Genesis Makes AI Evidence Synthesis Platform and Releases it for Free
Finding, reviewing and synthesising scientific evidence is one of the most time-consuming tasks in life sciences, and also one of the most crucial. Whether supporting pharmacovigilance, regulatory submissions or other medical affairs, teams often spend weeks manually reading literature, screening publications and tracking new evidence.
“Run it yourself. Run it with Genesis. Or have Genesis run it for you.” Genesis Research Group
Genesis Research Group is hoping to change that with its EVID AI evidence synthesis platform, designed to bring the entire evidence review process into a single platform. And best of all, it’s being released free of charge to life science organisations and eligible researchers until the end of 2026.
Developed by Genesis scientists and refined through two years of use on real client projects, users of the platform can perform rapid evidence searches, targeted literature reviews, ongoing surveillance and full systematic reviews without switching between multiple disconnected tools. It has been developed around real-world workflows across healthcare economics and outcomes research, real world evidence, medical affairs and market access.
The decision to release the platform for free for the remainder of 2026 is largely a strategic one. Instead of generating revenue from this software immediately, Genesis wants to encourage organisations to experience the platform firsthand, demonstrate its value and likely provide valuable feedback data to continuously improve the software.
Evidence synthesis is particularly well suited to this broader industry shift towards AI and automation, because AI can accelerate literature identification and organisation while leaving the critical interpretation and decision making with experienced professionals.
However, despite the potential benefits, AI-assisted evidence synthesis is not without risk. If search strategies are poorly designed or AI systems overlook relevant studies, important evidence could be missed, which will lead to biased conclusions being drawn. As with any GxP adjacent AI application, human oversight, validation and transparency remain essential to secure scientific integrity and confidence.
For pharmacovigilance teams, this is another example of AI being applied to one of the industry’s most labour-intensive activities. Faster evidence reviews and continuous literature surveillance have the potential to improve efficiency while allowing specialists to spend more time analysing safety data instead of searching for it.
