An agentic AI environment to support biomedical research in collaborative academic environments

Checked 16 Oct 2026. Open license (CC-BY, CC-BY-SA, CC0, public domain): full text indexed and used in synthesis.

Abstract Agentic artificial intelligence (AAI) is increasingly used by biomedical scientists, where it has substantially lowered the difficulty of integrating computational, statistical and data-science approaches into day-to-day research activities, assisting with project design, analysis and manuscript preparation. Significant barriers remain, however, which are unlikely to be removed solely by releasing more capable AI models. Meaningful use still demands a technical fluency that many biomedical researchers lack: a PI and their lab members must learn how to use the AAI system, establish standard operating procedures (SOPs) for managing, sharing and curating data, and enforce rules that address data privacy and security. Existing commercial AAI systems, which were designed primarily for software engineering purposes, need to be significantly re-purposed for biomedical-related data science. We present Murmurent, shared software that sits beneath the agentic AI and provides the skills, procedures and protections to address the concerns above, removing the need for a lab to develop them independently. This includes (1) infrastructure to support projects and so-called choreographies involving multiple group members; (2) a set of specialized agents each dedicated to typical biomedical data science tasks including software and statistical development, data visualization, literature search, equity, diversity, inclusion, and decolonization (EDID) review, and others; (3) a tiered memory which can retain important research decisions, intermediate, derived outputs and sensitive data, and which can exploit this information to automatically build better contexts in AAI sessions; (4) traceability records which are used by the AAI session to better plan and execute data analyses and software builds by, for example, helping to avoid repeating decisions that lead to dead-ends; (5) enforcement of SOPs for data maintenance and data governance across all lab members; and (6) multi-user capacity to allow groups to interact and collaborate. We use the system to identify putative inhibitors of Peptidyl-prolyl cis–trans Isomerase NIMA-interacting 1 (Pin1), a protein with a shallow catalytic site making it difficult to target. We describe the construction of several approaches to identify Pin1 inhibitors and the results they yield. Murmurent is open source.

• Wu et al. 2026 argue that the barriers to agentic AI in biomedical laboratories are organizational rather than model-centric—technical fluency, standard operating procedures and data-governance rules that more capable models alone will not remove—and they built the open-source Murmurent layer beneath the agents to supply them. Nelson et al. 2026's interview study reaches the same conclusion from the innovation side: AI's benefits depend on integration within a robust ecosystem of conventional experimentation. Trace →
• A lab-infrastructure builder and a cognition framework independently converge on structured memory as the missing layer in research agents: Wu et al. 2026 give Murmurent a tiered memory that retains research decisions plus traceability records that help avoid repeating dead-ends, while Cuadros et al. 2026 argue scientific cognition requires differentiated memory spaces with provenance treated as memory routing. Trace →
• The route around the infrastructure barrier extends from individual desktops to whole labs, and the barrier is organizational as much as computational: Wu et al. 2026 report that meaningful agentic-AI use demands technical fluency, data SOPs and privacy enforcement—barriers unlikely to be removed solely by releasing more capable AI models—and supply shared open-source software (Murmurent) so labs need not build these independently. Trace →

• AI for science and agentic research