--- title: From one AI product to an AI factory | daily.dev description: A two-year retrospective from Doctolib's ML Platform PM on scaling AI product development across a healthcare company. Covers five key transformations:... canonical: https://daily.dev/posts/from-one-ai-product-to-an-ai-factory-yrpjourpj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: From one AI product to an AI factory | daily.dev og:description: A two-year retrospective from Doctolib's ML Platform PM on scaling AI product development across a healthcare company. Covers five key transformations:... og:url: https://daily.dev/posts/from-one-ai-product-to-an-ai-factory-yrpjourpj og:image: https://api.daily.dev/og/posts/YRpjouRPJ.png og:image:alt: From one AI product to an AI factory 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. # From one AI product to an AI factory **[Medium](https://daily.dev/sources/medium_js)** · 20 min read · 1 upvotes · 0 comments ## Summary A two-year retrospective from Doctolib's ML Platform PM on scaling AI product development across a healthcare company. Covers five key transformations: unifying fragmented Data/ML/Engineering platforms into a single Data & AI Platform, shifting from technical enabler to product-minded platform with structured discovery and OKRs, industrializing AI product quality through shared evaluation tooling and a GenAI gateway, building Doctolib-specific accelerators (agent templates) to compress time-to-production from quarters to weeks, and driving near-100% adoption of AI coding assistants while converging internal productivity tooling with customer-facing AI infrastructure. Key lessons include that platform unification is an organizational challenge more than a technical one, prioritization for many internal customers requires both frameworks and judgment, and investment sequencing matters as much as the investments themselves. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is a GenAI gateway and why would a company build one internally? A GenAI gateway is a single access point that gives every internal team governed, compliant access to a broad catalog of models from multiple providers, swappable in minutes rather than requiring manual integration work. It also provides resilience through automatic fallback if a provider goes down, and lets teams optimize for both quality and cost more easily. _Teams weighing a build-vs-buy call on model access can compare real GenAI gateway tradeoffs on daily.dev._ ### How long did it take a feature team to build an agentic AI product using a golden-path agent template versus from scratch? Building an agentic product from scratch used to take several quarters at Doctolib. Using a golden-path agent template with native integrations to memory, observability, evaluation, model access, and standard guardrails, one feature team went from nothing to an agentic product running in beta in production in about three weeks during an internal hackathon. _Anyone estimating agentic product timelines can track real build-speed benchmarks like this on daily.dev._ ### Why might committing early to a single agentic framework across teams matter? Delaying the choice of a common agentic framework let different teams pick different frameworks independently, and by the time a single framework was chosen for the golden path, the divergence had already occurred, forcing a painful later migration to consolidate everyone onto one shared foundation. Not deciding turned out to be a decision with real migration cost. _Teams debating whether to standardize on one agentic framework early can weigh this tradeoff via daily.dev._ ## Similar posts on daily.dev - [AI SDLC Observations](https://daily.dev/posts/ai-sdlc-observations-df92qyb8m) · Medium · 2 upvotes · 0 comments - [8 lessons from tech leadership on scaling teams and AI](https://daily.dev/posts/8-lessons-from-tech-leadership-on-scaling-teams-and-ai-dl9u8nkjk) · Stack Overflow Blog · 0 upvotes · 0 comments - [AI made platform engineering strategic again](https://daily.dev/posts/ai-made-platform-engineering-strategic-again-beuzux7t1) · LeadDev · 0 upvotes · 0 comments - [Building API Products in the AI Era](https://daily.dev/posts/building-api-products-in-the-ai-era-ztlpa4iip) · Nordic APIs · 0 upvotes · 0 comments - [In 2026, AI Is Merging With Platform Engineering. Are You Ready?](https://daily.dev/posts/in-2026-ai-is-merging-with-platform-engineering-are-you-ready--aqcjfik83) · The New Stack · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#healthcare](https://daily.dev/tags/healthcare), [#platform-engineering](https://daily.dev/tags/platform-engineering) [View this post on daily.dev](https://daily.dev/posts/from-one-ai-product-to-an-ai-factory-yrpjourpj) ```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":"From one AI product to an AI factory","url":"https://daily.dev/posts/from-one-ai-product-to-an-ai-factory-yrpjourpj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/from-one-ai-product-to-an-ai-factory-yrpjourpj"},"datePublished":"2026-07-12T19:29:11.747Z","dateModified":"2026-09-14T09:15:17.809Z","description":"A two-year retrospective from Doctolib's ML Platform PM on scaling AI product development across a healthcare company. Covers five key transformations:...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/217bcd60c6ea0b08a13035bc8460ff16?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/217bcd60c6ea0b08a13035bc8460ff16?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","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":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/from-one-ai-product-to-an-ai-factory-yrpjourpj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,healthcare,platform-engineering","timeRequired":"PT20M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"From one AI product to an AI factory"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/from-one-ai-product-to-an-ai-factory-yrpjourpj#faq","mainEntity":[{"@type":"Question","name":"What is a GenAI gateway and why would a company build one internally?","acceptedAnswer":{"@type":"Answer","text":"A GenAI gateway is a single access point that gives every internal team governed, compliant access to a broad catalog of models from multiple providers, swappable in minutes rather than requiring manual integration work. It also provides resilience through automatic fallback if a provider goes down, and lets teams optimize for both quality and cost more easily. Teams weighing a build-vs-buy call on model access can compare real GenAI gateway tradeoffs on daily.dev."}},{"@type":"Question","name":"How long did it take a feature team to build an agentic AI product using a golden-path agent template versus from scratch?","acceptedAnswer":{"@type":"Answer","text":"Building an agentic product from scratch used to take several quarters at Doctolib. Using a golden-path agent template with native integrations to memory, observability, evaluation, model access, and standard guardrails, one feature team went from nothing to an agentic product running in beta in production in about three weeks during an internal hackathon. Anyone estimating agentic product timelines can track real build-speed benchmarks like this on daily.dev."}},{"@type":"Question","name":"Why might committing early to a single agentic framework across teams matter?","acceptedAnswer":{"@type":"Answer","text":"Delaying the choice of a common agentic framework let different teams pick different frameworks independently, and by the time a single framework was chosen for the golden path, the divergence had already occurred, forcing a painful later migration to consolidate everyone onto one shared foundation. Not deciding turned out to be a decision with real migration cost. Teams debating whether to standardize on one agentic framework early can weigh this tradeoff via daily.dev."}}]} ```