Watch and track your favorite playlist.
Curated by: Laravel News (16 videos)
Episode 2 of Ship AI with Laravel, a series on Laravel News where we build a full AI platform using Laravel 13 and the Laravel AI SDK. Last episode we got our support agent responding to customers. But the responses are free text. You can't route a ticket, set a priority, or track sentiment from a paragraph of English. You need data. In this episode we build a TicketClassifier agent that returns structured output instead of prose. You give it a customer message like "I was charged twice and nobody is answering my emails" and it comes back with category: billing, priority: high, sentiment: angry, and a one-line summary. Every field is constrained to specific allowed values so you always get clean, predictable data. We set the temperature to 0.3 for consistent classification, define a schema with four required fields, test it with different messages to make sure billing/angry and shipping/neutral come back correctly, then wire up a TicketController store method that validates input, classifies the ticket, and returns a 201 response. I verify the whole flow end to end in Tinker. ⭐ GitHub: https://github.com/harris21/ship-ai-with-laravel 👉 Full series playlist: https://www.youtube.com/playlist?list=PLsmlCYEtWNI_plnKPPO13XjfDJoMIfhLN 👉 Timestamps 00:00 Why Tickets Need AI 00:37 From Free Text to Structure 01:22 Scaffold Classifier Agent 02:24 Prompt Rules and Schema 03:54 Route Test and Debug 05:38 Second Example Shipping 06:14 Build Store Workflow 08:17 Routes and Automation Ideas 09:07 End to End Test in Tinker 10:20 Wrap Up and Next Episode ---------------------------------------------------------------------- ➫ Business Inquiries: hello@laravel-news.com ---------------------------------------------------------------------- JOIN OUR WEEKLY LARAVEL NEWSLETTER 👉 https://laravel-news.com/newsletter ----------------------------------------------------------------------