--- title: Introducing ai_decide: make fast decisions on your... description: Databricks launched ai_decide, a new AI Function powered by a decision model that makes fast, low-cost structured decisions over governed data instead of... canonical: https://daily.dev/posts/introducing-ai-decide-make-fast-decisions-on-your-governed-data-pn7hhms9g twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing ai_decide: make fast decisions on your governed data | daily.dev og:description: Databricks launched ai_decide, a new AI Function powered by a decision model that makes fast, low-cost structured decisions over governed data instead of... og:url: https://daily.dev/posts/introducing-ai-decide-make-fast-decisions-on-your-governed-data-pn7hhms9g og:image: https://api.daily.dev/og/posts/Pn7HHms9G.png og:image:alt: Introducing ai_decide: make fast decisions on your governed data 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. # Introducing ai_decide: make fast decisions on your governed data **[databricks](https://daily.dev/sources/databricks)** · 6 min read · 1 upvotes · 0 comments ## Summary Databricks launched ai_decide, a new AI Function powered by a decision model that makes fast, low-cost structured decisions over governed data instead of generating text. It evaluates one or more questions against unstructured input in a fraction of a second, returning probabilities, named-criteria choices, or ordered scores. Use cases include support ticket tagging, LLM model routing, and agent evaluation against policy. It is callable from SQL or a REST API, is compatible with TypeSafe AI's Jev decision model API, and is currently available in Beta. A live Snake game demo shows ai_decide making real-time move decisions. ## 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 ai_decide function in Databricks and when should I use it? ai_decide is a Databricks AI Function powered by a decision model that evaluates one or more questions against unstructured text and returns a probability, a choice from named criteria, or a score on an ordered scale, all in a fraction of a second. It suits structured decisions like ticket classification, model routing, or policy compliance checks where full LLM text generation is unnecessary, offering lower latency and cost. It is available in Beta via SQL or a REST API. _daily.dev surfaces practical releases like this for teams weighing LLM alternatives for structured decisions._ ### How is a decision model like Jev different from using an LLM for classification tasks? A decision model such as TypeSafe AI's Jev takes unstructured input plus a set of questions and returns decisions with probabilities directly, rather than generating text like an LLM does. This avoids the extra latency and cost of text generation for simple structured tasks such as categorizing tickets or routing prompts to models, which matters at enterprise scale where these costs compound. _developers comparing LLMs against lighter decision models for classification track shifts like this on daily.dev._ ### Can I call Databricks ai_decide from both SQL and a REST API? Yes, ai_decide can be called from SQL to make structured decisions at scale over stored data, or through a REST API for real-time applications and agents. It is directly compatible with teams already building on the TypeSafe AI API, and Databricks also lets you serve and run other open-weight decision models directly in SQL. _engineers integrating real-time decision logic into agents follow tooling updates like this on daily.dev._ ## Similar posts on daily.dev - [As AI agents grow, vendors carve out decision-making as a separate model layer](https://daily.dev/posts/as-ai-agents-grow-vendors-carve-out-decision-making-as-a-separate-model-layer-s16prsxwi) · InfoWorld · 0 upvotes · 0 comments - [Microsoft separates decision-making from generative AI with a new model](https://daily.dev/posts/microsoft-separates-decision-making-from-generative-ai-with-a-new-model-z7lrvkhp8) · InfoWorld · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#big-data](https://daily.dev/tags/big-data), [#databricks](https://daily.dev/tags/databricks), [#ai-gateway](https://daily.dev/tags/ai-gateway) [View this post on daily.dev](https://daily.dev/posts/introducing-ai-decide-make-fast-decisions-on-your-governed-data-pn7hhms9g) ```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":"Introducing ai_decide: make fast decisions on your governed data","url":"https://daily.dev/posts/introducing-ai-decide-make-fast-decisions-on-your-governed-data-pn7hhms9g","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-ai-decide-make-fast-decisions-on-your-governed-data-pn7hhms9g"},"datePublished":"2026-09-30T20:02:44.912Z","dateModified":"2026-09-30T20:03:08.721Z","description":"Databricks launched ai_decide, a new AI Function powered by a decision model that makes fast, low-cost structured decisions over governed data instead of...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/88d130c7d1d8514e4b87a2af91d1819d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/88d130c7d1d8514e4b87a2af91d1819d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"databricks","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":"databricks","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/fa7aa720f2db4d1eba826814730482c8","url":"https://daily.dev/sources/databricks"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/introducing-ai-decide-make-fast-decisions-on-your-governed-data-pn7hhms9g","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,big-data,databricks,ai-gateway","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"databricks","item":"https://daily.dev/sources/databricks"},{"@type":"ListItem","position":3,"name":"Introducing ai_decide: make fast decisions on your governed data"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/introducing-ai-decide-make-fast-decisions-on-your-governed-data-pn7hhms9g#faq","mainEntity":[{"@type":"Question","name":"What is the ai_decide function in Databricks and when should I use it?","acceptedAnswer":{"@type":"Answer","text":"ai_decide is a Databricks AI Function powered by a decision model that evaluates one or more questions against unstructured text and returns a probability, a choice from named criteria, or a score on an ordered scale, all in a fraction of a second. It suits structured decisions like ticket classification, model routing, or policy compliance checks where full LLM text generation is unnecessary, offering lower latency and cost. It is available in Beta via SQL or a REST API. daily.dev surfaces practical releases like this for teams weighing LLM alternatives for structured decisions."}},{"@type":"Question","name":"How is a decision model like Jev different from using an LLM for classification tasks?","acceptedAnswer":{"@type":"Answer","text":"A decision model such as TypeSafe AI's Jev takes unstructured input plus a set of questions and returns decisions with probabilities directly, rather than generating text like an LLM does. This avoids the extra latency and cost of text generation for simple structured tasks such as categorizing tickets or routing prompts to models, which matters at enterprise scale where these costs compound. developers comparing LLMs against lighter decision models for classification track shifts like this on daily.dev."}},{"@type":"Question","name":"Can I call Databricks ai_decide from both SQL and a REST API?","acceptedAnswer":{"@type":"Answer","text":"Yes, ai_decide can be called from SQL to make structured decisions at scale over stored data, or through a REST API for real-time applications and agents. It is directly compatible with teams already building on the TypeSafe AI API, and Databricks also lets you serve and run other open-weight decision models directly in SQL. engineers integrating real-time decision logic into agents follow tooling updates like this on daily.dev."}}]} ```