How AI Checks Documents for Policy Rules and Compliance
This patent describes a system where an AI model helps evaluate parts of a document against specific rules or policies given in plain language, then identifies problems or suggests fixes to ensure compliance.
Original patent title: “Large language model artificial intelligence text evaluation system”
This patent describes a system where an AI model helps evaluate parts of a document against specific rules or policies given in plain language, then identifies problems or suggests fixes to ensure compliance. Granted to Casetext in 2025 with 23 claims, and it is expected to expire in 2044.
Coverage
What does this patent actually cover?
The system first takes a document and divides it into smaller "text portions." It then compares these portions against specific rules, called "criteria," which are provided in everyday language (natural language) (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1). A processor selects a subset of the most relevant text portions, often by determining relevance scores (Claim 1, 5). Next, it creates special questions, or "criteria evaluation prompts," for a large language model (LLM) by combining the natural language criteria and the selected text (Claim 1). The LLM then generates new text by following the instructions in these prompts (Claim 1). This newly generated text is then evaluated to find any "noncompliance" with a "designated policy" (Claim 1). Finally, the system sends a message to a user, identifying the noncompliance (Claim 1) or even suggesting how to revise the document to become compliant (Claim 3). For example, a legal department could use this to automatically check if a contract draft adheres to specific company guidelines by feeding the guidelines as criteria and the contract as the document.
The gap
What does this patent NOT cover?
- Evaluating an entire document without first selecting a subset of relevant text portions based on criteria (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1 requires selecting a subset).
- Systems that do not use a generative language model to create "novel text" as part of the evaluation process (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1 specifies determining novel text generated by a generative language model).
- Identifying noncompliance without evaluating the *novel text* generated by the LLM (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1 states "identifying an instance of noncompliance... by evaluating the novel text").
- Systems that only provide a relevance score for text portions without also identifying policy noncompliance based on LLM-generated evaluation (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1 requires identifying noncompliance and transmitting a response).
- Evaluating text against criteria that are *not* specified in natural language (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1 specifies "one or more criteria specified in natural language").
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The noveltynoveltyThe requirement that an invention be different from anything publicly known before its priority date.Read more → lies in using a generative language model not just to find relevant text, but to generate novel text by executing an instruction to evaluate the selected text against criteria, and then evaluating that generated text to identify policy noncompliance. This moves beyond simple keyword matching or sentiment analysis by having the AI actively interpret and explain compliance.
The Patent Drawing
Schematic visualization of the patent's claim structure. Hand-drawn diagrams in progress for each landmark patent.
Where you've seen this
Real-world examples
Automated legal document review platforms
Contract compliance checking software
Regulatory policy adherence verification tools
Internal policy auditing systems
Content moderation tools for platform guidelines
Why it matters
The bigger picture
This technology is important for automating compliance checks and document review in fields that deal with large volumes of text and complex rules. It aims to make processes faster and more accurate by leveraging advanced AI models to understand and apply nuanced policy criteria. This could significantly reduce manual effort and human error in sectors like legal, regulatory, and corporate governance.
Filed
April 19, 2024
Granted
May 13, 2025
Market context
Who's building on this
Companies in this space
Casetext, the assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, is a legal technology company that actively uses AI for legal research and document review, notably with their CoCounsel product. Other major players in AI-driven document analysis and compliance include Thomson Reuters and LexisNexis. The underlying generative language models are provided by companies like OpenAI, Google, and Microsoft, which are foundational for systems like this patent describes.
Market impact
This patent addresses a significant need across industries like legal, finance, and healthcare for automated compliance and document review. It contributes to the growing trend of using advanced AI to reduce human error and improve efficiency in processing complex textual information. The market for AI-powered legal and compliance tools is rapidly expanding, driven by the capabilities of large language models to understand and interpret nuanced rules, potentially reshaping how businesses manage risk and ensure adherence to regulations.
Claim 1 — Plain English
What this patent covers
The system first takes a document and divides it into smaller "text portions." It then compares these portions against specific rules, called "criteria," which are provided in everyday language (natural language) (Claim 1). A processor selects a subset of the most relevant text portions, often by determining relevance scores (Claim 1, 5). Next, it creates special questions, or "criteria evaluation prompts," for a large language model (LLM) by combining the natural language criteria and the selected text (Claim 1). The LLM then generates new text by following the instructions in these prompts (Claim 1). This newly generated text is then evaluated to find any "noncompliance" with a "designated policy" (Claim 1). Finally, the system sends a message to a user, identifying the noncompliance (Claim 1) or even suggesting how to revise the document to become compliant (Claim 3). For example, a legal department could use this to automatically check if a contract draft adheres to specific company guidelines by feeding the guidelines as criteria and the contract as the document.
The clever bit
The novelty lies in using a generative language model not just to find relevant text, but to generate novel text by executing an instruction to evaluate the selected text against criteria, and then evaluating that generated text to identify policy noncompliance. This moves beyond simple keyword matching or sentiment analysis by having the AI actively interpret and explain compliance.
What it does not cover
- Evaluating an entire document without first selecting a subset of relevant text portions based on criteria (Claim 1 requires selecting a subset).
- Systems that do not use a generative language model to create "novel text" as part of the evaluation process (Claim 1 specifies determining novel text generated by a generative language model).
