Iris.ai
AI-driven research enhancement, smart discovery, scalable workspace.. [Freemium]
Last verified:
What is Iris.ai?
Iris.ai is an AI-powered research assistant and science assistant designed to increase the performance of R&D teams in mapping out existing knowledge from published research, patents, and internal R&D content. The tool moves beyond limiting keywords, endless result lists, and biased citations by using AI for cross-disciplinary, early-stage research projects. It serves as an AI knowledge foundation for regulated enterprises, turning complex enterprise data into AI that can be trusted.
The platform offers key features including visual content-based search, document set analysis, extracting and systematizing data points, automatically writing summaries of multiple documents, and powerful filters based on context descriptions. The Researcher Workspace includes modules like the Extraction tool that extracts entities and data from both text and tables, and Abstractive summarization. The Explore tool creates visual concept maps, while the Focus tool processes document sets. Recent updates include search in EU-funded projects via CORDIS integration, highlighting key terms in papers, map subscriptions, BibTex exports, and dark mode.
Iris.ai is designed for researchers in industry and academia, librarians, students, and R&D professionals in R&D-heavy industries like chemistry, pharmaceuticals, MedTech, material science, biotech, food safety, and engineering. The tool can be trained on each client's specific research field with no human involvement, using Natural Language Processing and Machine Learning to review massive collections of research papers or patents. Enterprise customers benefit from Agentic RAG-as-a-Services, with 330+ million documents securely ingested and 35%+ savings on LLM usage costs.
The platform offers free basic functionalities for individual registered users, with premium features available through organization licenses (university or company) or individual premium subscription. Premium includes access to more than 200 million open access research papers from Core.ac.uk, PubMed, and arXiv.org, problem statement querying, expanded content, edit functionalities, relevance filters, and CORDIS access. Students receive a 50% discount on individual premium subscriptions.
Iris.ai pricing
Pricing model: Freemium
Iris.ai offers basic functionalities for free for individual registered users with limited features in the Explore tool and access to Focus tool. Free users get 5GB cloud usage (~2 hours) with no overage possible - switching to local mode when limit reached. Premium features include problem statement querying, expanded content, edit functionalities, and relevance filters. Premium access requires either an organization license (university/library or company purchase) or individual premium subscription purchased by contacting [email protected]. Individual premium includes access to 200+ million open access research papers (Core.ac.uk, PubMed, arXiv.org), problem statement querying, CORDIS access for EU-funded projects search, and all tools. Students receive 50% discount on individual premium. To subscribe: create account, click
Iris.ai pros
- AI-powered cross-disciplinary research beyond keyword limitations
- Trains on client's specific research field without human involvement
- Extracts data from both text and tables automatically
- Visual content-based search with concept mapping
- Abstractive summarization of multiple documents
- Search in EU-funded projects via CORDIS integration
- Access to 200+ million open access research papers
- Highlights key terms showing connection to problem statement
- Map subscriptions with notifications for new relevant content
- BibTex and CSV export for reference managers
- Processes image-based PDFs with OCR integration
- 35%+ savings on LLM usage costs for enterprises
- 80%+ acceleration on AI go-to-market for enterprises
- 330+ million documents securely ingested platform-wide
- Dark mode interface option
- Works with patents and scientific papers together
- Feedback loop with domain experts for validation
- API connectivity for system integration
- Export data to CSV after extraction
- Contextual fingerprint matching for relevant literature
Iris.ai cons
- No publicly listed pricing - must contact for premium access
- Free version has limited Explore tool features
- Free users cannot input own problem statement
- Free users cannot search in patents
- Requires contact with [email protected] for individual premium
- Image-based PDFs require external OCR tool evaluation
- Further from patent formatting increases retraining chance
- Free plan switches to local mode when usage limit reached
- Limited mobile features for review and collaboration
- Slow processing speeds reported by some users
- Software crashes reported by some users
- Difficulty in data syncing issues
- Must get university/company to purchase organization license
- Free user cannot create or edit maps without registration
- 30+ minimum links required for CSV paper list import
- Chat feature currently only works in English
- May require retraining for very broad topic areas
- OCR processing requires additional evaluation step
- Overage fees apply for enterprise cloud usage beyond limits
- Not suitable for non-machine-readable PDFs
Frequently asked questions about Iris.ai
How do I train the machine in my research domain?
Training the machine on your specific research domain includes three steps: (1) Provide a good description of the company's area(s) of operation, (2) Set up a simple output data layout (only for data extraction), and (3) Establish a feedback loop with you, the domain expert, for validation of initial results. The Iris.ai core machine learns your research domain and context during the training phase with no humans involved.
Do I need to retrain the system for every product or disease I want to do reviews in?
No, as long as you work in the overall same field, it will be sufficient to train the system on that topic. However, if you are part of a major conglomerate that works across a large and very broad number of topics, it might be beneficial to have a handful of trained models in different areas. Most smaller providers or departments will not have this need.
How does the AI machine establish links between scientific documents and my research context?
The Iris.ai core machine learns your research domain and context during training. When fully trained, it identifies relevant literature by finding the most meaning-bearing words in your documents, then enriches these words with contextual synonyms and topic words to build a contextual 'fingerprint'. This fingerprint is matched with the content collection or database of scientific text the tool is connected to, allowing you to link a self-written problem statement or document against all available research papers, patents, and scientific text sources.
How does the tool know what relevant data to extract?
One of the configuration parameters for the tool is the output data layout. As a client, you specify the data you'd like to extract to this layout. With help from Iris.ai, you'll set up the desired output data layout for data extraction based on how you want the output to look like (e.g., headers).
Can Iris.ai extract data from text as well as tables?
Yes, Iris.ai extracts entities and data from both text and tables. Moreover, when there are data points in the text which are related to data points in tables, the machine makes those connections in the extraction output.
How about image-based PDFs? Can the machine process that?
Yes, the machine can process image-based PDFs, but this requires evaluation and incorporation of an external OCR tool (optical character recognition). That's not a problem for Iris.ai to do.
What document formats does the machine accept?
Any machine-readable PDF with text and/or tables of scientific and technical text can be inputted. However, the further away from patent formatting, the higher the chance of requiring retraining.
What's the output format for data extraction?
With the help from Iris.ai, you'll set up the desired output data layout for the data extraction, based on how you want the output to look like (e.g., headers). The output format is customized based on your specifications.
How can I export the data?
When you have extracted all the data from your documents, you can export the data to CSV or connect your system with Iris.ai's APIs. You can also export map results as a .csv file or in BibTex format for uploading to reference manager systems.
What is the difference between Free and Premium versions?
Free users get basic functionalities with limited features in the Explore tool (cannot input own problem statement, cannot search in patents) but can try the Focus tool and import single Explore maps into Focus studies. Premium includes problem statement querying, expanded content, edit functionalities, relevance filters, access to 200+ million open access research papers, CORDIS access for EU-funded projects search, map subscriptions, BibTex exports, and full access to all tools. Premium requires organization license or individual subscription via [email protected].