Leo and Summarization

Reading through a large number of articles every day can be time-consuming, especially if those articles are long.

Helping you save time is a problem we are very passionate about, so we are excited to release today a new Leo skill called Summarization.

We have taught Leo to read and summarize the articles in your feeds so that you can more efficiently scan through articles and determine which ones are relevant.


Leo automatically reads all the articles in your feeds and summarizes them.

Articles lists showcase those Leo summaries as articles descriptions

Leo summaries in article lists

When you open an article, Leo also highlights the key sentences which are part of the summary. The goal is to help you get to the key insights more efficiently.

Leo reads and highlights the most important sentences

Board newsletters and slack integration also take advantage of the Leo summaries for the article descriptions.

Available Now

The Leo Summarization skill is available now to all users in the Pro+ and Business plans.

If you prefer not to see the blue highlights, you can turn them off via the Leo Summary Highlights preference.

If you have feedback about the Leo Summarization skill, you are welcome to join the Feedly Lab slack channel and discuss it with the product team.

Leo and Topics

Broad business and tech publications produce hundreds of articles per week. Not all those articles are relevant to the topics, companies, or products you care about. Manually filtering out the noise can be overwhelming and time-consuming.

Relevance is a problem we are very passionate about. We have spent the last two years designing and building Leo, your AI research assistant to help declutter your feeds and save time.

Unlike black-box recommendation engines, Leo has a set of skills that let you define and control what is relevant to you.

We are excited to show you how the Leo Topic skill lets you track specific topics, companies, and keywords in your feeds.

Let’s get started!

Companies, People, and Products

Leo knows about all the companies, people, and products listed in Wikipedia and in the news. You can ask Leo to look for any of those named entities (and their known aliases) and prioritize articles that are a match.

You can, for example, look for mentions of your competitors or prospects in your industry or tech feeds.

Train Leo to prioritize mentions of Tesla across a set of trusted business sources

Smart Topics

Leo understands how to recognize articles about hundreds of “smart” topics (like artificial intelligence, cybersecurity, blockchain, energy, health, etc..). He’ll be looking for thousands of different terms related to that smart topic. We designed smart topics because an article can be about artificial intelligence without including the term “artificial intelligence”.

Train Leo to prioritize #AI across a set of broad business sources

We continuously teach Leo new smart topics. If there is a specific topic you would like to sponsor, please email leo@feedly.com

Keyword Matches

You can also ask Leo to look for exact matches of a keyword you are interested in. In this mode, Leo behaves like a saved search.

Train Leo to look for exact matches of the “downsizing” keyword in your business feeds

Composable with AND and OR

You can design more sophisticated priorities by combining multiple topics using AND and OR. AND means that both of the topics need to be present. OR means that either of the topics needs to be present.

Train Leo to look for mentions of DNA or CRISPER and cancer in your health industry feeds

Composable with Other Skills

The topic skill can be composed with all the other Leo skills allowing you, for example, to easily prioritize articles that reference a product launch (business event skill) while also being related to #artificial intelligence (topic skill)

Train Leo to prioritize product launch articles related to #AI

Or high severity software vulnerabilities (cybersecurity skill) related to docker (topic skill)

Train Leo to prioritize critical Docker vulnerabilities

Continuously Learning

You can use the Leo “less like this” down arrow to correct Leo when a topic detection is incorrect. This feedback is channeled to the Feedly ML Team and to the datasets used to train Leo, making topics increasingly more accurate and relevant over time.

Leo continuously learns from your feedback

Available Now

The Leo Topic skill is available now on both Web and Mobile for both Feedly Business and Feedly Pro+ users. We look forward to seeing how you train your Leo and how much time you can save.

If you have feedback about the Leo topic skill, you are welcome to join the Feedly Lab slack channel and discuss it with the product team.

Leo understands funding events, product launches, and partnership announcements

Industries are changing at a faster pace than ever. Keeping up with new threats and opportunities can be overwhelming and time consuming.

Today, we are excited to announce a new Leo skill that lets you easily track key business events like funding events, product launches, or partnerships.

Here is a quick demo

Funding Events

We have trained Leo to detect and understand funding events. This means that you can now ask Leo to read your tech, business or industry specific feed and prioritize articles related to funding events – saving you a tremendous amount of time.

Track funding events in your feeds

Product Launches

We have also trained Leo to detect and understand product launches.

Track product launch announcements in your feeds

This means that if you are part of a sales or sales enablement team, you can ask Leo to read TechCrunch or New York Times and notify you each time one of your customers or prospects launches a product. You can leverage that product launch event to create a warm approach and engage in a smart conversation.

Partnership Announcements

Finally, you can also easily prioritize the fraction of articles referencing partnership announcements.

Track partnership announcements in your feeds

Composable with other skills

The business event skill can be composed with all the other Leo skills allowing you, for example, to easily prioritize articles referencing a product launch (business event skill) and related to #artificial intelligence (topic skill).

Track funding announcements related to #artificial intelligence

Trained across 24 industries

Different industries use different vocabulary to describe these business events so we trained Leo across 24 different industries.

