Get the newsletter
Microsoft · AI / ML · Filed May 19, 2025 · USPTO published Nov 19, 2026 · This week's release

Microsoft Files Patent for an AI Ad Coach That Grades Its Own Advice

Microsoft's new patent application goes after a stubborn problem with AI business advice: people ignore it. Its answer is a second AI that predicts whether an advertiser will click the suggested button before the tip ever appears.

An advertising dashboard displays AI generated advice suggesting audience changes to improve marketing results. Drawing from patent filing US 2026/0368776 A1.
An advertising dashboard displays AI generated advice suggesting audience changes to improve marketing results.All 14 drawings ↓
Publication number
US 2026/0368776 A1(US20260368776A1)
Applicant
Microsoft Technology Licensing, LLC
Filed · Published
May 19, 2025 · Nov 19, 2026
Inventors
Shao Tang, Zhipeng Wang
Status when we published
Rejected again; the company can still amend or appeal
Document
18 claims
US classification
705/14.43
Examiner
PATEL, DIPEN M (Art Unit 3621)

What Microsoft's ad-advice scoring filing does

You're a marketing manager looking at your ad dashboard when a box pops up. It says to target a new audience for a 15% bump in clicks. The advice is clear and specific, and you hit "Dismiss" anyway.

Microsoft's filing says this happens a lot. The AI that writes the tip works in a vacuum. It has no idea that you care more about leads than clicks, or what you did with similar advice last month.

So the filing adds a checkpoint. After the first AI drafts a tip, a second AI predicts whether you will actually act on it. It bases that guess on your own past behavior and the state of your campaign. Tips that score high enough get shown, and the rest never reach you. When you do press the button, that click becomes new training material for the scorer.

From the filing · CLAIM 1
… sending a prompt to a generative artificial intelligence (AI) model, the prompt comprising the set of performance metrics and instructions for the generative AI model to generate a recommendation …

Translation: The system feeds campaign numbers and instructions into an AI to get suggestions.

How the scoring model judges each AI tip

The system starts with a campaign's report card: numbers such as impressions (how many times an ad was shown), click-through rate, conversion rate (how many viewers take a desired step) and qualified leads. Those numbers go into a prompt, a written instruction, sent to a generative AI model (a text-writing AI, like a chatbot). The model replies with a recommendation: advice text plus a conversion element, meaning a button such as "Create Audience" that the advertiser can press.

Before anyone sees it, a reward model scores the draft. Claim 1 has it take in three things: context data about the campaign, action data about what this advertiser has done before, and the original prompt. It turns each into embeddings (numeric summaries of meaning) using a self-attention layer (a technique that weighs which parts of the input matter most) and a causal self-attention layer (the same idea, reading in order). A cross-attention layer then blends the summaries together, and the model outputs one score predicting whether the button will get pressed.

The draft is shown only if the score clears a threshold. The filing also describes these extras:

  • Generating several drafts, ranking them by score, and showing the top one.
  • Adding each button press to the training data so the scorer is retrained over time.
  • Pulling in relevant documents to enrich the scorer's context.
  • Training the advice writer and the scorer together.
From the filing · THE ABSTRACT
… sending the recommendation to a reward model to generate a reward value for the recommendation, the reward value indicating whether the digital content information of the recommendation will cause the conversion element to generate an interaction event …

Translation: A second model evaluates the AI advice to predict if users will click on it.

What the final rejection means for Microsoft

If it works as described, an ad dashboard would show fewer tips you'd skip and more you'd act on, because each tip is screened against what you have done before. The filing's own example is a "Create Audience" suggestion promising a 15% click boost that an advertiser ignored, since their real goal was leads. The description sets this inside a professional networking platform's ad tool, though the claims are not limited to that.

A patent examiner has issued a final rejection of this application (status as of October 8, 2026). Microsoft can still amend the claims or appeal, so nothing here is settled. Treat it as a look at how the company thinks about making AI advice earn its place on your screen.

This is the 48th Microsoft filing we've tracked since May on AI models working in teams, following testing AI setups first and one model many specialties.

Source: US 2026/0368776 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 · 14 sheets

14 drawing sheets from US 2026/0368776 A1 · click any drawing to enlarge

How content servers deliver personalized feeds to user devices, drawing sheet 1 from US 2026/0368776 A1
Sheet 1 How content servers deliver personalized feeds to user devices
Inside the computer setup that processes AI tasks, drawing sheet 2 from US 2026/0368776 A1
Sheet 2 Inside the computer setup that processes AI tasks
Connecting ad campaign creators with users browsing content feeds, drawing sheet 3 from US 2026/0368776 A1
Sheet 3 Connecting ad campaign creators with users browsing content feeds
An advertiser dashboard showing AI advice to boost campaign performance, drawing sheet 4 from US 2026/0368776 A1
Sheet 4 An advertiser dashboard showing AI advice to boost campaign performance
Training the AI ad coach alongside a scoring model, drawing sheet 5 from US 2026/0368776 A1
Sheet 5 Training the AI ad coach alongside a scoring model
The scoring model that grades marketing suggestions, drawing sheet 6 from US 2026/0368776 A1
Sheet 6 The scoring model that grades marketing suggestions
Generating ad recommendations using scores from the evaluation model, drawing sheet 7 from US 2026/0368776 A1
Sheet 7 Generating ad recommendations using scores from the evaluation model
The language model design that generates text advice, drawing sheet 8 from US 2026/0368776 A1
Sheet 8 The language model design that generates text advice
Show the other 6 sheets
How the AI scores tips before showing the best one, drawing sheet 9 from US 2026/0368776 A1
Sheet 9 How the AI scores tips before showing the best one
Steps for grading advice before sending it to an advertiser, drawing sheet 10 from US 2026/0368776 A1
Sheet 10 Steps for grading advice before sending it to an advertiser
Retraining the scoring model based on real clicks, drawing sheet 11 from US 2026/0368776 A1
Sheet 11 Retraining the scoring model based on real clicks
A computer setup built to teach and test AI models, drawing sheet 12 from US 2026/0368776 A1
Sheet 12 A computer setup built to teach and test AI models
Feeding user reactions back into model training loops, drawing sheet 13 from US 2026/0368776 A1
Sheet 13 Feeding user reactions back into model training loops
Hardware parts inside a server running the ad system, drawing sheet 14 from US 2026/0368776 A1
Sheet 14 Hardware parts inside a server running the ad system
Patent filing page

More in AI recommendation

All 91 AI recommendation patents →

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.