--- title: Foundries vs Navigators: Lowering the Cost of Science description: A guest essay from Endura Therapeutics CEO Adrian Sanborn argues that AI has made scientific thinking cheap while physical experimentation remains slow,... canonical: https://daily.dev/posts/foundries-vs-navigators-lowering-the-cost-of-science-krwlmuhyv twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Foundries vs Navigators: Lowering the Cost of Science | daily.dev og:description: A guest essay from Endura Therapeutics CEO Adrian Sanborn argues that AI has made scientific thinking cheap while physical experimentation remains slow,... og:url: https://daily.dev/posts/foundries-vs-navigators-lowering-the-cost-of-science-krwlmuhyv og:image: https://api.daily.dev/og/posts/kRWlmuHyV.png og:image:alt: Foundries vs Navigators: Lowering the Cost of Science og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Foundries vs Navigators: Lowering the Cost of Science **[Latent Space](https://daily.dev/sources/latentspace)** · 12 min read · 1 upvotes · 0 comments ## Summary A guest essay from Endura Therapeutics CEO Adrian Sanborn argues that AI has made scientific thinking cheap while physical experimentation remains slow, creating two adaptation strategies in biotech: 'Foundries' (companies like Xaira, Insitro, and Lila that industrialize experimental throughput) and 'Navigators' (companies that use AI models to make faster decisions without needing proprietary data or models). At Endura, LLMs now handle analysis pipeline rewrites in an afternoon instead of weeks, internal data dashboards are built in-house in a day rather than bought from vendors, and a fleet of LLM research agents triaged 500 disease targets down to 100 with expert-level depth reports, work that previously would have required a century of expert reading time. The piece argues this operational shift toward agile, in-house tooling is more consequential than flashy AI lab announcements. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How did Endura Therapeutics use LLM agents to triage disease targets for drug development? Endura built a two-stage triage process using a fleet of LLM research agents. The first pass covered about 500 disease targets with three-page reports filtering on prevalence, existing treatments, and mechanism fit. The second pass analyzed the remaining 100 targets with thirty-page reports on biology and competitive landscape, prompted to act like skeptical experts rather than summarizers. _daily.dev surfaces how teams apply LLM agents to research and decision-making workflows like this._ ### What is the difference between a foundry and a navigator company in AI-driven biotech? A foundry lowers the cost of doing experiments by industrializing measurement technology, such as next-generation sequencing or high-throughput microscopy, with companies like Xaira, Insitro, and Lila as examples. A navigator instead spends surplus AI-driven thinking capacity to improve decisions and internal processes without needing proprietary models or massive datasets, a strategy available to any company regardless of size. _developers weighing where to invest AI effort in a research pipeline can track this distinction on daily.dev._ ### Why hasn't AI sped up the throughput of physical lab experiments the way it has sped up software coding? Physical experiments remain gated by real-world processes that take days or weeks to verify results, regardless of how fast analysis or planning can now happen. AI has dramatically cut the cost of thinking, writing analysis code, and building dashboards, but it has done little to accelerate the wet-lab measurement step itself, creating an asymmetry between cheap thinking and slow doing. _daily.dev helps engineers follow how AI reshapes bottlenecks across scientific and software workflows._ ## Similar posts on daily.dev - [AI for science needs reasoning, not just data](https://daily.dev/posts/ai-for-science-needs-reasoning-not-just-data-lelrazoe7) · MIT Technology Review · 0 upvotes · 0 comments - [AI materials discovery now needs to move into the real world](https://daily.dev/posts/ai-materials-discovery-now-needs-to-move-into-the-real-world-xu1en29vn) · MIT Technology Review · 0 upvotes · 0 comments - [AI Disruptors: How the Next Generation of Business is Being Built](https://daily.dev/posts/ai-disruptors-how-the-next-generation-of-business-is-being-built-jqt436mt3) · DigitalOcean · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#biotech](https://daily.dev/tags/biotech) [View this post on daily.dev](https://daily.dev/posts/foundries-vs-navigators-lowering-the-cost-of-science-krwlmuhyv) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Foundries vs Navigators: Lowering the Cost of Science","url":"https://daily.dev/posts/foundries-vs-navigators-lowering-the-cost-of-science-krwlmuhyv","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/foundries-vs-navigators-lowering-the-cost-of-science-krwlmuhyv"},"datePublished":"2026-09-24T15:05:42.158Z","dateModified":"2026-09-24T15:06:09.302Z","description":"A guest essay from Endura Therapeutics CEO Adrian Sanborn argues that AI has made scientific thinking cheap while physical experimentation remains slow,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d8f697709e0f803e5c0b93b864c825de?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d8f697709e0f803e5c0b93b864c825de?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Latent Space","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Latent Space","logo":"https://media.daily.dev/image/upload/s--DnJ9laFj--/f_auto,q_auto/v1780213196/logos/latentspace?_a=BAMAMiWQ0","url":"https://daily.dev/sources/latentspace"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/foundries-vs-navigators-lowering-the-cost-of-science-krwlmuhyv","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,biotech","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Latent Space","item":"https://daily.dev/sources/latentspace"},{"@type":"ListItem","position":3,"name":"Foundries vs Navigators: Lowering the Cost of Science"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/foundries-vs-navigators-lowering-the-cost-of-science-krwlmuhyv#faq","mainEntity":[{"@type":"Question","name":"How did Endura Therapeutics use LLM agents to triage disease targets for drug development?","acceptedAnswer":{"@type":"Answer","text":"Endura built a two-stage triage process using a fleet of LLM research agents. The first pass covered about 500 disease targets with three-page reports filtering on prevalence, existing treatments, and mechanism fit. The second pass analyzed the remaining 100 targets with thirty-page reports on biology and competitive landscape, prompted to act like skeptical experts rather than summarizers. daily.dev surfaces how teams apply LLM agents to research and decision-making workflows like this."}},{"@type":"Question","name":"What is the difference between a foundry and a navigator company in AI-driven biotech?","acceptedAnswer":{"@type":"Answer","text":"A foundry lowers the cost of doing experiments by industrializing measurement technology, such as next-generation sequencing or high-throughput microscopy, with companies like Xaira, Insitro, and Lila as examples. A navigator instead spends surplus AI-driven thinking capacity to improve decisions and internal processes without needing proprietary models or massive datasets, a strategy available to any company regardless of size. developers weighing where to invest AI effort in a research pipeline can track this distinction on daily.dev."}},{"@type":"Question","name":"Why hasn't AI sped up the throughput of physical lab experiments the way it has sped up software coding?","acceptedAnswer":{"@type":"Answer","text":"Physical experiments remain gated by real-world processes that take days or weeks to verify results, regardless of how fast analysis or planning can now happen. AI has dramatically cut the cost of thinking, writing analysis code, and building dashboards, but it has done little to accelerate the wet-lab measurement step itself, creating an asymmetry between cheap thinking and slow doing. daily.dev helps engineers follow how AI reshapes bottlenecks across scientific and software workflows."}}]} ```