Get the newsletter
Microsoft · AI / ML · Filed Jul 23, 2026 · USPTO published Nov 19, 2026 · This week's release

Microsoft Files Patent for Web Searches That Come Back as a Written Report

Search 'best time to visit Hawaii' and this Microsoft system would run several extra searches you never typed, pick the best results, and write you a cited report.

A search engine results page formatted as an organized research report with a table of contents, written answers, and source citations. Drawing from patent filing US 2026/0368190 A1.
A search engine results page formatted as an organized research report with a table of contents, written answers, and source citations.All 13 drawings ↓
Publication number
US 2026/0368190 A1(US20260368190A1)
Applicant
Microsoft Technology Licensing, LLC
Filed · Published
Jul 23, 2026 · Nov 19, 2026
Inventors
Mohamed Salman Ismail GADIT, Elbio Renato Torres ABIB, Andrew Peter OAKLEY, Nathan James CHALMERS, Ming GONG, Wenbiao DING, Aparna RAJARAMAN, Baoquan FAN, Lile PALMA HATTORI
Status when we published
Waiting for an examiner
Document
20 claims
US classification
707/726
Parent application
Continuation of 19/067,307 (filed Feb 28, 2025)(19067307)

What Microsoft's report-style search does

When you search the web today, you mostly get a list of links, plus a quick answer for popular topics. The rest is on you: opening tabs, skimming pages, and piecing together what's true. Microsoft's patent application describes a way for the search engine to do that reading for you.

Say you search for best time to visit Hawaii. The system first works out what you're really after, then runs extra searches of its own, like the cheapest time to travel, when the weather is best, and when events happen. It gathers hundreds of results, keeps the top handful, and has AI write a short answer plus several topic sections, each with links back to its sources.

Only harder questions get this treatment. A search like 'youtube' or '2+2' just gets normal results. The filing's goal is to deliver the whole report in under 10 seconds.

From the filing · CLAIM 1
… determining a search intent associated with the search query; determining multiple related queries for the search query based on the set of initial search link results and the search intent; …

Translation: The system figures out what you actually mean and thinks up follow up questions based on the initial links.

How the extra searches get ranked and written

The system starts with a normal search. It pulls a first list of links from the search index, then hands the query and those links to a small AI model (a compact model, about 1.5 billion settings in the filing's example, trained for one narrow job). That model works out the search intent, meaning what you're really trying to find out.

Next, a second small model creates related queries, which the filing calls fan-out. Each one runs against the index in parallel. In the filing's example, 5 related queries bring back 250 extra results. A third small model scores them against your intent and keeps the top 5 or 10 as the 'enhanced' results.

Then several jobs overlap:

  • A complexity score decides whether the question deserves a full document at all.
  • Another model writes a one or two sentence directed answer at the same time.
  • Several copies of a section-writing model draft topic sections in parallel, with cited links.
  • Lightweight checkers remove repeated content, inaccurate claims and broken image links, and enforce safety rules.
  • A layout model adds matching answer cards (short, targeted answers) and arranges the page.

The filing says doing these steps one at a time could take over a minute. Overlapping them aims for under 10 seconds.

From the filing · THE ABSTRACT
… utilizes search results to determine intent, generate a directed answer, curate topic sections, and create a generative search results document for the search query.

Translation: It reads through web links to write a custom answer organized into neat sections just for you.

Why Microsoft's cited-report search could matter

For you, this points to a search page that reads like a short briefing on research-style questions, with sources attached so you can check the claims. The regular links stay on the page, so you can still go read the originals.

For Microsoft, the pitch is cost and speed. Search runs at huge volume, and the filing leans on small, specialized models that use less computing power than large ones. It also describes skipping simple queries and reusing a finished document when the same search comes back with similar results. That keeps the expense of AI-written answers in check.

This is the 36th Microsoft filing we've tracked since July on our AI agents that act for you watchlist, adding to earlier work like one screening what the AI reads and one fixing networks from manuals.

Source: US 2026/0368190 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Microsoft patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 13 sheets

13 drawing sheets from US 2026/0368190 A1 · click any drawing to enlarge

How AI turns web results into a full report, drawing sheet 1 from US 2026/0368190 A1
Sheet 1 How AI turns web results into a full report
Connected servers and AI models that assemble your search document, drawing sheet 2 from US 2026/0368190 A1
Sheet 2 Connected servers and AI models that assemble your search document
Steps taken behind the scenes to write a customized answer, drawing sheet 3 from US 2026/0368190 A1
Sheet 3 Steps taken behind the scenes to write a customized answer
Figuring out your question's goal to trigger follow-up web searches, drawing sheet 4 from US 2026/0368190 A1
Sheet 4 Figuring out your question's goal to trigger follow-up web searches
Scoring and sorting the best web links for your report, drawing sheet 5 from US 2026/0368190 A1
Sheet 5 Scoring and sorting the best web links for your report
Deciding whether a search query needs a written summary, drawing sheet 6 from US 2026/0368190 A1
Sheet 6 Deciding whether a search query needs a written summary
Writing distinct report sections and screening out errors, drawing sheet 7 from US 2026/0368190 A1
Sheet 7 Writing distinct report sections and screening out errors
Pairing visual cards with the final document on your screen, drawing sheet 8 from US 2026/0368190 A1
Sheet 8 Pairing visual cards with the final document on your screen
Show the other 5 sheets
Entering a question into the deep search box, drawing sheet 9 from US 2026/0368190 A1
Sheet 9 Entering a question into the deep search box
Showing progress while the AI builds a detailed report, drawing sheet 10 from US 2026/0368190 A1
Sheet 10 Showing progress while the AI builds a detailed report
Reading the completed research document and its sources, drawing sheet 11 from US 2026/0368190 A1
Sheet 11 Reading the completed research document and its sources
Steps the system takes to assemble a written report, drawing sheet 12 from US 2026/0368190 A1
Sheet 12 Steps the system takes to assemble a written report
Computer parts that power the document generator, drawing sheet 13 from US 2026/0368190 A1
Sheet 13 Computer parts that power the document generator
Patent filing page

Watchlists this filing belongs to

All watchlists →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.