Reed NewsReed News
Back to Journal
February 9, 20265 min

Why We Built Reed News

By Reed Team

A couple of years ago, we found a burnt-out car on our street. Scorch marks on the asphalt, police tape, neighbors standing around looking. Nobody knew what had happened.

So we did what everyone does: opened the local newspaper. Nothing. We scrolled past celebrity headlines, opinion pieces, lifestyle columns. The story about the car fire, right outside our home, was buried somewhere around page eleven, if it existed at all.

Something similar happened to a friend who lives near a prison. An inmate had escaped. It was in the local paper, but under global news and editorials. They didn't find out until after the fact.

That's the point. It's not that local papers do a bad job. It's that "local" doesn't mean the same thing for you as it does for everyone else in your city.

Critical information at the individual level

Your local newspaper shows you news for your city. But your city is big. And what happens on your street, in your neighborhood, near your school, that matters more to you than it ever could to someone living twenty kilometers away.

A burnt-out car on your street is a 10 out of 10 in relevance for you. For someone across town, it's barely a footnote. But today's news services treat you both the same.

We built Reed to solve that. Reed knows where you are and scores every piece of news across five geographic levels: street, neighborhood, city, region, and country. If something happens near you that's significant at the local level, even if it's not a top story citywide, you see it first.

Eventually, we want to send you a notification if someone escapes from the prison in your area. Not to the whole city. To you, because you live there.

That's what we mean by critical information at the individual level.

News first, recommendations second

Most news apps and social platforms optimize for engagement. They show you what you want to see, not what you need to know. The result is filter bubbles and a feeling of being informed without actually being informed.

Reed does the opposite. First, we show you the most important news for you based on where you are and what's happening in the world. That's the foundation. It never gets displaced.

Then, once you've seen the important stuff, we gently tilt your feed toward topics we think interest you. Sports, tech, a specific politician, a company. But never more than 15–25% of your feed. Compare that to a streaming service that recommends 80% of its content. We also reserve 18% of the feed for topics outside your usual patterns, so you don't get stuck in a bubble.

A missed movie recommendation doesn't matter. A missed news story can.

Synthesis, not aggregation

Reed isn't a place that collects headlines from other newspapers and sends you elsewhere. That's what aggregators do: Google News, Flipboard, similar services. The content belongs to someone else and you get sent somewhere else.

Reed works more like a wire service. Like Reuters or AP. We gather reporting from over 1,000 sources, cluster articles about the same event, and write our own reporting based on the collected material. Then we review our own text with independent fact-checking against the source material.

The difference is that when you write your own content, you can show exactly how it was made. And that's exactly what we do.

What actually happened?

When something happens in the world, different outlets report it differently. Sometimes because they have different information. Sometimes because they have different perspectives. Sometimes because they're deliberately angling their coverage.

Reed tries to cut through that. Our approach is simple: what happened, how sure are we that it happened, what don't we know, and how do we know what we know?

If a newspaper leaning one direction reports A and B, and a newspaper leaning the other direction reports B and C, then we can say with some confidence that B is probably true. We don't take sides. We don't try to convince you of anything. We show you what we know and how we know it.

Every article has a transparency panel showing sources with timestamps, five confidence levels from unconfirmed to confirmed, what we don't know, and how the article was made.

AI with open cards

Reed is an AI-native newsroom. We use AI at every step, from extracting events from source material to writing articles and fact-checking them.

We believe AI has a place in journalism. But we also believe the secrecy around AI in media is a problem. Many newsrooms use AI today without telling their readers. We do the opposite.

Transparency isn't an extra feature. It's the core of how Reed works.

No barriers

Reed has no ads. No login required. No paywall.

We believe basic news reporting, knowing what's happening in your world, shouldn't require you to hand over your data or open your wallet. That's a deliberate choice, not a lack of business model.

What we're building toward

Right now, Reed is an app for Swedish news. But the vision is bigger.

We want to build the world's largest news organization, not by hiring thousands of journalists, but by combining AI synthesis with distributed reporting. Imagine anyone being able to contribute information from their corner of the world, and that information being verified, synthesized, and published with full transparency.

From the smallest village to the European Parliament.

It's a long road. But every step starts with the same principle: the most important news for you should reach you first, and you should always be able to scrutinize how we know what we claim to know.

Try it yourself

Reed is available on the App Store for iPhone. Download it, read an article, open the transparency panel.

