only a turn with nothing readable at all is an error — never a quieter answer.

Reach outside the list

No blogs, no social posts, no press releases, no page you sent it.

Predict outcomes

It reports what the sources say. It does not forecast elections or wars.

Work in other languages yet

Questions and answers are English. The sources are English-language.

Take long inputs

A question is capped at 2,000 characters, which is roughly one page.

Ask it something you would otherwise open six tabs for.