--- title: Integrating Looker and Gemini Enterprise | daily.dev description: Google Cloud's Looker semantic layer now integrates with Gemini Enterprise via the Agent-to-Agent (A2A) protocol, enabling natural language queries against... canonical: https://daily.dev/posts/integrating-looker-and-gemini-enterprise-uf8ty4ash twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Integrating Looker and Gemini Enterprise | daily.dev og:description: Google Cloud's Looker semantic layer now integrates with Gemini Enterprise via the Agent-to-Agent (A2A) protocol, enabling natural language queries against... og:url: https://daily.dev/posts/integrating-looker-and-gemini-enterprise-uf8ty4ash og:image: https://api.daily.dev/og/posts/UF8tY4ASH.png og:image:alt: Integrating Looker and Gemini Enterprise 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. # Integrating Looker and Gemini Enterprise **[Google Cloud](https://daily.dev/sources/gcp)** · 6 min read · 0 upvotes · 0 comments ## Summary Google Cloud's Looker semantic layer now integrates with Gemini Enterprise via the Agent-to-Agent (A2A) protocol, enabling natural language queries against governed enterprise data. The integration routes Gemini chat requests through Looker's semantic layer, which generates deterministic SQL based on version-controlled business logic — eliminating AI hallucinations from raw NL2SQL guesswork. Security is maintained through a zero-risk pass-through architecture: data is never stored or replicated by Gemini, OAuth consent binds user sessions to Looker credentials, and existing row-level and column-level access controls are fully enforced. Users also get interactive, presentation-ready charts directly in the Gemini chat interface, and Looker agents can interoperate with other first- and third-party agents for multi-agent workflows. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does the Looker and Gemini Enterprise integration prevent AI hallucinations in business metrics? Looker's governed semantic layer generates deterministic, precise SQL based on version-controlled business logic instead of letting a language model guess table joins and filters. When a user requests a KPI like revenue, the request routes to a Looker agent that returns the exact, governed enterprise metric rather than an inconsistent guess, eliminating the schema-guessing problem typical of NL2SQL models. _Explore how developers keep AI-generated analytics accurate and governed via daily.dev._ ### What security model does the Looker to Gemini Enterprise integration use to protect enterprise data? It uses a zero-risk pass-through architecture where Gemini Enterprise processes data live but never ingests, replicates, or stores underlying database records. Users provide a one-time OAuth consent binding their Gemini session to their Looker credentials, and existing row-level and column-level access controls, including restrictions on sensitive rows like payroll data, remain enforced even when agents are published to the Agent Gallery. _Track how enterprise AI integrations balance data access with governance on daily.dev._ ### What happened to Looker agents published in Gemini Enterprise before Looker release 26.12? Agents published before Looker release 26.12 lack the newer native chart and interactive visualization capabilities added in this integration update. Google recommends updating or republishing those agents to take advantage of the enhanced visualizations, which render presentation-ready charts like monthly sales trends or regional distributions directly inside the Gemini Enterprise chat interface. _Follow release-specific upgrade steps for BI agent tooling like this on daily.dev._ ## Similar posts on daily.dev - [Dashboard agents in Looker](https://daily.dev/posts/dashboard-agents-in-looker-rxfzczvoc) · Google Cloud · 1 upvotes · 0 comments - [Looker Conversational Analytics now GA](https://daily.dev/posts/looker-conversational-analytics-now-ga-etaqfwjoq) · Google Cloud · 2 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 unveils Gemini Enterprise to provide companies a more unified platform for AI innovation](https://daily.dev/posts/google-unveils-gemini-enterprise-to-provide-companies-a-more-unified-platform-for-ai-innovation-i1bhoim6n) · SD Times · 2 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#data-engineering](https://daily.dev/tags/data-engineering), [#google-gemini](https://daily.dev/tags/google-gemini), [#bi](https://daily.dev/tags/bi) [View this post on daily.dev](https://daily.dev/posts/integrating-looker-and-gemini-enterprise-uf8ty4ash) ```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":"Integrating Looker and Gemini Enterprise","url":"https://daily.dev/posts/integrating-looker-and-gemini-enterprise-uf8ty4ash","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/integrating-looker-and-gemini-enterprise-uf8ty4ash"},"datePublished":"2026-08-11T16:12:35.150Z","dateModified":"2026-09-13T21:58:14.536Z","description":"Google Cloud's Looker semantic layer now integrates with Gemini Enterprise via the Agent-to-Agent (A2A) protocol, enabling natural language queries against...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/470f6eb1f2b7fb43c1407821dff266c4?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/470f6eb1f2b7fb43c1407821dff266c4?_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/integrating-looker-and-gemini-enterprise-uf8ty4ash","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,data-engineering,google-gemini,bi","timeRequired":"PT6M"} {"@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":"Integrating Looker and Gemini Enterprise"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/integrating-looker-and-gemini-enterprise-uf8ty4ash#faq","mainEntity":[{"@type":"Question","name":"How does the Looker and Gemini Enterprise integration prevent AI hallucinations in business metrics?","acceptedAnswer":{"@type":"Answer","text":"Looker's governed semantic layer generates deterministic, precise SQL based on version-controlled business logic instead of letting a language model guess table joins and filters. When a user requests a KPI like revenue, the request routes to a Looker agent that returns the exact, governed enterprise metric rather than an inconsistent guess, eliminating the schema-guessing problem typical of NL2SQL models. Explore how developers keep AI-generated analytics accurate and governed via daily.dev."}},{"@type":"Question","name":"What security model does the Looker to Gemini Enterprise integration use to protect enterprise data?","acceptedAnswer":{"@type":"Answer","text":"It uses a zero-risk pass-through architecture where Gemini Enterprise processes data live but never ingests, replicates, or stores underlying database records. Users provide a one-time OAuth consent binding their Gemini session to their Looker credentials, and existing row-level and column-level access controls, including restrictions on sensitive rows like payroll data, remain enforced even when agents are published to the Agent Gallery. Track how enterprise AI integrations balance data access with governance on daily.dev."}},{"@type":"Question","name":"What happened to Looker agents published in Gemini Enterprise before Looker release 26.12?","acceptedAnswer":{"@type":"Answer","text":"Agents published before Looker release 26.12 lack the newer native chart and interactive visualization capabilities added in this integration update. Google recommends updating or republishing those agents to take advantage of the enhanced visualizations, which render presentation-ready charts like monthly sales trends or regional distributions directly inside the Gemini Enterprise chat interface. Follow release-specific upgrade steps for BI agent tooling like this on daily.dev."}}]} ```