Today, the media business isn't necessarily seeing AI as much of an friend - a technology that has already been used to replace reporters with AI-generated copy, and other companies using AI to scoop up the work of journalists in order to feed their appetites for chatbots, without sending traffic back to the publisher as a search engine once did. But one startup, an AI newsreader called Particle from former Twitter engineers, believes that AI could serve a valuable role in the media industry-by helping consumers make sense of the news and dig deeper into stories-while still finding a way to support the publishers' businesses.

Particle was founded by Sara Beykpour, the former senior director of Product Management at Twitter, where she is working on the company's products such as Twitter Blue, Twitter Video, and conversations. The seed funding from the company amounts to $4.4 million. This spring, the company announced a $10.9 million Series A led by Lightspeed. It is joined by Marcel Molina, formerly of Twitter and Tesla as a senior engineer.

To the consumer, the concept of Particle is to better understand news using the help of AI technology. From being more than a summarizer that gives quick reads and bullets of stories for catch-ups on the fly, it offers a number of high smart features that allow you to consume the news in different manners.

But rather than taking work from publishers merely for Particle's own use, Particle intends to provide compensation to publishers or even drive traffic back to news sites by prominently showing and linking to sources right below its AI summarization.

For starters, Particle has partnered with specific publishers that feed it content from their APIs, including some outlets like Reuters, AFP, and Fortune. Such partners get more prominently positioned, and their links are highlighted in gold above others.

Already, beta tests indicate that readers are clicking through to publishers' sites because of the app's design and user interface, though that could shift now that the app is launching beyond news junkies to the general public. Over time, the company hopes to introduce other ways to work with the media as well, in addition to sending them referral traffic. The team also discusses availability with publishers of paywalled content in a mutually sensible way.
"Having deep partnerships and collaboration is one of the things that we're really interested in," says Beykpour.

To support its referral activities, the article section of the app features large tap targets that make it easy for readers to click through to the publisher's site. It also includes the face of journalists on their bylines, and readers can click through links to the profiles of publishers so they may read more of their works or follow them.

With the in-app AI tools, news users can flip between a different mode, like "Explain Like I'm 5," to get a simpler version of a complicated story or those that summarize "just the facts," (or the 5 W's — who, what, when, where, and why). You can have the news summed up in another language besides English, or even listen to an audio summary of a story or a personalized selection of stories while on the go. Particle also pulls out significant quotes from a story and other links of reference.

But two of the more interesting features involve how Particle uses AI to help frame the news from different angles and lets you delve deeper into the story at hand by asking questions.

In Particle, one tool called "Opposite Sides" tries to break users' filter bubbles by presenting different viewpoints from the same story. This model has been tried before by other news apps, including startup Brief and SmartNews. Unlike previous attempts, Particle includes a story spectrum that depicts how news is being covered across both "red" and "blue"-leaning sites, with bubbles placed to demonstrate how far to the left or right the news' positioning is, and how disproportionate the coverage may be from one side or the other. The AI will also summarize the positions of both sides, so news consumers can come to their own opinion of the matter.

But the killer feature is an AI chatbot that lets you ask questions and get instant answers about a story. The app will include suggested questions and those asked by others. For example, if you are reading about Trump's proposals on plans for his immigration policies, you might want to ask the chatbot such questions as "What are the potential legal challenges to Trump's deportation plans? " or "What are the potential costs of mass deportation?

" among others.

Particle will then use its AI technology to find those answers and fact-check them for accuracy.

The chat function uses OpenAI as well as…our own pre-processing and post-processing, Beykpour explains in an interview with TechCrunch. It uses the content, searches the web a little bit-if it wants to find extra information on the web-to generate those answers. She says that after the answer is generated, Particle includes an extra step where the AI has to go find the supporting material that matches those answers. In total, the app leverages emerging tech, such as OpenAI's GPT-4o and GPT-4o mini, Anthropic, Cohere, and many more, while also less pioneering AI from Google, which is not LLM-based.

"We have a processing pipeline that takes related content and summarizes it into bullet points, into a headline, sub-headline, and does all the extractions," she continues.

"Then…we pull out quotes and links and all sorts of relevant information about [the story].".

And we have our algorithms to rank, so that the most important or relevant link is the one that you see first -- or what we think is the most important or relevant quote is the one that you see first.

The company claims to be cutting AI accuracy problems that would otherwise occur one out of 100 times, cutting their chance to one out of 10,000 times. Particle will be using human editors as it scales, she says, to better manage the AI-created content and curate the company's homepage. For now, the app is free on iOS, and works across iPhone and iPad.