Neuron AI
GitHubForumNewsletter
  • Getting Started
    • Introduction
  • Key Concepts
  • Installation
  • Agent
  • Tools & Function Calls
  • Streaming
  • RAG
  • Attachments (Documents & Images)
  • Advanced
    • Structured Output
    • Logging & Observability
    • MCP Connector
    • Error Handling
  • Post Processor
  • Components
    • AI provider
    • Chat History & Memory
    • Embeddings Provider
    • Vector Store
    • Data loader
  • Examples
    • YouTube Agent
Powered by GitBook
On this page
  • The Problem With AI Systems
  • Get Started With Inspector
  • Create An Ingestion Key
  • Legacy PHP
  • Laravel
  • Symfony
  • CodeIgniter
  1. Advanced

Logging & Observability

Trace your AI agent implementations to detect errors and performance bottlenecks in real-time.

PreviousStructured OutputNextMCP Connector

Last updated 1 day ago

The Problem With AI Systems

Integrating AI Agents into your application you’re not working only with functions and deterministinc code, you program your agent also influencing probability distributions. Same input ≠ output. That means reproducibility, versioning, and debugging become real problems.

Many of the Agents you build with Neuron AI will contain multiple steps with multiple invocations of LLM calls. As these applications get more and more complex, it becomes crucial to be able to inspect what exactly is going on inside your system.

Why is the model taking certain decisions? What data is the model reacting to?

Prompting is not programming in the common sense. No static types, small changes break output, long prompts cost latency, and no two models behave exactly the same with the same prompt.

The team designed Neuron AI with built-in observability features, so you can monitor AI agents were running, allowing you to get meaningful insights from inside of your agents to help you maintain reliability for production applications.

Get Started With Inspector

You have to install the Inspector package based on your development environment. We provide integration packages for , , , , . Check out our GitHub organizations.

Neuron AI integrates seamlessly with Inspector just installing the appropriate package. When your agents are being executed, you will see the details of their internal steps on the Inspector dashboard.

Create An Ingestion Key

For any additional support drop in a live chat in the the dashboard. We are happy to listen from your experience, find new possible improvements, and make the tool better overtime.

Legacy PHP

To activate monitoring you need to pass the Inspector instance or create a new one if it's not already integrated into your app.

use App\Neuron\MyAgent;
use NeuronAI\Observability\AgentMonitoring;

// The Inspector instance in your application - https://inspector.dev/
$inspector = new \Inspector\Inspector(
    new \Inspector\Configuration('INSPECTOR_INGESTION_KEY')
);

// Attach monitoring to the Agent
$response = MyAgent::make()
    ->observe(new AgentMonitoring($inspector))
    ->chat(...);

Laravel

The Inspector Laravel package already contains an helper function to access the Inspector instance, so you can pass it to the agent:

use App\Neuron\MyAgent;
use NeuronAI\Observability\AgentMonitoring;

// Attach montioring to the Agent
$response = MyAgent::make()
    ->observe(new AgentMonitoring(inspector()))
    ->chat(...);

Symfony

If use the Inspector Symfony bundle you can get the current Inspector instance from the container to pass it to the agent.

use App\Neuron\MyAgent;
use NeuronAI\Observability\AgentMonitoring;

// Retrieve the Inspector instance, or type hint into your current class
$inspector = $this->container->get(\Inspector\Inspector::class);

// Attach montioring to the Agent
$response = MyAgent::make()
    ->observe(new AgentMonitoring($inspector))
    ->chat(...);

CodeIgniter

You can load the inspector service with the helper function, and call the service to be injected into the agent:

use App\Neuron\MyAgent;
use NeuronAI\Observability\AgentMonitoring;

// Load the inspector service
helper('inspector');

// Attach montioring to the Agent
$response = MyAgent::make()
    ->observe(new AgentMonitoring(inspector()))
    ->chat(...);

To create an Ingestion key head to the and create a new app.

For further support don't esitate to contact us via live chat, or at

Inspector dashboard
[email protected]
Inspector
PHP
Laravel
Symfony
CodeIgniter
Drupal