Scrutinize us. That's the whole point.

Reed News is an independent Swedish AI-native newsroom. Questions? hello@reednews.app

February 24, 20265 min

How Reed News Works

By Reed Team

Most news outlets ask you to trust them. We ask you to scrutinize us.

That is not a slogan. It is a design decision. Every article Reed publishes has a transparency panel showing exactly how our articles are created. Which sources we used, which steps we took, what we know and can confirm, but also what we do not know. This article describes how that process works.

From source to article

Reed monitors over 1,000 news sources. When something happens in the world, dozens of outlets often write about the same event. Sometimes with the same facts, sometimes with different ones, sometimes with contradictory information.

Our process looks like this:

First, we collect reporting from all sources covering an event, then we cluster the articles. We identify which articles are about the same thing. Next, we extract facts, locations, timestamps, and people involved from the collected material. We do research -- background information about people, organizations, and places that are mentioned. Then we write our own article based on the collected material. Finally, we review our own text against the source material, independently of the writing process.

That last step is the most important: we fact-check ourselves.

The two-source principle

Reed does not publish an article based on a single source. We require at least two independent sources before publishing. With one exception: official government statements, since they constitute primary sources in themselves.

This means we are sometimes slower than others. An event that only one newspaper has reported on will not be published by us until more sources confirm it. That is a natural consequence of how we work -- we would rather be right than fast.

Fact-checking with RAG review

When an article is written, it goes through an automated review that operates independently of the writing process. The system extracts the central claims in the article and then searches for support in the source material.

This is done through what is called RAG review (Retrieval-Augmented Generation), a process where the system independently searches through the actual source material to find support, or lack of support, for each individual claim. It is not the same AI that wrote the text that reviews it, but an independent process that matches claims against the original reporting.

Each claim is assessed as confirmed, unconfirmed, or disputed.

If the review finds problems, there are three possible outcomes: the article is approved, the article is rewritten with corrections, or the article is escalated for manual review. An article may be rewritten at most twice. If it does not pass after that, it goes to manual review.

This means we never publish anything that has not passed our own fact-checking.

Five confidence levels

Not all information sources are equally reliable -- everyone who reads news knows this. But it is rarely shown. Reed shows it.

Every article has a confidence level on a five-point scale:

  • Confirmed -- Multiple independent sources, verified information.
  • High -- Official sources, consistent reporting.
  • Medium -- A primary source, reasonable but not independently verified.
  • Low -- A single source, conflicting information exists.
  • Unconfirmed -- Circulating but not verified.

We believe it is better to publish a story with a clearly marked low confidence level than not to publish it at all -- provided that the reader truly knows what they are getting.

What we don't know

This is perhaps the most important section in every Reed article, and the most unusual.

Every article has a section called "What we don't know." It lists the questions we could not answer (if any exist), the information we lack, the perspectives missing from the reporting.

It was a deliberate design decision. Journalism is not just about what happened. It is about what we can actually be certain of, and being honest about the limits of our knowledge.

AI with open cards

Reed uses AI in every step of its editorial process. From identifying events in source material to writing articles, extracting quotes, and checking facts in the finished text. We know this raises questions -- can you trust AI-generated journalism?

Our answer is that you should not have to trust us. You should be able to scrutinize. Every article shows which steps were taken and which sources form the basis. If something is wrong, you should be able to see where the error occurred.

Most newsrooms that use AI to some extent (which is most of them) do not tell their readers about it. We do the opposite. Not because we have to, but because we believe transparency is the only way to earn trust.

How we handle errors

We will make mistakes. Every newsroom does. The difference is what happens next.

Every article has a changelog showing how the text has evolved over time. If we correct a factual error, it is visible. If the confidence level changes, it is visible. If new information is added, that is visible too.

We do not erase mistakes. We show them.

What we don't do

We don't take political sides. Reed does not try to convince you of anything. When a story is reported differently by different outlets, we try to identify what is common -- what is likely true -- and be clear about what is disputed.

We don't sell your attention. Reed has no ads. Your behavior in the app is used to give you more relevant news -- not to show you more relevant ads.

We don't hide how we work. If you wonder how a specific article was created, open the transparency panel. Everything is there.

Scrutinize us

We are not asking for your trust. We are asking you to look at how we work and judge for yourself.

Open an article. Open the transparency panel. Look at the sources. Read what we know -- and what we don't know. Compare with the original sources if you want.

That is the whole point of Reed.