- Identifying noncompliance without evaluating the *novel text* generated by the LLM (Claim 1 states "identifying an instance of noncompliance... by evaluating the novel text").
- Systems that only provide a relevance score for text portions without also identifying policy noncompliance based on LLM-generated evaluation (Claim 1 requires identifying noncompliance and transmitting a response).
- Evaluating text against criteria that are *not* specified in natural language (Claim 1 specifies "one or more criteria specified in natural language").
Patent timeline
Application submitted to the patent office
Application published, typically 18 months after filing
Patent officially issued
Patent enters public domain
PatentBrief Score
Impact Score
Early stage
Citation count
0/40
No citations yet
Claim breadth
15/20
Broad claimsclaimsThe numbered statements at the end of a patent that legally define what the inventor owns.Read more →
Recency
20/20
Granted within 5 years
Assignee scale
0/20
Independent or smaller assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →
PatentBrief Impact Score — based on citation count, claim breadth, recency, and assignee scale. Not a legal assessment.
Heuristic Value Estimate
What this patent might be worth
$47K – $150K
Midpoint $94K · 17.7 yr remaining · industry ×1.6
Heuristic only — blends forward/backward citation counts, claim scope, time remaining, litigation history, and CPC-derived industry baseline. Real valuations need a professional appraisal.
Claim text not yet imported for this patent
The original legal language
Original claims
23 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
DeFoor, W., Arredondo, P., Walker, R., deLevie, A., Qadrud-Din, J., O'Kelly, B., & Blake, E. (2025). How AI Checks Documents for Policy Rules and Compliance (U.S. Patent No. 12,299,406). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/12299406/large-language-model-artificial-intelligence-text-evaluation-system
Auto-generated from the patent record. Double-check author order and the issue date against the official USPTO document before submitting.
Embed
Add this patent to your site
Drop this plain-English patent card into any blog post or article — free, no signup. It always links back to the full breakdown here.
<div data-patentlens-widget data-patent-number="US12299406"></div> <script src="https://patentbrief.org/embed.js" async></script>
Stay in the loop
Get a weekly digest of new patents.
One email per week. No spam. Unsubscribe anytime.
Keep exploring
Related patents you should know
US 4683195 · 1987
How to Make Billions of Copies of a DNA Segment
This patent describes the Polymerase Chain Reaction (PCR), a method to rapidly create many copies of a specific piece of DNA or RNA, enabling its detection and analysis.
Cetus Corp
US 8697359 · 2014
How to Edit Genes in Human Cells Using an Engineered CRISPR System
This patent describes an engineered CRISPR-Cas9 system for precisely cutting DNA in eukaryotic cells to change how genes work, opening the door for gene editing in complex organisms.
Massachusetts Institute of Technology
US 7657849 · 2010
How the iPhone's Slide-to-Unlock Gesture Works
Apple's 2010 patent describes unlocking a device by dragging a specific graphical image across the touchscreen along a predefined path, a gesture that became iconic with the original iPhone.
Apple Inc
US 4733665 · 1988
How Doctors Implant a Permanent Stent Using a Balloon
This patent describes the method for placing a permanent, expandable wire mesh tube inside a blood vessel or other body tube using a balloon-tipped catheter to widen it and keep it open.
Expandable Grafts Partnership
US 4965188 · 1990
How to Make Many Copies of a DNA Piece with Heat
This patent describes the Polymerase Chain Reaction (PCR) method, a technique to make millions of copies of a specific DNA segment using a heat-resistant enzyme and repeated temperature changes.
Cetus Corp
US 4235871 · 1980
How to Encapsulate Active Materials in Lipid Bubbles Efficiently
This patent describes a method for trapping biologically active substances inside tiny, multi-layered fat bubbles called liposomes, using a specific water-in-oil emulsion and gel-forming process to improve how much material gets captured.
Individual
More to explore
More in Software & Internet
US 4405829 · 1983 · Massachusetts Institute of Technology
How RSA Public-Key Encryption Keeps Digital Messages Secret
US 6285999 · 2001 · Leland Stanford Junior University
How Websites Get Ranked by Importance
US 5960411 · 1999 · Amazon com Inc
How Amazon's One-Click Ordering Works for Online Purchases
US 7669123 · 2010 · Facebook Inc
Displaying Friends' Activities in a Social Network Feed
New to patents?
Common Questions
Frequently Asked Questions
What does How AI Checks Documents for Policy Rules and Compliance cover?
This patent describes a system where an AI model helps evaluate parts of a document against specific rules or policies given in plain language, then identifies problems or suggests fixes to ensure compliance.
Who owns patent US 12299406?
Casetext owns this patent, granted in 2025.
When does this patent expire?
This patent is expected to expire on April 19, 2044, when the invention enters the public domain.
What problem does this patent solve?
This technology is important for automating compliance checks and document review in fields that deal with large volumes of text and complex rules. It aims to make processes faster and more accurate by leveraging advanced AI models to understand and apply nuanced policy criteria. This could significantly reduce manual effort and human error in sectors like legal, regulatory, and corporate governance.
What does this patent NOT cover?
Evaluating an entire document without first selecting a subset of relevant text portions based on criteria (Claim 1 requires selecting a subset).
Patent monitoring