Benchling launches Science Foundries, a new way for scientists and agents to work together

With agents working towards a shared goal on shared context, R&D teams run more science at once and move programs forward faster

SAN FRANCISCO, Oct. 15, 2026 /PRNewswire/ -- Benchling today launched Science Foundries, a new way to run scientific processes end-to-end with agents and scientists working together.

With Science Foundries, R&D teams pick a process or a goal, such as produce proteins, optimize a promising lead, or improve a manufacturing process. They set which steps agents run and when scientists need to approve. From there, the Foundry runs. Agents execute and monitor work, coordinate handoffs, and surface key decisions to scientists, all working from the same scientific data and context.

Benchling has spent the past 18 months bringing AI to science. Agents have become the fastest-growing capability the company has ever released, with scientists delegating real work to them every day. Science Foundries now extend that agentic work from individual tasks to entire scientific workflows.

"We're moving into a world where scientists can run more experiments, explore more ideas, and advance more programs. Lab automation, CROs, and generative models are each a key piece of this. Running them in parallel toward one scientific goal is a new kind of challenge. Science Foundries bring teams of agents and scientists together to power this new way of working," said Ashu Singhal, co-founder and President of Benchling.

A Foundry for high-throughput biologics

Over the past few months, Benchling has embedded with scientists to build Foundries across R&D. One example is for a pharma team that's designing, producing, and testing antibodies at high throughput. The team has models that design sequences, CROs that synthesize constructs, and lab automation for production and assays. Typically this process required scientists to manually process data and feed it from one step to the next. Their Science Foundry now automates this process end-to-end:

• A design agent uses scientific models to generate and evaluate sequences.
• A cloning agent drafts the assembly strategy and places orders to a CRO.
• A lab agent dispatches instructions to workcells, captures the data, and performs QC.
• An analysis agent interprets the results and updates training datasets.

Because agents capture structured data across the entire process, scientists spend more of their time on the decisions that matter, such as which design strategies to focus on and which candidates to advance, with better evidence behind each one. Work also moves faster between steps. When an assay finishes at 11pm, agents pick up the results and present an analysis by the time the scientist starts their day. Across a program, starting each experiment a day sooner can add up to months.

The Foundry also changes how much a team can explore. A design round used to test one strategy at a time, because each needed a scientist to set it up and track it. Now agents can run several design strategies against the same goal at once, each with its own constructs, runs, and analysis, and compare them side by side. Scientists choose a direction from a wider set of results.

Parabilis Medicines: from individual agents to Science Foundries

Parabilis Medicines, a clinical-stage biopharma pioneering a new class of alpha-helical peptides, has moved from chat, to standalone agents, to Science Foundries.

Parabilis' lean scientific team is running several programs in parallel. They started out using individual Agents for discrete tasks like defining candidate-target profiles, experimental design, and SPR analysis. Now, they're deploying Science Foundries that bring teams of agents together across entire scientific processes like protein production, screening, and lead optimization—compressing whitespace between experiments and helping scientists spend more of their time on the decisions that drive programs forward.

"AI and automation are transforming every part of the drug discovery process. We are working to empower lean teams of scientists by creating tools that handle as much of the execution as possible, and Science Foundries in Benchling are the perfect complement to automated labs - with teams of agents that keep science moving around the clock by automating the data capture, analysis, and handoffs needed to turn one experiment into the next," said John McGee, Parabilis Medicines, Scientific Co-Founder and Head of Platform.

Foundries across R&D

Benchling is building Science Foundries for teams across R&D:

• Therapeutic Areas: Search literature to help define target candidate profiles, suggest assays to reuse or tweak from past programs, and design and orchestrate assay cascades.
• Preclinical: Review in vivo study designs, process data from CROs, present analyzed results, and write study reports
• Process Development: Propose DoE, process data from bioreactors, orchestrate analytical requests, and write study documentation

Availability

Starting today, Benchling customers can set up their own Science Foundries. Each engagement begins by that is key to accelerating the entire organization: protein production, screening, assay development, method development, or in vivo work.Then start a conversation with Benchling AI and have it build your first Science Foundry.

Reach out to Benchling here for a free consultation on how to deploy Science Foundries for your organization.

About Benchling
Benchling is the AI platform for biotech R&D, unifying scientific data and automating workflows to accelerate discovery and development. Trusted by more than 1,300 companies worldwide, from pioneering startups to global leaders like Merck, Moderna, and Sanofi, Benchling gives scientists a single place to capture, connect, and act on data across the entire R&D lifecycle. With Benchling AI, agents and models work directly inside scientific workflows, grounded in structured data. The result is faster teams, better molecules, and breakthroughs that reach the world sooner.

SOURCE Benchling