--- title: More Jev in There There: smart conditions and AI assignment description: Building on an earlier post about using Jev (a Laravel AI SDK helper) to detect spam and auto-replies, There There now applies the same classification approach... canonical: https://daily.dev/posts/more-jev-in-there-there-smart-conditions-and-ai-assignment-t9pb5mogg twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: More Jev in There There: smart conditions and AI assignment | daily.dev og:description: Building on an earlier post about using Jev (a Laravel AI SDK helper) to detect spam and auto-replies, There There now applies the same classification approach... og:url: https://daily.dev/posts/more-jev-in-there-there-smart-conditions-and-ai-assignment-t9pb5mogg og:image: https://api.daily.dev/og/posts/T9pB5MOgg.png og:image:alt: More Jev in There There: smart conditions and AI assignment 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. # More Jev in There There: smart conditions and AI assignment **[FREEK.DEV](https://daily.dev/sources/freek)** · 4 min read · 0 upvotes · 0 comments ## Summary Building on an earlier post about using Jev (a Laravel AI SDK helper) to detect spam and auto-replies, There There now applies the same classification approach to two new features: smart workflow conditions described in plain language instead of keyword lists, and automatic ticket assignment to the right team member. Smart conditions turn a plain-language description into a Jev Boolean question answered alongside existing spam/auto-reply checks, storing the probability with the message so workflows don't re-call Jev. Assignment uses a Jev Choice question with a 'none of these' fallback so vague tickets aren't misrouted, and disabled or channel-restricted members are filtered out before Jev chooses. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How can I use an AI classification question to match support tickets against a plain-language description instead of keyword matching? Define a Boolean question wrapping the description, such as 'The incoming message matches this workflow description: {description}', with true/false answer options tied to whether the message fits. The question runs alongside other classification questions (like spam and auto-reply detection) in one request, and the resulting probability is stored with the message so the workflow can read it later without calling the AI again. _Developers building AI-assisted workflow matching can find implementation patterns like this shared on daily.dev._ ### How do you use an AI model to automatically assign support tickets to the right team member without misrouting vague requests? Ask the AI a Choice question listing eligible people or teams along with short descriptions of what each handles, plus an explicit 'None of these' option. Assignment only happens when there is a clear favorite; if nobody clearly fits, no assignment is made and another workflow step can pick up the ticket later, avoiding unnecessary hand-offs from forced matches. _Teams designing AI-based routing logic often compare approaches like this one via daily.dev before building their own._ --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#php](https://daily.dev/tags/php), [#laravel](https://daily.dev/tags/laravel), [#jev](https://daily.dev/tags/jev) [View this post on daily.dev](https://daily.dev/posts/more-jev-in-there-there-smart-conditions-and-ai-assignment-t9pb5mogg) ```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":"More Jev in There There: smart conditions and AI assignment","url":"https://daily.dev/posts/more-jev-in-there-there-smart-conditions-and-ai-assignment-t9pb5mogg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/more-jev-in-there-there-smart-conditions-and-ai-assignment-t9pb5mogg"},"datePublished":"2026-09-30T14:11:38.929Z","dateModified":"2026-10-01T07:02:27.918Z","description":"Building on an earlier post about using Jev (a Laravel AI SDK helper) to detect spam and auto-replies, There There now applies the same classification approach...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cde79ac5a76910500195eaf604858a91?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cde79ac5a76910500195eaf604858a91?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"FREEK.DEV","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":"FREEK.DEV","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/286e833d1aaa453d99849cd4dbb7a106","url":"https://daily.dev/sources/freek"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/more-jev-in-there-there-smart-conditions-and-ai-assignment-t9pb5mogg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,php,laravel,jev","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"FREEK.DEV","item":"https://daily.dev/sources/freek"},{"@type":"ListItem","position":3,"name":"More Jev in There There: smart conditions and AI assignment"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/more-jev-in-there-there-smart-conditions-and-ai-assignment-t9pb5mogg#faq","mainEntity":[{"@type":"Question","name":"How can I use an AI classification question to match support tickets against a plain-language description instead of keyword matching?","acceptedAnswer":{"@type":"Answer","text":"Define a Boolean question wrapping the description, such as 'The incoming message matches this workflow description: {description}', with true/false answer options tied to whether the message fits. The question runs alongside other classification questions (like spam and auto-reply detection) in one request, and the resulting probability is stored with the message so the workflow can read it later without calling the AI again. Developers building AI-assisted workflow matching can find implementation patterns like this shared on daily.dev."}},{"@type":"Question","name":"How do you use an AI model to automatically assign support tickets to the right team member without misrouting vague requests?","acceptedAnswer":{"@type":"Answer","text":"Ask the AI a Choice question listing eligible people or teams along with short descriptions of what each handles, plus an explicit 'None of these' option. Assignment only happens when there is a clear favorite; if nobody clearly fits, no assignment is made and another workflow step can pick up the ticket later, avoiding unnecessary hand-offs from forced matches. Teams designing AI-based routing logic often compare approaches like this one via daily.dev before building their own."}}]} ```