--- title: Inside Kilo Speed: We Taught Kilo to Test Itself | daily.dev description: Kilo's team built a self-testing loop for their VS Code extension and CLI, enabling their AI agent to open VS Code windows, drive the extension like a real... canonical: https://daily.dev/posts/inside-kilo-speed-we-taught-kilo-to-test-itself-htdgme3ff twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Inside Kilo Speed: We Taught Kilo to Test Itself | daily.dev og:description: Kilo's team built a self-testing loop for their VS Code extension and CLI, enabling their AI agent to open VS Code windows, drive the extension like a real... og:url: https://daily.dev/posts/inside-kilo-speed-we-taught-kilo-to-test-itself-htdgme3ff og:image: https://api.daily.dev/og/posts/HTdgmE3FF.png og:image:alt: Inside Kilo Speed: We Taught Kilo to Test Itself 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. # Inside Kilo Speed: We Taught Kilo to Test Itself **[Kilo Blog](https://daily.dev/sources/kilo-ai-blog)** · 5 min read · 0 upvotes · 0 comments ## Summary Kilo's team built a self-testing loop for their VS Code extension and CLI, enabling their AI agent to open VS Code windows, drive the extension like a real user, compile and run the CLI, assert on output, and run performance benchmarks autonomously. The key insight is that this differs from traditional test suites: instead of encoding what a human decided to check in the past, the agent decides what to verify in real time for the specific change it just made. The benchmarking capability proved especially valuable, allowing iterative performance optimization loops (e.g., 'optimize until under 50ms') that weren't previously feasible. The post argues that the harness enabling an agent to see and validate its own output is often what separates a demo from a shippable product, and predicts that agent-driven self-testing will become the default workflow as computer-use model capabilities improve. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [We're back on Product Hunt — here's how far Kilo has come](https://daily.dev/posts/we-re-back-on-product-hunt-here-s-how-far-kilo-has-come-jalcqyaqw) · Kilo Blog · 1 upvotes · 0 comments - [Ramp’s Inspect shows closed-loop AI agents are software’s future](https://daily.dev/posts/ramp-s-inspect-shows-closed-loop-ai-agents-are-software-s-future-l9utwdes9) · The New Stack · 0 upvotes · 0 comments --- Tags: [#testing](https://daily.dev/tags/testing), [#ai-agents](https://daily.dev/tags/ai-agents), [#vscode](https://daily.dev/tags/vscode) [View this post on daily.dev](https://daily.dev/posts/inside-kilo-speed-we-taught-kilo-to-test-itself-htdgme3ff) ```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":"Inside Kilo Speed: We Taught Kilo to Test Itself","url":"https://daily.dev/posts/inside-kilo-speed-we-taught-kilo-to-test-itself-htdgme3ff","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/inside-kilo-speed-we-taught-kilo-to-test-itself-htdgme3ff"},"datePublished":"2026-07-20T23:33:41.725Z","dateModified":"2026-09-14T07:01:44.248Z","description":"Kilo's team built a self-testing loop for their VS Code extension and CLI, enabling their AI agent to open VS Code windows, drive the extension like a real...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/576ba107ddae38cec8523b2db0c872a2?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/576ba107ddae38cec8523b2db0c872a2?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Kilo Blog","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":"Kilo Blog","logo":"https://media.daily.dev/image/upload/s--x3pmrf8D--/f_auto,q_auto/v1774964071/logos/kilo-ai-blog?_a=BAMAMiWQ0","url":"https://daily.dev/sources/kilo-ai-blog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/inside-kilo-speed-we-taught-kilo-to-test-itself-htdgme3ff","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"testing,ai-agents,vscode","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Kilo Blog","item":"https://daily.dev/sources/kilo-ai-blog"},{"@type":"ListItem","position":3,"name":"Inside Kilo Speed: We Taught Kilo to Test Itself"}]} ```