Fine-tune your Feedly AI Feeds with Natural Language Filters

15 Second-summary

Feedly AI Feeds are already powerful, but what if you could fine-tune them even further? Introducing Natural Language Filters—a new way to refine your feeds with precise, natural language queries on top of our AI Models.

With Natural Language Filters, you can:

Zero in on highly specific niche topics.
Filter by dollar amounts, percentages, and other numerical data.
Focus on directional relationships (e.g., which company acquired whom).
Ensure entities are truly connected in context, not just mentioned together.

Cut through the noise like never before—Feedly’s AI Feeds are now sharper, smarter, and more tailored to your research needs.

Introducing Natural Language Filters

Finding the right information in a sea of data is challenging. That’s why we’re introducing Natural Language Filters—a new way to fine-tune your Feedly AI Feeds with precise, natural language queries. Whether you need to track highly specific niche topics, filter by numerical values, or pinpoint directional relationships, Natural Language Filters give you unparalleled control over your results. Now, you can ensure the articles you surface are not just relevant but highly precise—helping you cut through the noise and focus on what truly matters.

Zero in on highly specific and niche topics

Researching niche topics can be challenging, even for the most well-crafted AI Feeds. While combining AI Models can help focus your query, the results can still be noisy. By adding a Natural Language Filter to an AI Feed, you can narrow in on articles about niche topics that are not currently supported by the AI Model library. For instance, you can create an LLM filter to surface results about specific products or models of a specific product.

You can also exclude topics from the feed by adding a “NOT” Natural Language Filter to remove unrelated content that could be cluttering your feed. For instance, you can exclude products you don’t compete against from an AI Feed that tracks competitor’s moves.

Filter by dollar amount, percentage or numerical data

While Feedly’s AI Models help analysts identify complex topics like industries, strategic moves, and companies, they were not designed to identify specific numbers or figures. However, with the new Natural Language Filters, analysts can now search for numbers as well as specify greater than and less than, percentages, or date ranges.

Focus on directional relationships

Specify the direction of transaction you care about and only surface articles that meet that criteria. For instance, you can narrow your trade search to only goods being exported from the United States into Mexico and Canada.

Ensure entities are truly connected in context, not just mentioned together

Specify the exact relationship you want to see between entities in you AI Feed. Often, multiple strategic events are listed in a single article, and both entities you care about may be mentioned throughout the article but not in relation to each other. With a Natural Language Filter, you can specify exactly how you wish the entities to be connected.

Final Thoughts

Natural Language Filters complement rather than replace AI Models, helping to refine your AI Feeds. While AI Models typically deliver superior results, Natural Language Filters provide a precise final adjustment to sharpen your focus, particularly when an AI Model returns broader results than your specific intelligence requirements demand.