Get the newsletter
Microsoft · AI / ML · Filed Jun 21, 2025 · USPTO published Nov 19, 2026 · This week's release

Microsoft Patents a Chatbot That Hands You to a Specialist AI Mid-Chat

A chatbot usually answers the same way whether you want a coach or a brainstorming partner. This Microsoft patent application would size up your first exchange, then move you to an AI trained for that kind of conversation.

A computer setup connects a person to an analysis system that tracks their goals and routes the chat to different AI models. Drawing from patent filing US 2026/0368185 A1.
A computer setup connects a person to an analysis system that tracks their goals and routes the chat to different AI models.All 13 drawings ↓
Publication number
US 2026/0368185 A1(US20260368185A1)
Applicant
MICROSOFT TECHNOLOGY LICENSING, LLC
Filed · Published
Jun 21, 2025 · Nov 19, 2026
Inventors
Bahareh SARRAFZADEH, Sheshera Shashidhar MYSORE, Debarati DAS
Status when we published
Approved; patent expected soon
Document
20 claims
US classification
707/722
Examiner
MENG, JAU SHYA (Art Unit 2168)
Parent application
Claims priority from a provisional application 63807738 (filed May 18, 2025)

What Microsoft's chatbot hand-off actually does

Every time you ask a chatbot for a draft and then reply 'make it funnier' or 'give me five more,' you are telling it what kind of help you want. Today, one all-purpose AI answers whether you are brainstorming, polishing a cover letter, or just saying thanks.

This Microsoft patent application describes a chatbot that watches for that pattern. After your first request and the reply, it works out what you are probably trying to do. Then it hands the rest of the chat to a different AI that was trained for people who behave that way. You do not have to pick anything.

Microsoft's approach starts with real chat logs. It sorts how people follow up after an answer into a handful of recurring habits, then links each habit to the kinds of first requests that tend to lead to it. Each habit gets its own specialist version of the AI, trained on its own slice of the logs.

From the filing · CLAIM 1
… selecting, based on the selected co-occurring pattern, a second AI model from a plurality of tailored AI models, each tailored AI model being fine-tuned to a respective co-occurring pattern using a segmented dataset corresponding to the respective co-occurring pattern …

Translation: The system picks a specialized chatbot that has been trained on past conversations matching what the user wants.

How follow-up habits pick the right AI model

The claims describe a system with a chat window that gives you access to a first AI model. It watches your opening prompt and the model's reply, and from those it detects your intent, meaning what you are really trying to get done.

That intent maps to a co-occurring pattern of follow-up types: a recurring mix of things people say next, like asking for more options, requesting a new style, or replying with thanks. The patterns come from logs of many users' chats, where AI classifiers labeled each message (the example uses eleven follow-up types and 18 intent labels). Principal Component Analysis (a statistics method that finds the main ways data varies) groups sessions with similar habits. A regression analysis (a test of which first requests predict which habits) then links them to intents.

Each pattern gets its own tailored AI model, fine-tuned (given extra training) on the slice of logs that matches it. When the system detects your intent, it picks the matching model and sends your further messages there without user intervention. The new replies show up in the same chat window.

Per the filing, the detection and routing can be done by a separate analysis engine or by the first model itself. The examples focus on writing tasks, though the filing says the idea can apply to other AI settings.

From the filing · THE ABSTRACT
Further user interaction is directed to a second AI model that is fine-tuned to the user intent based on a conversational history of interactions with a plurality of users.

Translation: The chat is handed off to a specialized expert bot automatically.

Why routing your chats could change AI answers

If it works, you would get help shaped to what you are doing, such as a coach that anticipates your questions or a brainstorming partner that offers ideas, without picking a mode or writing a long prompt. The filing also mentions replies tuned to the reader you are writing for, and to your own knowledge and style. Microsoft frames it as a better fit between person and AI, with fewer erroneous inputs and outputs and less wasted computing.

The patent office has approved this application, and once Microsoft pays the final fee it should be issued as a granted patent. It describes a design, not a product, and the filing names no specific Microsoft app.

That makes this Microsoft's 51st filing we've tracked since May in our AI teams working together watchlist, following applications like trimming specialist AI parts and rewriting chatbot instructions for safety.

Source: US 2026/0368185 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 2026/0368185 A1 · click any drawing to enlarge

How the system picks the best AI model, drawing sheet 1 from US 2026/0368185 A1
Sheet 1 How the system picks the best AI model
Mapping patterns in follow-up chats to predict user needs, drawing sheet 2 from US 2026/0368185 A1
Sheet 2 Mapping patterns in follow-up chats to predict user needs
Categories used to sort how people reply to AI answers, drawing sheet 3 from US 2026/0368185 A1
Sheet 3 Categories used to sort how people reply to AI answers
Writing goals the system detects in an opening message, drawing sheet 4 from US 2026/0368185 A1
Sheet 4 Writing goals the system detects in an opening message
Example chats requesting longer text or new styles, drawing sheet 5 from US 2026/0368185 A1
Sheet 5 Example chats requesting longer text or new styles
An example chat ending with simple polite thank-yous, drawing sheet 6 from US 2026/0368185 A1
Sheet 6 An example chat ending with simple polite thank-yous
Servers sharing prompt preferences across multiple user devices, drawing sheet 7 from US 2026/0368185 A1
Sheet 7 Servers sharing prompt preferences across multiple user devices
Connecting multiple gadgets to an AI during live group sessions, drawing sheet 8 from US 2026/0368185 A1
Sheet 8 Connecting multiple gadgets to an AI during live group sessions
Show the other 5 sheets
Internal parts of a device running the AI chat assistant, drawing sheet 9 from US 2026/0368185 A1
Sheet 9 Internal parts of a device running the AI chat assistant
How context and chat history feed into the server, drawing sheet 10 from US 2026/0368185 A1
Sheet 10 How context and chat history feed into the server
Steps for transferring your chat to a specialist AI, drawing sheet 11 from US 2026/0368185 A1
Sheet 11 Steps for transferring your chat to a specialist AI
Computer hardware that powers the AI handoff system, drawing sheet 12 from US 2026/0368185 A1
Sheet 12 Computer hardware that powers the AI handoff system
Cloud servers delivering chat services across connected gadgets, drawing sheet 13 from US 2026/0368185 A1
Sheet 13 Cloud servers delivering chat services across connected gadgets
Patent filing page

More in AI assistant & agent

All 436 AI assistant & agent 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.