Laravel Ai Sdk

by asyrafhussin1aa0ff717c10MIT86 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 6 weeks ago

Laravel AI SDK for building AI-powered features. Use when creating agents, generating images or audio, working with embeddings, vector search, or testing AI features. Triggers on tasks involving laravel/ai, AI agents, tool-calling, structured output, streaming, embeddings, reranking, or AI faking in tests.

AI-generated overview

Guidelines for building AI features in Laravel with the laravel/ai SDK, covering agents, tools, embeddings, media and testing.

What it does
This skill is a reference guide for the Laravel AI SDK (laravel/ai), organized into 17 rules across seven categories: agents, tools, embeddings and search, media generation, files and vector stores, infrastructure, and testing. It explains patterns such as creating agents, prompting with conversation context, structured output, streaming and queueing, custom and provider tools, image and audio generation, embeddings and reranking, and faking AI features in tests. It produces guidance and code examples rather than runnable artifacts, and points to individual rule files and a compiled AGENTS.md document.
When to use it
Use it when writing Laravel code that integrates the laravel/ai SDK, such as creating AI agents, tool calling, structured output, streaming responses, embeddings, vector search or RAG, media generation, or testing AI features with fakes. It targets Laravel 13 and PHP 8.3 or later.
Requirements
No scripts are included; it is instructions and reference documents only. Applying the guidance assumes a Laravel 13 project on PHP 8.3 or later with the laravel/ai package installed, plus whatever AI provider credentials and network access the described features require.

Laravel AI SDK

Comprehensive guide for building AI-powered features with the Laravel AI SDK (laravel/ai). Contains 17 rules across 7 categories covering agents, tools, media generation, embeddings, vector stores, and testing.

When to Apply

Reference these guidelines when:

  • Creating AI agents with instructions, tools, and structured output
  • Prompting agents with conversation context
  • Streaming or queueing agent responses
  • Generating images, audio, or transcriptions
  • Creating and querying vector embeddings
  • Building RAG (retrieval-augmented generation) features
  • Testing AI features with fakes and assertions

Rule Categories by Priority

PriorityCategoryImpactPrefix
1AgentsCRITICALagent-
2ToolsHIGHtool-
3Embeddings & SearchHIGHembed-
4Media GenerationMEDIUMmedia-
5Files & StorageMEDIUMfiles-
6InfrastructureMEDIUMinfra-
7TestingHIGHtest-

Quick Reference

1. Agents (CRITICAL)

  • agent-create-configure - Create agents with artisan, PHP attribute configuration
  • agent-prompting - Prompt agents, conversation context, RemembersConversations
  • agent-structured-output - Structured output with JSON schema
  • agent-streaming-async - Streaming, broadcasting, and queueing responses
  • agent-middleware - Agent middleware pipeline
  • agent-anonymous - Anonymous agents for quick interactions

2. Tools (HIGH)

  • tool-create - Create custom tools with schema and handle method
  • tool-provider - Provider tools: WebSearch, WebFetch, FileSearch, SimilaritySearch

3. Embeddings & Search (HIGH)

  • embed-generate-cache - Generate, store, and cache vector embeddings
  • embed-rerank - Rerank documents and collections by relevance

4. Media Generation (MEDIUM)

  • media-images - Generate, store, and queue images
  • media-audio-transcription - Text-to-speech and speech-to-text

5. Files & Storage (MEDIUM)

  • files-vector-stores - File storage and vector stores for RAG

6. Infrastructure (MEDIUM)

  • infra-failover - Automatic provider failover for resilience

7. Testing (HIGH)

  • test-agents - Fake agents, assert prompts, prevent stray prompts
  • test-media - Fake images, audio, and transcriptions
  • test-data - Fake embeddings, reranking, files, and vector stores

Essential Patterns

Creating an Agent

php
<?php
namespace App\Ai\Agents;
use Laravel\Ai\Contracts\Agent;use Laravel\Ai\Promptable;
class SalesCoach implements Agent{    use Promptable;
    public function instructions(): string    {        return 'You are a sales coach, analyzing transcripts and providing feedback.';    }}

Prompting

php
use App\Ai\Agents\SalesCoach;
$response = SalesCoach::make()->prompt('Analyze this sales transcript...');
return (string) $response;

Generating Images

php
use Laravel\Ai\Image;
$image = Image::of('A donut sitting on the kitchen counter')    ->landscape()    ->generate();
$path = $image->store();

Generating Embeddings

php
use Illuminate\Support\Str;
$embeddings = Str::of('Napa Valley has great wine.')->toEmbeddings();

Testing

php
use App\Ai\Agents\SalesCoach;
SalesCoach::fake(['First response', 'Second response']);
SalesCoach::make()->prompt('Analyze this...');
SalesCoach::assertPrompted('Analyze this...');

How to Use

Read individual rule files for detailed explanations and code examples.

Each rule file contains:

  • YAML frontmatter with metadata (title, impact, tags)
  • Brief explanation of why it matters
  • Bad Example with explanation
  • Good Example with explanation
  • Laravel 13 and PHP 8.3 specific context and references

Full Compiled Document

For the complete guide with all rules expanded: AGENTS.md

Source and attribution

Source:asyrafhussin/agent-skillsinskills/laravel-ai-sdkat commit1aa0ff7

License: MIT

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal