Hostname: page-component-5db58dd55d-smskv Total loading time: 0 Render date: 2026-07-09T08:01:42.198Z Has data issue: false hasContentIssue false
Accepted manuscript

Agents.design.bio: An Agent-Based Decision-Support Framework for Scaling Biodesign

Published online by Cambridge University Press:  03 July 2026

O. Telhan*
Affiliation:
Design.bio, New York, New York, USA
*
*Author for correspondence. Email: orkan@design.bio
Rights & Permissions [Opens in a new window]

Accessibility of Accepted Manuscripts

Accepted Manuscripts are early, peer-reviewed versions that have not yet been copyedited, typeset, or formally published and may not meet all accessibility standards. A fully formatted accessible version will follow.

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

Biodesign projects often stall between promising material prototypes—bacterial cellulose textiles, mycelium composites, algae-derived materials—and scalable, economically viable production systems. This gap emerges from fragmented decision-making across material design, cultivation processes, and techno-economic evaluation, since each domain operates with distinct metrics, vocabularies, and decision thresholds—making cross-domain reasoning difficult to formalize and transfer. We present agents.design.bio, a decision-support framework that enables students, designers, educators, and founders to engage interdisciplinary expertise through structured reasoning. The platform offers a unified conversational interface in which users interact with domainspecific agents: Designer (@designer), Farmer (@farmer), and CFO (@cfo). Together, they operate on a shared knowledge base, manufacturing datasets, and techno-economic models. Rather than generating speculative ideas, the agents evaluate user-defined scenarios and highlight trade-offs, sensitivities, and risks—making cross-domain dependencies explicit and testable. The demonstration walks through four phases— material evaluation, process optimization, scale-up stress testing, and trade-off analysis—reframing scale-up as a structured learning process rather than a late-stage financial constraint.

Information

Type
Demo: Biodesign Conference
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
© The Author(s), 2026. Published by Cambridge University Press