Benchling

Scientists lose an estimated 20 hours a week to logistical tasks. AI can take on much of that work when in vivo data is structured at the point of capture. See four places it’s already working for in vivo teams, from CRO data ingestion to study reporting.

Your CRO sends results back as PDFs and Excel files, and someone on your team re-keys them before anyone can compare studies. AI agents can now ingest that package and link results to the right study, animals, and test articles. See what else AI is doing for in vivo teams 💡

Novel antibody formats are multiplying fast, but most data infrastructure hasn’t kept pace. Your years of antibody data end up unstructured, and AI models have nothing to learn from. At #PEGSEurope, I’ll show how we close the gap, giving antibody teams a shared, structured foundation to design, characterize, register, and learn from proteins, and what that means for the speed of your DBTL cycles. Join my session on Tuesday, Nov 17 at 12:15 PM and visit our booth #421! 🔗 View the session details: https://lnkd.in/eHWQY4nb

Today we launched Direct Data Share, making it easy to connect your scientific data between Benchling and Snowflake. Everything stays up to date, with no custom pipelines needed. That means less time moving data between systems and more time putting it to work. Now available in beta: https://lnkd.in/ewNBqFCD

Even highly automated labs can get slowed down by manual handoffs between experiments. Benchling's Head of AI Nicholas Larus-Stone spoke with R&D World about how AI agents helped one biologics lab overcome this bottleneck and increase throughput. Plus, how our newly launched Science Foundries bring agents together to coordinate work across entire scientific processes. Read the full interview: https://lnkd.in/eC_Vj4Cy

Parabilis Medicines started with individual AI agents. Now they’re taking the next step with Science Foundries. We’ve been working with Parabilis to deploy teams of agents across entire scientific processes, from protein production to screening and lead optimization. The goal? Less waiting between experiments and more time for scientists to focus on the decisions that move programs forward. Read about it: https://lnkd.in/eGyX4_sz