--- title: Turning AI agents into doctors for your project's health description: Tuist frames a vision where AI coding agents act as diagnostic doctors for a project's health, using build, test, and bundle data collected by Tuist as the... canonical: https://daily.dev/posts/turning-ai-agents-into-doctors-for-your-project-s-health-f8pjutlaq twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Turning AI agents into doctors for your project's health | daily.dev og:description: Tuist frames a vision where AI coding agents act as diagnostic doctors for a project's health, using build, test, and bundle data collected by Tuist as the... og:url: https://daily.dev/posts/turning-ai-agents-into-doctors-for-your-project-s-health-f8pjutlaq og:image: https://api.daily.dev/og/posts/f8PjutlAQ.png og:image:alt: Turning AI agents into doctors for your project's health 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. # Turning AI agents into doctors for your project's health **[ Tuist ](https://daily.dev/sources/tuist-blog)** · 12 min read · 0 upvotes · 0 comments ## Summary Tuist frames a vision where AI coding agents act as diagnostic doctors for a project's health, using build, test, and bundle data collected by Tuist as the 'medical records.' The narrative follows a fictional platform engineer, David, who becomes the bottleneck for debugging Xcode and Gradle issues until his team starts feeding Tuist data to coding agents like Codex and Claude via CLI skills or an MCP server. Use cases include diagnosing flaky tests, explaining build/test failures, investigating oversized app bundles, and optimizing cache usage. Tuist positions itself as aiming to become a 'virtual platform team,' eventually taking proactive action on issues rather than just answering questions, drawing a comparison to Sentry's Seer for errors. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the difference between using an MCP server versus a CLI for AI coding agents accessing project data? An MCP server is more convenient for setup and authentication since the LLM client can manage the auth flow and session, making data accessible even to people without the CLI installed, such as an engineering director checking flakiness data. A CLI is often better if you already use it since it manages sessions itself and is needed anyway when you must act on the data within a codebase, making a separate MCP feel redundant in that case. _daily.dev is where developers weighing MCP against CLI integrations compare real tradeoffs before choosing._ ### How can AI agents help diagnose flaky tests in a project? Tuist collects test run data across many builds and identifies which tests are flaky, exposing that information through CLI commands or an MCP server. A coding agent like Codex or Claude can pull this flakiness data along with guideline skills or prompts and use it to diagnose root causes and propose fixes, similar to handing a doctor a patient's full medical history before prescribing treatment. _developers chasing flaky test root causes can track agentic debugging approaches like this on daily.dev._ ## Similar posts on daily.dev - [The new Tuist, from build toolchains to bare metal](https://daily.dev/posts/the-new-tuist-from-build-toolchains-to-bare-metal-waw3c6jvd) · Tuist · 0 upvotes · 0 comments - [Head of the Agents and Assistants Department](https://daily.dev/posts/head-of-the-agents-and-assistants-department-gekkcfmi0) · Beam Bloggers Webring · 0 upvotes · 0 comments - [Code like a surgeon](https://daily.dev/posts/code-like-a-surgeon-5uzyvisn6) · Hacker News · 0 upvotes · 0 comments - [How I use AI agents to write code](https://daily.dev/posts/how-i-use-ai-agents-to-write-code-onvlmqy00) · Read the Tea Leaves · 99 upvotes · 3 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#platform-engineering](https://daily.dev/tags/platform-engineering), [#build-systems](https://daily.dev/tags/build-systems) [View this post on daily.dev](https://daily.dev/posts/turning-ai-agents-into-doctors-for-your-project-s-health-f8pjutlaq) ```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":"Turning AI agents into doctors for your project's health","url":"https://daily.dev/posts/turning-ai-agents-into-doctors-for-your-project-s-health-f8pjutlaq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/turning-ai-agents-into-doctors-for-your-project-s-health-f8pjutlaq"},"datePublished":"2026-08-23T12:23:42.936Z","dateModified":"2026-08-23T12:59:26.910Z","description":"Tuist frames a vision where AI coding agents act as diagnostic doctors for a project's health, using build, test, and bundle data collected by Tuist as the...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/29c619b4b91ff1da62b90886007da071?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/29c619b4b91ff1da62b90886007da071?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"\n Tuist\n ","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":"\n Tuist\n ","logo":"https://media.daily.dev/image/upload/s--3AYDH23h--/f_auto,q_auto/v1787487506/logos/tuist-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/tuist-blog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/turning-ai-agents-into-doctors-for-your-project-s-health-f8pjutlaq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,mcp,platform-engineering,build-systems","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"\n Tuist\n ","item":"https://daily.dev/sources/tuist-blog"},{"@type":"ListItem","position":3,"name":"Turning AI agents into doctors for your project's health"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/turning-ai-agents-into-doctors-for-your-project-s-health-f8pjutlaq#faq","mainEntity":[{"@type":"Question","name":"What is the difference between using an MCP server versus a CLI for AI coding agents accessing project data?","acceptedAnswer":{"@type":"Answer","text":"An MCP server is more convenient for setup and authentication since the LLM client can manage the auth flow and session, making data accessible even to people without the CLI installed, such as an engineering director checking flakiness data. A CLI is often better if you already use it since it manages sessions itself and is needed anyway when you must act on the data within a codebase, making a separate MCP feel redundant in that case. daily.dev is where developers weighing MCP against CLI integrations compare real tradeoffs before choosing."}},{"@type":"Question","name":"How can AI agents help diagnose flaky tests in a project?","acceptedAnswer":{"@type":"Answer","text":"Tuist collects test run data across many builds and identifies which tests are flaky, exposing that information through CLI commands or an MCP server. A coding agent like Codex or Claude can pull this flakiness data along with guideline skills or prompts and use it to diagnose root causes and propose fixes, similar to handing a doctor a patient's full medical history before prescribing treatment. developers chasing flaky test root causes can track agentic debugging approaches like this on daily.dev."}}]} ```