--- title: How Benchling builds agents when the smartest AI isn't... description: Benchling's Head of AI Nicholas Larus-Stone shares how the R&D data platform builds AI agents for scientific work. Key insights include using multiple model... canonical: https://daily.dev/posts/how-benchling-builds-agents-when-the-smartest-ai-isn-t-smart-enough-yp55n4egs twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How Benchling builds agents when the smartest AI isn't smart enough | daily.dev og:description: Benchling's Head of AI Nicholas Larus-Stone shares how the R&D data platform builds AI agents for scientific work. Key insights include using multiple model... og:url: https://daily.dev/posts/how-benchling-builds-agents-when-the-smartest-ai-isn-t-smart-enough-yp55n4egs og:image: https://api.daily.dev/og/posts/Yp55N4eGS.png og:image:alt: How Benchling builds agents when the smartest AI isn't smart enough 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. # How Benchling builds agents when the smartest AI isn't smart enough **[LangChain](https://daily.dev/sources/langchain)** · 4 min read · 0 upvotes · 0 comments ## Summary Benchling's Head of AI Nicholas Larus-Stone shares how the R&D data platform builds AI agents for scientific work. Key insights include using multiple model providers on the same task to catch errors through disagreement, a structured weekly trace review process with a rotating 'fire chief', and how agents are compressing scientific workflows by reducing dead time between experiment steps. The conversation also covers context engineering, memory systems where agents create their own skills, evals without clean benchmarks, and why understanding LLMs is more analogous to biology than software engineering. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Evaluating AI Agents in Practice: Benchmarks, Frameworks, and Lessons Learned](https://daily.dev/posts/evaluating-ai-agents-in-practice-benchmarks-frameworks-and-lessons-learned-tohpewvfd) · InfoQ · 2 upvotes · 0 comments - [Three Years of Building Agents in Production \(Part 2\)](https://daily.dev/posts/three-years-of-building-agents-in-production-part-2--9uvhtnda1) · Mabl Engineering Blog · 2 upvotes · 1 comments - [Core Bottleneck In AI Engineering Isn't Writing Code. It's Trusting What Code Produces](https://daily.dev/posts/core-bottleneck-in-ai-engineering-isn-t-writing-code-it-s-trusting-what-code-produces-sslmnacfy) · Netguru · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#langchain](https://daily.dev/tags/langchain) [View this post on daily.dev](https://daily.dev/posts/how-benchling-builds-agents-when-the-smartest-ai-isn-t-smart-enough-yp55n4egs) ```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":"How Benchling builds agents when the smartest AI isn't smart enough","url":"https://daily.dev/posts/how-benchling-builds-agents-when-the-smartest-ai-isn-t-smart-enough-yp55n4egs","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-benchling-builds-agents-when-the-smartest-ai-isn-t-smart-enough-yp55n4egs"},"datePublished":"2026-07-08T19:22:56.004Z","dateModified":"2026-07-08T19:23:23.077Z","description":"Benchling's Head of AI Nicholas Larus-Stone shares how the R&D data platform builds AI agents for scientific work. Key insights include using multiple model...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c077d2439ada4a13ae6908429f586fb2?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c077d2439ada4a13ae6908429f586fb2?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"LangChain","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":"LangChain","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/0f4f2629e0724a849823f8cd0d913e13","url":"https://daily.dev/sources/langchain"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-benchling-builds-agents-when-the-smartest-ai-isn-t-smart-enough-yp55n4egs","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents,langchain","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"LangChain","item":"https://daily.dev/sources/langchain"},{"@type":"ListItem","position":3,"name":"How Benchling builds agents when the smartest AI isn't smart enough"}]} ```