--- title: How Amplitude ships product improvements in 1–2 days... description: Amplitude's product agent Wave, roughly 80% powered by OpenAI models, helps teams ship product improvements in an estimated 1-2 days instead of a month. Wave... canonical: https://daily.dev/posts/how-amplitude-ships-product-improvements-in-1-2-days-with-openai-falonkq5y twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How Amplitude ships product improvements in 1–2 days with OpenAI | daily.dev og:description: Amplitude's product agent Wave, roughly 80% powered by OpenAI models, helps teams ship product improvements in an estimated 1-2 days instead of a month. Wave... og:url: https://daily.dev/posts/how-amplitude-ships-product-improvements-in-1-2-days-with-openai-falonkq5y og:image: https://api.daily.dev/og/posts/FalonkQ5Y.png og:image:alt: How Amplitude ships product improvements in 1–2 days with OpenAI 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 Amplitude ships product improvements in 1–2 days with OpenAI **[OpenAI](https://daily.dev/sources/openai)** · 6 min read · 1 upvotes · 0 comments ## Summary Amplitude's product agent Wave, roughly 80% powered by OpenAI models, helps teams ship product improvements in an estimated 1-2 days instead of a month. Wave combs through analytics, session replays, customer feedback, and code to find opportunities, then hands technical plans to coding agents like Codex. On Amplitude's own homepage, personalizing suggestion cards drove a 160% lift in card-driven sends after one day. Amplitude uses GPT-6.1 Sol for deep investigations, GPT-6 Luna for cheap frequent checks, and GPT-Image-2.5 Flare for mockups; GPT-6.1 Sol scored 4.06/5 on its Opportunity Investigator evaluation versus 3.62, 3.52, and 2.94 for alternatives. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How long does it take Amplitude's Wave agent to ship a product improvement using OpenAI models? Amplitude estimates Wave can help teams ship a product improvement in 1 to 2 days, down from roughly a month. Wave identifies opportunities from session replays, analytics, and code, builds a technical plan, and hands it to coding agents such as Codex. Among customer-launched experiments, one in four went live the same day the opportunity was surfaced, and two in three within a week. _daily.dev tracks agentic workflow case studies like this for teams measuring real shipping speed gains._ ### How does GPT-6.1 Sol compare to other models for AI agent code investigation tasks? GPT-6.1 Sol scored 4.06 out of 5 on Amplitude's Opportunity Investigator evaluation, ahead of three alternative models that scored 3.62, 3.52, and 2.94. It led on all five investigation criteria measured (corroboration, false positive avoidance, incorporating evaluator feedback, recovering from tool failures, and evidence alignment) and had the fastest median investigation time at 54 minutes. _developers comparing reasoning models for agent tasks follow benchmarks like this on daily.dev._ ### What OpenAI models power Amplitude's Wave product agent and what does each one do? Wave is roughly 80% powered by OpenAI models: GPT-6.1 Sol handles the opportunity manager and deep investigations into code and data, GPT-6 Luna handles frequent low-cost tasks like scanning code and running small evaluation checks, and GPT-Image-2.5 Flare generates product mockups using screenshots from session replays as visual references. _teams architecting multi-model agent pipelines track real deployments like this one on daily.dev._ ## Similar posts on daily.dev - [Claude, Gemini, and ChatGPT ship new models every week, and I finally stopped chasing every new release](https://daily.dev/posts/claude-gemini-and-chatgpt-ship-new-models-every-week-and-i-finally-stopped-chasing-every-new-rele-5xq9gzu4x) · XDA Developers · 0 upvotes · 0 comments - [OpenAI launches GPT-6 Sol and Luna, boasting lower cost and fewer mistakes](https://daily.dev/posts/openai-launches-gpt-6-sol-and-luna-boasting-lower-cost-and-fewer-mistakes-7fzpvatba) · TechCrunch · 0 upvotes · 0 comments - [How Third Moment Research runs 10,000 agents for 36\+ hours](https://daily.dev/posts/how-third-moment-research-runs-10-000-agents-for-36-hours-ummtnlk1q) · OpenAI · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#openai](https://daily.dev/tags/openai), [#openai-codex](https://daily.dev/tags/openai-codex) [View this post on daily.dev](https://daily.dev/posts/how-amplitude-ships-product-improvements-in-1-2-days-with-openai-falonkq5y) ```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 Amplitude ships product improvements in 1–2 days with OpenAI","url":"https://daily.dev/posts/how-amplitude-ships-product-improvements-in-1-2-days-with-openai-falonkq5y","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-amplitude-ships-product-improvements-in-1-2-days-with-openai-falonkq5y"},"datePublished":"2026-11-12T20:29:57.992Z","dateModified":"2026-11-12T20:33:04.379Z","description":"Amplitude's product agent Wave, roughly 80% powered by OpenAI models, helps teams ship product improvements in an estimated 1-2 days instead of a month. Wave...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c73951c1a3e10c81db8efcc6b5ad3820?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c73951c1a3e10c81db8efcc6b5ad3820?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"OpenAI","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":"OpenAI","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/984b3632316f4afaa3d5213d5c64fe65","url":"https://daily.dev/sources/openai"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-amplitude-ships-product-improvements-in-1-2-days-with-openai-falonkq5y","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,openai,openai-codex","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"OpenAI","item":"https://daily.dev/sources/openai"},{"@type":"ListItem","position":3,"name":"How Amplitude ships product improvements in 1–2 days with OpenAI"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-amplitude-ships-product-improvements-in-1-2-days-with-openai-falonkq5y#faq","mainEntity":[{"@type":"Question","name":"How long does it take Amplitude's Wave agent to ship a product improvement using OpenAI models?","acceptedAnswer":{"@type":"Answer","text":"Amplitude estimates Wave can help teams ship a product improvement in 1 to 2 days, down from roughly a month. Wave identifies opportunities from session replays, analytics, and code, builds a technical plan, and hands it to coding agents such as Codex. Among customer-launched experiments, one in four went live the same day the opportunity was surfaced, and two in three within a week. daily.dev tracks agentic workflow case studies like this for teams measuring real shipping speed gains."}},{"@type":"Question","name":"How does GPT-6.1 Sol compare to other models for AI agent code investigation tasks?","acceptedAnswer":{"@type":"Answer","text":"GPT-6.1 Sol scored 4.06 out of 5 on Amplitude's Opportunity Investigator evaluation, ahead of three alternative models that scored 3.62, 3.52, and 2.94. It led on all five investigation criteria measured (corroboration, false positive avoidance, incorporating evaluator feedback, recovering from tool failures, and evidence alignment) and had the fastest median investigation time at 54 minutes. developers comparing reasoning models for agent tasks follow benchmarks like this on daily.dev."}},{"@type":"Question","name":"What OpenAI models power Amplitude's Wave product agent and what does each one do?","acceptedAnswer":{"@type":"Answer","text":"Wave is roughly 80% powered by OpenAI models: GPT-6.1 Sol handles the opportunity manager and deep investigations into code and data, GPT-6 Luna handles frequent low-cost tasks like scanning code and running small evaluation checks, and GPT-Image-2.5 Flare generates product mockups using screenshots from session replays as visual references. teams architecting multi-model agent pipelines track real deployments like this one on daily.dev."}}]} ```