Anticipatory Intelligence, Built for Smarter Decisions

We use commercially available, pre-trained LLMs within a retrieval-augmented generation (RAG) architecture and do not train or fine-tune these models. This RAG-driven approach allows us to harness LLMs for their reasoning and narrative strengths while ensuring that all factual content and conversational context come exclusively from our trusted data ecosystem. Quality is ensured through expert review, real-world scenario testing and automated evaluation (e.g., LLM-as-a-judge), combining human oversight and scalable checks to deliver reliable, continuously improving outputs.

Although the LLM is the key tool to provide a fluent narrative, answers to user queries are based on our extensive collection of curated content. This means that our AI-generated responses draw from trusted sources, such as Cortellis Regulatory Intelligence, Cortellis Drug Discovery Intelligence, OFF-X Translational Safety Intelligence, rather than broad (and potentially inaccurate or biased) internet content that common AI tools might use.

Depending on the product and your content subscription options, our AI tools will use various content types to generate responses.

Customer data is protected by a comprehensive security framework, including encryption in transit (TLS 1.2+) and at rest, strict role-based access with multi-factor authentication and full data isolation. Customer data is never used to train or fine-tune models nor shared with third parties.

We comply with global standards (ISO 27001, SOC 2, GDPR) and maintain continuous monitoring, logging and regular audits. All data processing occurs in secure environments aligned with our data protection policies.

Clarivate takes a deliberate, governance-led approach to AI—designed to deliver trusted, secure, and high-impact outcomes for drug development and commercialization. Our AI Center of Excellence guides product teams with rigorous oversight to ensure AI is applied responsibly and consistently across the organization.

At the core is the Clarivate AI Platform, which provides shared, scalable AI capabilities across our solutions. This foundation enables faster innovation, supports multiple use cases, and delivers advanced functionality within a consistent, secure user experience that protects data privacy.

We are initially enabling customers to access Clarivate’s trusted data and expertise more quickly through natural-language interaction. More advanced AI capabilities will be introduced progressively throughout 2026.

As a trusted partner to innovators whose ultimate end user is the patient, we have a critical responsibility to mitigate AI-induced inaccuracies. We are taking the following steps toward achieving this goal:

• The prompts used in our products are crafted by expert prompt engineers who ensure that the settings of the LLM are optimized to maximize faithfulness to the source content and minimize hallucinations. Our system is designed to provide references to the source text when delivering an answer. In addition, our systems can handle negative rejections, ensuring that it does not fabricate one when an answer cannot be provided due to insufficient information. Instead, the system presents an explanation to the user for the lack of response.
• The information presented to users always originates from our trustworthy, curated content. We use a combination of RAG/RAG Fusion models to ensure that the information users see is based on the vetted content your organization can access via Clarivate solutions. Our tools offer full transparency regarding the content that was used to generate the response and ensure proper attribution to the specific sources used.
• We continuously test our solutions and the results they produce, including through dedicated beta programs and close collaboration with customers and subject matter experts. Our data science expertise helps increase system accuracy, fairness, robustness and interpretability in a programmatic way.

Ensuring clarity and trust in our solutions is one of our top priorities. Our conversational discovery and AI-powered tools present the resources on which their responses are based, so that you can always explore relevant materials for further context.