Leo’s industries

Continuously learning

You can use the Leo prompt or the “less like this” down arrow to correct Leo when the event detection is incorrect. This feedback is channeled to the Feedly ML team and to the datasets used to train Leo.

Tell Leo when he has detected a wrong event so that he can learn

Available now

The Leo business event skill is available on Web and Mobile now for Feedly Teams users. Because we have been getting a lot of Leo requests from non-Team users, we will also be launching a $12/month Pro+ plan in October which will include Leo, a Twitter integration, and all other Pro features.

If you have feedback about the Leo business event skill, you are welcome to join the Feedly Lab slack channel.

Design review of the upcoming Feedly Dark Theme

As part of the redesign of the Left Navigation bar, we are going to change the theme system on the Web to be more consistent with the theming on mobile: offering users the choice between a white theme and a dark theme.

Here is a preview of what the dark theme might look like

Upcoming Feedly Web Dark Theme

And here is the sister white theme

Upcoming Feedly Web White Theme

If you want to participate to the design review, please join the Feedly Lab Slack.

-Edwin, Gregoire, and Eduardo

Meet the New Feedly Dark Theme and Navigation Bar

We are excited to launch a new version of the Feedly Web UI that improves the navigation and add support for a cool dark theme. Here is a quick demo.

More visible Add Content (+)

The profile and add content are now more visible in a left band. Teams users will also be able to more easily add new teammates and share feeds and boards.

The new left band

Pin or unpin

You can continue to pin or unpin the navigation bar


Right-click Menus

You can right click on a feed, a source, a board, or a priority and use the contextual menu to quickly manage your resources.

Right-click on any oject

Easily rename inline

Renaming your feeds, sources, or boards is going to become a lot easier.

Rename inline

Drag and sort

Drag and drop and easily re-order your categories.

Drag and sort sections

This impacts both the order in the left navigation and the order of the sections in the Today page.

A Cool New Dark Theme

The day/night icon on the left band makes it easy to switch from the default white theme to the new cool dark theme.

Thank you!

We would like to thank Gregoire Vella for leading the design of these two projects. We are very excited to have Gregoire as part of the design team. He has a really sharp eye and he is a pleasure to work with.

We would also like to thank the Feedly Lab community and Twitter community for all the bugs and suggestions reported during the beta.

We are continuously shifting to a more open and collaborative process. If you are actively using Feedly and want to share ideas or frustrations, please join the Feedly Lab Community on Slack or Twitter.

Happy reading!


Feedly Mini for Chrome gets smarter in version 5

One million Feedly users rely on Feedly Mini to quickly add new sources to their feeds and save essential articles to their boards.

Saving insightful articles to your boards allows you to share and shine with your team and train Leo. The more articles you save to a board, the greater the accuracy of Leo’s like board priorities.

We are excited to announce a new version of the Feedly Mini Chrome browser extension that makes following sources and saving articles even easier.

Saving an article to one of your Feedly Boards

One of the popular feature requests for Feedly Mini was the ability to add a note to the article being saved to a board.

Quickly annotate and save web pages to one of your Feedly boards

In version 5, if you have access to the annotation features, you will be able to add a note to the article you are saving to your boards.

If you are part of Feedly Teams and have connected Feedly Teams with Slack, you will be able to mention a teammate or a Slack channel directly in Feedly mini and quickly notify your teammates.

Following a new source

We are also bringing the power of our new discovery experience to Feedly Mini v5.

Quickly follow a new source

Let’s imagine that you are browsing the Web and you discovered a new source you want to follow in Feedly.

When you click on the Feedly Mini icon, Feedly Mini will automatically discover the RSS feed for the page you are reading and show you a popup with information about that source.

You can click on Follow in Feedly to preview the RSS in Feedly and add it to one of your feeds.

You can also click on Explore to tap into the collective wisdom of the Feedly community and determine what are the sources that user often co-read with the source you are looking at.

No more having to look at the source page to find an RSS URL and manually searching for that URL to be able to add it to one of your feeds.

This is the first step for us to bring some of the work we are doing with Leo and discovery to Feedly Mini. Let us know what you think by joining the Feedly Lab Slack community and expect to see more in the next three to six months as Leo matures

How to Send Newsletters On Demand

There are some common questions about the “send now” feature for team newsletters. Here is a quick reference to guide you through the steps.

Sending newsletters on demand makes it easy to grab a snapshot of your team boards and feeds. We want to help your team move forward and save time!

Time is of the essence, so let’s review the steps and jump into your questions!

How To Send Now:

  1. Save new articles to your board (Nothing saved since the last email, the board won’t send now)
  2. Open your Newsletter dashboard
  3. Select the board or feed to send now
  4. Click send now
Newsletters are proving to be a useful tool for team collaboration.
Our teams use them internally, and we will keep building with your feedback in mind.

Thank you to all the teams who have sent questions, feedback, and bug reports!


