Get the newsletter
Microsoft · AI / ML · Filed Feb 11, 2025 · USPTO published Aug 13, 2026 · Aug 13 release

Microsoft Patent Unveils Dual AI Model System for Smarter Content Suggestions

Microsoft has filed a patent for a system that uses two different AI models in sequence: a small, fast one to figure out what you might want to do with an image, and a much larger one to actually do it.

Various image inputs paired with relevant action suggestions generated by the dual AI system. Drawing from patent filing US 2026/0237196 A1.
Various image inputs paired with relevant action suggestions generated by the dual AI system.All 18 drawings ↓
Publication number
US 2026/0237196 A1(US20260237196A1)
Applicant
Microsoft Technology Licensing, LLC
Filed · Published
Feb 11, 2025 · Aug 13, 2026
Inventors
Biyi FANG, Yibo SUN, Xiao TU, Mengchen LIU, Dongdong CHEN, Victoria Yuantong CHEN
Status when we published
Waiting for an examiner
Document
20 claims
US classification
715/708

How Microsoft's two-AI approach handles image editing tasks

A document sits on your screen with a chart or a photo embedded in it. Your software needs to figure out what helpful things it could offer you to do with that image, and then carry out whichever one you pick.

Microsoft's patent describes splitting that job across two AI models. A small language model handles the quick, cheap part: reading the image and generating a short list of suggested actions, like "add a caption" or "rewrite this label." That list pops up in your interface almost immediately because the small model is fast and inexpensive to run. When you pick one, a much bigger, more capable AI model takes over and does the actual work.

The practical payoff is that you don't wait for a massive AI to slowly think about what to offer you before anything appears on screen. The heavy lifting only kicks in when you've already told the system what you want.

From the filing · CLAIM 1
… the first request includes a first prompt that tasks a small language model of the content generation service with generating the action suggestions based at least on the content in the image file …

Translation: The system uses a lightweight AI to quickly look at your image and suggest relevant tasks you might want to perform.

How the small model scouts and the large model executes

The patent describes an augmentation service that sits between a client application (say, a document editor) and a cloud-based AI platform.

When you open a file containing an image, the augmentation service sends a prompt to a small language model (SLM), essentially a lighter, faster AI, asking it to look at the image content and produce a menu of relevant suggested actions. The SLM is chosen here deliberately: it's cheaper to query, responds quickly, and doesn't need to do complicated generative work, just produce a short structured list.

Once you select an action from that list, the service fires a second request, this time to a large language model (LLM), the kind of heavyweight AI better suited to open-ended, nuanced generation tasks. The LLM then actually performs the chosen action, whether that's rewriting text, generating a description, or transforming content in some other way.

  • First request: SLM reads the image, returns candidate actions
  • User picks an action from the displayed list
  • Second request: LLM executes the selected action

This two-step architecture means the expensive model only runs after you've committed to a choice, rather than speculatively generating everything upfront.

From the filing · THE ABSTRACT
The second request includes a second prompt that tasks a large language model (LLM) to perform the selected action.

Translation: Once you pick a suggestion, a more powerful AI model takes over to actually carry out the work for you.

What this means for AI features in Microsoft's Office apps

For anyone using AI-assisted editing tools, the difference between a system that feels instant and one that feels sluggish often comes down to when the heaviest computation runs. By front-loading a lightweight model for the suggestion step, Microsoft's approach could make AI action menus feel responsive rather than like a spinning wheel. You'd see options quickly, pick one, and only then does the system call in the expensive model.

This kind of tiered architecture also has real cost implications for Microsoft at scale: SLM queries are a fraction of the price of LLM queries, so offloading the "what should I offer?" question to a smaller model is straightforwardly cheaper to run across millions of users. The pattern shows up across new Big Tech patents in the AI-assisted productivity space, where companies are racing to make generative features feel fast enough to use mid-task rather than as an afterthought.

Source: US 2026/0237196 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 · 18 sheets

18 drawing sheets from US 2026/0237196 A1 · click any drawing to enlarge

Architecture of augmentation service system, drawing sheet 1 from US 2026/0237196 A1
Sheet 1 Architecture of augmentation service system
Action suggestion generation process steps, drawing sheet 2 from US 2026/0237196 A1
Sheet 2 Action suggestion generation process steps
Message sequence for suggestion requests, drawing sheet 3 from US 2026/0237196 A1
Sheet 3 Message sequence for suggestion requests
Training process for small language model, drawing sheet 4 from US 2026/0237196 A1
Sheet 4 Training process for small language model
Dataflow for model training and optimization, drawing sheet 5 from US 2026/0237196 A1
Sheet 5 Dataflow for model training and optimization
Example images used for testing, drawing sheet 6 from US 2026/0237196 A1
Sheet 6 Example images used for testing
Content suggestions generated from image inputs, drawing sheet 7 from US 2026/0237196 A1
Sheet 7 Content suggestions generated from image inputs
Context menu interaction for suggestions, drawing sheet 8 from US 2026/0237196 A1
Sheet 8 Context menu interaction for suggestions
Show the other 10 sheets
Microsoft Patent Unveils Dual AI Model System for Smarter Content Suggestions patent drawing, sheet 9
Sheet 9
Microsoft Patent Unveils Dual AI Model System for Smarter Content Suggestions patent drawing, sheet 10
Sheet 10
Microsoft Patent Unveils Dual AI Model System for Smarter Content Suggestions patent drawing, sheet 11
Sheet 11
Microsoft Patent Unveils Dual AI Model System for Smarter Content Suggestions patent drawing, sheet 12
Sheet 12
Microsoft Patent Unveils Dual AI Model System for Smarter Content Suggestions patent drawing, sheet 13
Sheet 13
Microsoft Patent Unveils Dual AI Model System for Smarter Content Suggestions patent drawing, sheet 14
Sheet 14
Microsoft Patent Unveils Dual AI Model System for Smarter Content Suggestions patent drawing, sheet 15
Sheet 15
Microsoft Patent Unveils Dual AI Model System for Smarter Content Suggestions patent drawing, sheet 16
Sheet 16
Microsoft Patent Unveils Dual AI Model System for Smarter Content Suggestions patent drawing, sheet 17
Sheet 17
Microsoft Patent Unveils Dual AI Model System for Smarter Content Suggestions patent drawing, sheet 18
Sheet 18
Patent filing page

Watchlists this filing belongs to

All watchlists →