Introducing Smart search: turn any material into an effective prior art search

Today we're launching Smart search, our latest feature designed to respond to everyday realities and how patent professionals actually work. Smart Search accepts any combination of materials: text, images, PDFs, Microsoft Office documents, and uses AI to synthesize them into a search query representative of their technical content. This eliminates the need to manually piece together information from different sources, letting you work flexibly with whatever materials you have. Smart search is also a critical building block for the automated novelty search workflows in the forthcoming IPRally Agent.

What is Smart search?

Patent search rarely starts with a single, perfectly formatted text description. More often than not, you're working with an invention disclosure form, a few images, PowerPoint slides with text, images, flowcharts, etc explaining the concept, and perhaps some additional notes, all scattered across different files. Until now, searching with these diverse materials meant first studying the materials in detail, defining the essence of the invention or technology, and manually synthesizing everything into text or Boolean queries.

Smart search lets you use multiple files, formats and modalities to launch a search quickly. Simply drag and drop more or less any search materials and let the AI synthesize them into a single rich AI search query. This simplifies the beginning of the search workflow significantly and creates a comprehensive, more complete search input. 

In line with our transparency and trust-building goals, the user will also see how the AI understood each single information source, and what the query is: we present it in an intuitive patent claim format with the most essential features in a first “claim” and optional or preferred features in dependent “claims”. The query is also editable for maximum control.

Another reason for using claim-format queries is that IPRally's proprietary patent retrieval AI has been trained specifically on claims, making them the optimal format for accurate AI-powered patent searches.

Ideal use cases

Smart search is particularly valuable for:

Novelty and patentability searches: When you create or receive an invention disclosure in any format, you can run the first prior art search for it extremely quickly.

State of the art analysis: Upload research papers, manuscripts, images from competitors' products, and your own technical notes to build a comprehensive search query that captures key aspects of the technology.

Freedom to operate studies: Run a quick search with product specifications, prototype images, or other technical documentation to search for potential blocking patents across multiple dimensions of your product.

R&D intelligence: Researchers can upload experimental results, prototype images, and technical descriptions to quickly understand the patent landscape around their innovations.

Infringement and Evidence of Use analyses: Upload material covering a potentially competing product or process, filter the results to your own portfolio, and spot intellectual property to improve your business or negotiation position.

__wf_reserved_inherit

How Smart search works

The workflow is straightforward:

1. Add your materials
Drag and drop or select multiple files from the following formats:

  • Images (PNG, JPG, WEBP)
  • PDFs
  • Word documents (DOCX)
  • PowerPoint presentations (PPTX)
  • Spreadsheets (XLSX)

Add any additional text description you want to include, or give some brief context or instructions. 

2. Let AI study and process the materials
Smart search uses large language models to analyze each file individually, extracting relevant technical information. You can see exactly how the Smart search interpreted each file, giving you full transparency into the process.

3. Review (and edit) the search query
Just like with our Free text search, you'll see the AI-generated search query (mock claim) built from all your input materials. You can review it, edit it if needed, and then re-run the search.

4. Get results
Review your search results as usual, with the confidence that all your input materials have been considered comprehensively.

__wf_reserved_inherit

This approach ensures you maintain full control and visibility throughout the process while letting AI handle the heavy lifting of synthesizing diverse materials.

Watch Smart search in action

What to know about Smart search

  • Free text search remains available: For users who prefer a non-Gen AI search option, our traditional Free text search continues to be available and fully supported. 
  • Image search has been phased out since Smart search covers these features as an improved, more flexible version.
  • The Refine button in Free text search will be phased out in the near future since Smart search can perform the same functionality in a more powerful way.
  • Supported file formats: The formats listed above cover most situations. Support for additional formats like video and audio files may be added in the future. Let us know your needs!
  • AI processing visibility: You'll always see what information was extracted from your files before the final search query is generated. This transparency ensures you can verify the AI's interpretation and make adjustments if needed. 
  • Editable queries: The AI-generated search query in claim format is always editable. You have full control to adjust emphasis, add specific terminology, or refine the scope before running the search.
  • The search graph will be viewable, but not editable in Smart search. We recommend editing the claim-format query, in case you need to adjust the target of the search. Copying the claims into the Free text search, will allow graph-level control, if needed.

