--- title: What agents mean for Rust (and vice versa) · baby steps description: A Rust language designer argues that Rust is well suited to agentic/LLM-driven coding because its performance-tuning knobs pair well with agent-driven... canonical: https://daily.dev/posts/what-agents-mean-for-rust-and-vice-versa-baby-steps-wz99s6xv2 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: What agents mean for Rust (and vice versa) · baby steps | daily.dev og:description: A Rust language designer argues that Rust is well suited to agentic/LLM-driven coding because its performance-tuning knobs pair well with agent-driven... og:url: https://daily.dev/posts/what-agents-mean-for-rust-and-vice-versa-baby-steps-wz99s6xv2 og:image: https://api.daily.dev/og/posts/wZ99s6Xv2.png og:image:alt: What agents mean for Rust (and vice versa) · baby steps 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. # What agents mean for Rust (and vice versa) · baby steps **[Niko Matsakis - baby steps](https://daily.dev/sources/babysteps)** · 17 min read · 0 upvotes · 0 comments ## Summary A Rust language designer argues that Rust is well suited to agentic/LLM-driven coding because its performance-tuning knobs pair well with agent-driven optimization and its strong type system provides guardrails that keep agents from introducing subtle bugs. The piece covers three pillars of agentic software construction—design, construction, and optimization—and argues type systems alone aren't enough, pointing to proof tools like Verus, Creusot, Aeneas, and Kani as a path to proving unsafe code sound. The author proposes a 'no more unsafe code' north star for Rust, meaning all unsafe code could eventually be proven free of undefined behavior, and suggests the biggest open problem is 'design'—capturing architecture and intent in a form agents can translate into code. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Why is Rust growing so fast in popularity according to recent usage data? Rust is currently the second-fastest growing language after TypeScript, with Meta engineers reportedly writing twice as much first-party Rust code in one year as in the previous nine years combined. The growth is attributed partly to AI coding agents making it easy to try performant languages, and partly to Rust's type system providing guardrails that keep agents from introducing subtle bugs. _Developers tracking which languages are rising alongside AI coding tools can follow trends like this on daily.dev._ ### What tools exist for formally verifying Rust code is free of undefined behavior? Several proof tools target Rust, including Verus, Creusot, Aeneas, and Kani. Verus works by trusting the Rust borrow checker's uniqueness guarantees, which simplifies the job of the SMT solver and makes proof checking faster and more reliable than in languages without such guarantees, starting with proving code is panic-free and extending to richer correctness properties. _Developers evaluating formal verification options for Rust can keep up with tooling comparisons on daily.dev._ ### Can AI agents help optimize low-level or cryptographic code safely? Yes, agents are reportedly being used by engineers to hand-tune cryptographic assembly code and to diagnose async performance pitfalls like long polls or blocking using profilers such as dial9. This works especially well for code with clear mathematical definitions, since an agent can be told to optimize freely as long as it proves the result stays correct using theorem provers like Lean or Rocq. _Engineers pairing AI agents with performance tuning can track emerging workflows like this on daily.dev._ ## Similar posts on daily.dev - [Zig vs Rust in 2026](https://daily.dev/posts/zig-vs-rust-in-2026-hhp61o6ff) · Lobsters · 68 upvotes · 4 comments - [The Agent Is Not the Point](https://daily.dev/posts/the-agent-is-not-the-point-hig4o7ntd) · BirkeyCo · 2 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#rust](https://daily.dev/tags/rust), [#type-systems](https://daily.dev/tags/type-systems) [View this post on daily.dev](https://daily.dev/posts/what-agents-mean-for-rust-and-vice-versa-baby-steps-wz99s6xv2) ```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":"What agents mean for Rust (and vice versa) · baby steps","url":"https://daily.dev/posts/what-agents-mean-for-rust-and-vice-versa-baby-steps-wz99s6xv2","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/what-agents-mean-for-rust-and-vice-versa-baby-steps-wz99s6xv2"},"datePublished":"2026-10-14T08:17:49.453Z","dateModified":"2026-10-14T08:24:20.199Z","description":"A Rust language designer argues that Rust is well suited to agentic/LLM-driven coding because its performance-tuning knobs pair well with agent-driven...","image":"https://media.daily.dev/image/upload/s--VDukGCjf--/f_auto/v1722860399/public/Placeholder%2002","thumbnailUrl":"https://media.daily.dev/image/upload/s--VDukGCjf--/f_auto/v1722860399/public/Placeholder%2002","isAccessibleForFree":true,"articleSection":"Niko Matsakis - baby steps","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":"Niko Matsakis - baby steps","logo":"https://media.daily.dev/image/upload/logos/placeholder.jpg","url":"https://daily.dev/sources/babysteps"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/what-agents-mean-for-rust-and-vice-versa-baby-steps-wz99s6xv2","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,rust,type-systems","timeRequired":"PT17M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Niko Matsakis - baby steps","item":"https://daily.dev/sources/babysteps"},{"@type":"ListItem","position":3,"name":"What agents mean for Rust (and vice versa) · baby steps"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/what-agents-mean-for-rust-and-vice-versa-baby-steps-wz99s6xv2#faq","mainEntity":[{"@type":"Question","name":"Why is Rust growing so fast in popularity according to recent usage data?","acceptedAnswer":{"@type":"Answer","text":"Rust is currently the second-fastest growing language after TypeScript, with Meta engineers reportedly writing twice as much first-party Rust code in one year as in the previous nine years combined. The growth is attributed partly to AI coding agents making it easy to try performant languages, and partly to Rust's type system providing guardrails that keep agents from introducing subtle bugs. Developers tracking which languages are rising alongside AI coding tools can follow trends like this on daily.dev."}},{"@type":"Question","name":"What tools exist for formally verifying Rust code is free of undefined behavior?","acceptedAnswer":{"@type":"Answer","text":"Several proof tools target Rust, including Verus, Creusot, Aeneas, and Kani. Verus works by trusting the Rust borrow checker's uniqueness guarantees, which simplifies the job of the SMT solver and makes proof checking faster and more reliable than in languages without such guarantees, starting with proving code is panic-free and extending to richer correctness properties. Developers evaluating formal verification options for Rust can keep up with tooling comparisons on daily.dev."}},{"@type":"Question","name":"Can AI agents help optimize low-level or cryptographic code safely?","acceptedAnswer":{"@type":"Answer","text":"Yes, agents are reportedly being used by engineers to hand-tune cryptographic assembly code and to diagnose async performance pitfalls like long polls or blocking using profilers such as dial9. This works especially well for code with clear mathematical definitions, since an agent can be told to optimize freely as long as it proves the result stays correct using theorem provers like Lean or Rocq. Engineers pairing AI agents with performance tuning can track emerging workflows like this on daily.dev."}}]} ```