May 31, 2026 Evaluating RAG in Laravel: Is Your Agent Retrieving the Right Chunks? Your Laravel RAG demo answers fine. That doesn't prove retrieval is right. Here's how to eval a RAG system built on the AI SDK and pgvector, and catch the regression that ships to production without a single error. laravel ai rag pgvector laravel-ai-sdk
Read article May 30, 2026 Multi-Agent Orchestration in Laravel: When You Actually Need It The Laravel AI SDK lets one agent delegate to another. Most teams reach for it too early. Here's when sub-agents earn their place, the three gotchas that bite you, and how to test the hand-off. laravel ai agents multi-agent laravel-ai-sdk
Read article May 30, 2026 Prompt-Injection Guardrails in Laravel: Defend the Tools, Not the Prompt You can't out-prompt an attacker — to the model, your instructions and a malicious ticket are the same text. Here's where guardrails actually live in a Laravel AI app: the tools, the middleware, and the output. laravel ai security prompt-injection laravel-ai-sdk
Read article May 29, 2026 Evals in Laravel: How to Prove Your AI Output Is Actually Good Your Laravel AI tests prove the code runs. They don't prove the output is good. Here's how to eval a real feature with the AI SDK: a golden dataset, an LLM judge you build yourself, and a regression gate that catches a bad prompt before your customers do. laravel ai evals testing laravel-ai-sdk
Read article February 18, 2026 Laravel AI SDK + Livewire: Build a Streaming Chat Interface Every Livewire AI chat tutorial uses the raw OpenAI client. This one uses the official Laravel AI SDK — streaming, conversation memory, and production fixes. laravel livewire ai streaming laravel-ai-sdk
Read article 
