--- title: Bringing delight to customer phone calls with AI | daily.dev description: Voicify, a voice AI platform for restaurants and healthcare, shares how they overcame latency, traffic spikes, and compliance challenges by migrating to Gemini... canonical: https://daily.dev/posts/bringing-delight-to-customer-phone-calls-with-ai-5baxzd0fj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Bringing delight to customer phone calls with AI | daily.dev og:description: Voicify, a voice AI platform for restaurants and healthcare, shares how they overcame latency, traffic spikes, and compliance challenges by migrating to Gemini... og:url: https://daily.dev/posts/bringing-delight-to-customer-phone-calls-with-ai-5baxzd0fj og:image: https://api.daily.dev/og/posts/5baXzD0Fj.png og:image:alt: Bringing delight to customer phone calls with AI 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. # Bringing delight to customer phone calls with AI **[Google Cloud](https://daily.dev/sources/gcp)** · 5 min read · 1 upvotes · 0 comments ## Summary Voicify, a voice AI platform for restaurants and healthcare, shares how they overcame latency, traffic spikes, and compliance challenges by migrating to Gemini Flash via Google's Gemini Enterprise Agent Platform on Vertex AI. Key outcomes include 25-30% cost savings over previous LLMs, onboarding time reduced from 1-2 weeks to 1-2 days, 100% uptime during peak traffic like Thanksgiving, and improved time-to-first-token metrics. Architectural highlights include dynamic menu context loading (avoiding full menu in prompts) and a multicloud-ready voice orchestration platform meeting HIPAA, SOC2, ISO27001, and PCI compliance requirements. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How much cost savings did switching to Gemini Flash provide compared to previous LLMs for a voice AI ordering platform? Voicify reported approximately 25% to 30% cost savings after switching to Gemini Flash served via Gemini Enterprise Agent Platform, compared to its previous use of other LLMs, along with greater reliability and improved latency for its phone-based ordering assistant. _daily.dev surfaces real cost and latency trade-offs for teams evaluating LLM providers for voice applications._ ### How do you handle large restaurant menus in an LLM prompt without hurting response latency? Rather than placing an entire restaurant menu into a single prompt, Voicify includes only certain menu information in the initial prompt and gathers more details as the conversation progresses. This reduces prompt complexity, improves response times, and keeps focus on only the relevant parts of the menu for each interaction. _Developers designing prompt strategies for complex catalogs can find similar patterns on daily.dev._ ## Similar posts on daily.dev - [Gemini Live API available on Vertex AI](https://daily.dev/posts/gemini-live-api-available-on-vertex-ai-pwpyu7zkz) · Google Cloud · 1 upvotes · 0 comments - [Google Cloud Announces Gemini Enterprise Agent Platform](https://daily.dev/posts/google-cloud-announces-gemini-enterprise-agent-platform-b4ocuevnb) · C\# Corner · 0 upvotes · 0 comments - [Google launches Gemini 3.5 Flash to push AI agents deeper into enterprise workflows](https://daily.dev/posts/google-launches-gemini-3-5-flash-to-push-ai-agents-deeper-into-enterprise-workflows-6mutw1fr1) · InfoWorld · 0 upvotes · 0 comments - [Google finally builds the AI and agent platform it’s been describing for years](https://daily.dev/posts/google-finally-builds-the-ai-and-agent-platform-it-s-been-describing-for-years-v8gbkmxko) · The New Stack · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#google-gemini](https://daily.dev/tags/google-gemini), [#conversational-ai](https://daily.dev/tags/conversational-ai), [#vertex-ai](https://daily.dev/tags/vertex-ai) [View this post on daily.dev](https://daily.dev/posts/bringing-delight-to-customer-phone-calls-with-ai-5baxzd0fj) ```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":"Bringing delight to customer phone calls with AI","url":"https://daily.dev/posts/bringing-delight-to-customer-phone-calls-with-ai-5baxzd0fj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/bringing-delight-to-customer-phone-calls-with-ai-5baxzd0fj"},"datePublished":"2026-07-23T16:07:03.721Z","dateModified":"2026-09-13T19:53:55.166Z","description":"Voicify, a voice AI platform for restaurants and healthcare, shares how they overcame latency, traffic spikes, and compliance challenges by migrating to Gemini...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c33435fc89ca71220276036d34de567e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c33435fc89ca71220276036d34de567e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Google Cloud","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":"Google Cloud","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/gcp","url":"https://daily.dev/sources/gcp"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/bringing-delight-to-customer-phone-calls-with-ai-5baxzd0fj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,google-gemini,conversational-ai,vertex-ai","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Google Cloud","item":"https://daily.dev/sources/gcp"},{"@type":"ListItem","position":3,"name":"Bringing delight to customer phone calls with AI"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/bringing-delight-to-customer-phone-calls-with-ai-5baxzd0fj#faq","mainEntity":[{"@type":"Question","name":"How much cost savings did switching to Gemini Flash provide compared to previous LLMs for a voice AI ordering platform?","acceptedAnswer":{"@type":"Answer","text":"Voicify reported approximately 25% to 30% cost savings after switching to Gemini Flash served via Gemini Enterprise Agent Platform, compared to its previous use of other LLMs, along with greater reliability and improved latency for its phone-based ordering assistant. daily.dev surfaces real cost and latency trade-offs for teams evaluating LLM providers for voice applications."}},{"@type":"Question","name":"How do you handle large restaurant menus in an LLM prompt without hurting response latency?","acceptedAnswer":{"@type":"Answer","text":"Rather than placing an entire restaurant menu into a single prompt, Voicify includes only certain menu information in the initial prompt and gathers more details as the conversation progresses. This reduces prompt complexity, improves response times, and keeps focus on only the relevant parts of the menu for each interaction. Developers designing prompt strategies for complex catalogs can find similar patterns on daily.dev."}}]} ```