Smart search is built on our existing Generative AI infrastructure and follows the same careful approach to AI assistance that we use in features like Ask AI and Smart filters.

Looking ahead

Smart search is a significant step toward our vision of transparent fully automated patent search workflows. By enabling AI to work with diverse input materials, we're laying the groundwork for future capabilities. The same search workflow and multi-format input capability will be provided as a starting point of our novelty search Agent, out soon.

Join our webinar to see Smart search in action

We're hosting a webinar on January 22 where we'll demonstrate Smart search and show you how to get the most out of this new capability. You'll see real-world examples, learn best practices, and have the chance to ask questions. Register here.

Learn more in the help center

For step-by-step guidance on using Smart search, including supported file types and best practices for reviewing and refining queries, see our Help center.

Try Smart search today

Smart search is available now for all IPRally users. Start your free trial to experience how Smart search, along with features like Projects, Ask AI, and Smart filters, can transform your patent search workflow.

‍

‍

‍

‍

Read more

Thank you to everyone who joined No more drafting in the dark: prior-art-aware patent drafting with IPRally Protection. Across our EU and US sessions, you sent us more than 80 questions, from file formats and drawings to claim clarity and US disclosure duties. We have grouped the answers by theme and merged similar questions. Some were answered live or in the chat during the sessions, and we include those here too.

Webinar Q&A follow-up: your questions about IPRally Intelligence answered

Your questions on IPRally Intelligence, answered: from working with larger datasets to verifying results at paragraph level.

IPRally is SOC 2 Type II compliant

IPRally has completed its SOC 2 Type II examination. Advantage Partners, our independent auditor, tested our security controls in operation from March 4 to June 4, 2026, and issued an unqualified opinion: no exceptions noted on any control tested.

When systems start talking: IPRally's journey toward a virtual IP department

Something new is happening: people talk to systems in plain language, systems talk back, and systems have started talking to each other the same way. As AI climbs from the small decisions to the large ones, the question for IP work is no longer whether it gets automated, but how to stay in control once it is. Co-founder and CPO, Sakari Arvela, lays out where this leads – through IPRally's new API and upcoming MCP support toward a virtual IP department that's always on – and why humans end up more important in that picture, not less.

Search, Intelligence, Protection: the three pillars of IPRally’s next chapter

For nearly a decade IPRally has been obsessed with getting one task right: patent search. Having built the best patent search in the world, we’re now reorganizing around three pillars – Search, Intelligence, and Protection – the newest of which makes drafting prior-art-aware from the first sentence. Co-founder and CPO Sakari Arvela maps out the next chapter, and why Protection is the shift he's most personally invested in.

NGen selects IPRally to bring AI-native patent intelligence to Canada's advanced manufacturers

After evaluating a range of tools on functionality, usability, and cost, Canada's Global Innovation Cluster for Advanced Manufacturing chose IPRally to power its Patent Search Adoption Tool Pilot Program.

IPRally and RPX Corporation announce strategic collaboration, cross-linking AI-powered patent search with RPX Empower

IPRally today announces a strategic collaboration with RPX Corporation, the global patent risk management service provider, that further expands the capabilities of the RPX Empower platform and provides seamless access to business critical complementary information for IPRally users.

Macro meets micro: IPRally's next chapter builds intelligence on search

Excellence in patent search was always the foundation. But foundations are meant to be built on. After years of staying focused – and saying no to a lot – IPRally is now ready to bring the same rigor and precision that redefined search to the bigger, strategic questions that businesses make decisions on. CCO Andreas Cehlinder explains why now, and what comes next.

What does quality actually mean for automated patent search?

When agentic AI tools entered the patent search market, quality became the topic everyone wanted to talk about, and one of the hardest to discuss honestly. Impressive-looking outputs are easy to generate, but outputs you can actually trust take a different kind of work. IPRally's co-founder and CPO Sakari Arvela breaks down what quality means for Agent, and shares the data behind that claim.

Webinar Q&A follow-up: Your questions about IPRally Agent answered

More people joined our Agent launch sessions than any webinar we've run, and the questions kept coming well after we wrapped. Thank you to everyone who joined! We couldn't address everything live, so we've compiled the most common and insightful ones here and given each the thorough answer it deserves. Whether you attended or are discovering Agent for the first time, we hope this is useful.