Why didn’t I receive my newsletter? Common problems & solutions:

  • No new articles saved since the last newsletter sent. It will only send if there are new articles available (ie. saved) in the board.
  • Solution: For now, we suggest removing and then re-saving some articles to the board. After that, return to the newsletter dashboard and hit “send now” once again.
  • It works the same way the very first time you activate a newsletter and for your future scheduled newsletters.
  • Maybe the newsletter is in spam.
  • Solution: Please check your spam folder and add <teams@feedly.com> to your address book. That will tell your email provider to deliver newsletters to your inbox.

What articles will (or won’t) be included in the newsletter when I hit Send Now?

On-demand newsletters only include new articles saved since the last newsletter sent. This is the most common reason why a newsletter doesn’t send.

To send an on-demand newsletter with specific articles, we suggest removing and then re-saving those articles to the board. After that, return to the newsletter dashboard and hit “send now” once again.

What about analytics?

Coming soon 🙂

How do I add newsletters to my Feedly account?

We suggest starting a 30-day free trial of Feedly Teams. The trial gives you full access to newsletters and our support team. We are here to help you and your team get the most out of Feedly.

Thank you for trying newsletters! Have a question not answered here? Ask us in the comments or in the app.

— Victoria, Remi, and Emily

More posts about Newsletters:

Newsletter examples

Introducing Team Newsletters

All Newsletter tutorials 

New AI-Driven Discovery Experience

We love the Web because it is an open and distributed network that offers everyone the freedom and control to publish and follow what matters to them.

We also love the web because it has enabled a new generation of content creators (Ben Thompson, Bruce Schneier, Tina Eisenberg, Seth Godin, Maria Popova, etc.). Those independent thinkers continuously explore the edge of the known and share insightful and inspiring ideas with their communities.

Connecting people to the best sources for the topics that matter to them has been core to our mission since the very start of Feedly.

But discovery is a hard problem. The web is organic, a reflection of the global community’s changing needs and priorities. There are millions of sources across thousands of topics and we all have a different appetite when it comes to feeding our minds.

About twelve months ago, we created a machine learning team to see if the latest progress in deep learning and natural language processing could help us crack this nut.

Today, we are excited to give you a preview of the result of that work with the release of the new discovery experience in the Feedly Lab app (Experience 06).

Two thousand topics

The first discovery challenge is to create a taxonomy of topics.

You can think of Feedly as a rich graph of people, topics, and sources. To build the right taxonomy, we started with the raw data on all of Feedly’s sources. We had to create a model to clean, enrich, and organize that data into a hierarchy of topics. Learn more about the data science behind this.

The result is a rich, interconnected network of two thousand English topics. And it’s mapped well with how people expect to explore and read on the Web.

Some topics are broad: tech, security, design, marketing. Some are very niche: augmented reality, malware, typography, or SEO.

On the discovery homepage, we showcase thirty topics based on popular industries, trends, skills, or passions. You can access all of the topics in Feedly via the search box.

The fifty most interesting sources

The second discovery challenge is to find the fifty most interesting sources someone researching any topic might want to follow.

Ranking sources is hard because not all sources are equal. In tech as an example, you have mainstream publications like The Verge or TechCrunch, expert voices like Ben Thompson, and lots of B-list noisy sources which don’t add much value.

In addition, for niche topics like virtual reality, some sources are specific to VR while others cover a range of related topics.

To solve this challenge, we created a model which looks at sources through three different lenses:

  • follower count
  • relevance (how focused is the source on the given topic)
  • engagement (a proxy for quality and attention)

The outcome is new search result cards. You can explore the fifty most interesting sources for a given topic and sort them using the lens that is most important to you.


One of the benefits of the new topic model is that the 2,000 topics are organized in a hierarchy. This makes it easy for you to zoom in or out and explore many different neighborhoods of the Web.

For example, from the cybersecurity topic, you can jump to a list of related topics that let you dig deeper into malware, forensics, or privacy.

One more thing…

We have done a lot of research over the last four years to understand how people discover new sources. One insight we learned is that people often co-read certain sources. For example, if you are interested in art, design, and pop culture and you follow Fubiz, there is a high chance that you also follow Designboom.

With that in mind, we spent some time creating a model that learns what sources are often co-read. The idea is that a user could enter a source that they love and discover another source they could pair it with.

You can learn more about the machine learning model (we call it feed2vec) powering this experience through the article Paul published here.

As a user, you can access this feature by searching in the discover page for a source you love to read. The result will be a list of sources which are often co-read with that source.

Thank you!

I would like to thank Paul, Michelle, Mathieu, and Aymeric for the great research work they did to take this project from zero to one. People who have tried to tackle discovery know that it is a very hard challenge and the results of this project have been very impressive.

We would also like to thank the community for participating in the Battle of the Sources experiment. Your input was key in helping us learn how to model the source ranking. We are going to continue to invest in discovery and we look forward to continuing to collaborate with you.

We would also like to thank Dan Newman, Daron Brewood, Enrico, Joey, Lior, Paul Adams, Ryan Murphy, and Joseph Thornley from the Lab for reviewing an earlier version of this article.