Patent professionals spend hundreds of hours on prior art searches and freedom-to-operate analyses. KTH Law's PatentWorkflow AI is a free, open-source web application that generates production-ready n8n workflow configurations - turning complex, multi-step patent analysis into automated pipelines powered by large language models.

 

PatentFlow AI landing page: configure Prior Art and FTO workflows

 

Prior Art Search FTO Analysis

The Prior Art workflow automates the discovery
of existing patent disclosures relevant to a new
invention. It begins with AI-driven feature
extraction from product specifications, then
queries multiple patent databases - PQAI,
SerpAPI, Google Patents - using semantically
expanded search terms.

The Freedom to Operate workflow determines
whether a product may infringe existing patent
claims. Unlike prior art search, FTO is claimcentric
- it maps product features directly to
structured claim elements and quantifies
infringement risk.
1. Feature Extraction - structured technical features from specs 1. Feature-to-Claim Mapping - functional similarity analysis
2. Query & Retrieval - multi-source patent database search 2. Claim Parsing - structured decomposition of limitations
3. Iterative Filtering - semantic similarity and CPC/IPC overlap 3. Coverage Analysis - full match, partial overlap, or no match
4. Disclosure Analysis - feature-to-patent evidence mapping 4. Legal Review - risk assessment and design around options
5. Human Review - attorney validation and strategy  

 

The Workflow Builder

The visual Workflow Builder provides an intuitive interface for configuring patent analysis parameters. Users select the workflow type, enter product details, choose an AI model (GPT-5/GPT-5.2, Claude 4.6, etc.), pick patent data sources, and generate production-ready n8n JSON - downloadable with a single click.

 

Workflow Builder: configure parameters and generate n8n JSON for import

 

Getting Started

PatentFlow AI is completely free and open source. No account required - visit the web app, configure your workflow, and download the n8n JSON.

  1. Visit patent-n8n-flows.lovable.app
  2. Choose Prior Art Search or FTO Analysis
  3. Enter product name and technical features
  4. Select AI model and patent data sources
  5. Generate and download n8n workflow JSON
  6. Import into n8n and configure API
    credentials
  7. Activate/publish

 

You can also fork the project from github:

AVAILABLE ON GITHUB Fork it. Extend it. Contribute workflows: github.com/kthlaw/patent-n8n-flows

 

About the Author and Firm

This analysis is provided by Kama Thuo, PLLC, an engineering & technology law firm focused on patents, AI, and wireless telecom law. Brian Kibet is a multidisciplinary professional with expertise in wireless engineering, paralegal practice, and software development. With a strong background in AI and automation, he designs intelligent workflows for intellectual property processes, with a focus on patent-related work, bridging the gap between technical innovation and legal strategy.

Whether you are an inventor seeking to license your technology or a company navigating an IP dispute, our firm has the technical and legal expertise to protect your interests. Reach out to us to see how we can assist you at www.kthlaw.com/patents, or explore our AI-powered legal services at https://www.kthlaw.com/ai.