Monitor your Laravel AI agents and jobs.

AI work in a Laravel app often runs inside queued jobs and the scheduler. AgentPing has a first-party package that captures each run, so cost, missed runs and quality are visible without leaving the framework.

Track your first AI workflow Read the Laravel SDK docs

Production AI in Laravel fails quietly.

AI inside a Laravel queue or schedule fails the same quiet way: a job stops being dispatched, a scheduled command silently no-ops, or token spend creeps inside a job no one is watching. Laravel logs the exception you do throw, not the run that simply did not happen.

Wire it up in a few lines.

Wrap AI work inside a job or scheduled command. The package flushes on the job boundary, so a long-running worker still reports each run, and a job that stops dispatching can raise a missed-run alert.

Install

install Laravel 
composer require agentping/laravel

Instrument

example · php Laravel 
use AgentPing\Laravel\Facades\AgentPing;

// Inside a queued job or scheduled command:
AgentPing::run('nightly-digest', ['customer_id' => 'acme-corp'], function () use ($ticket) {
    return $assistant->handle($ticket);
});

Full setup, environment variables and options are in the Laravel SDK docs.

What AgentPing tracks for Laravel.

  • Cost per run for AI calls inside jobs and commands, priced server side.
  • Cost by customer and feature, tagged where the work runs.
  • Missed run alerts for scheduled commands and recurring jobs.
  • Run status and latency, with the SDK flushing per job.
  • Output quality scoring on sampled runs.
Read the Laravel SDK docs Heartbeat webhook docs

What you see in the dashboard.

  • A run list for Laravel, each row showing cost, status and latency, filterable by agent, customer and feature.
  • Cost by agent, customer and feature, so you can see which accounts and features drive AI spend, not just one provider total.
  • An incident the moment a scheduled run misses its window or a cost spike breaks its baseline, delivered to Slack, email, PagerDuty or a webhook.
  • A quality trend once you turn on scoring, so a regression in your Laravel output shows up as a falling line, not a support ticket.
Does it work inside queued jobs?
Yes. The package flushes telemetry on a per-job boundary, so AI work inside a queued job is captured even on a long-running worker, and a job that stops being dispatched can raise a missed-run alert.
Does it auto-instrument the Laravel AI SDK?
It listens to the framework AI events where present, so model calls are captured into the current run without manual wiring, and you can still open a run explicitly around any block of work.
What does it cost to monitor Laravel?
There is a free plan with no card and no time limit, enough to wire up your first agents. Paid plans start at $99/month with named limits and no metered billing, so the bill never surprises you. Annual billing is two months free.
Does AgentPing see my prompts and outputs?
Only if you choose to send them. By default AgentPing prices runs from model and token counts and tracks status and timing, which needs no prompt or output content. Payload capture for quality scoring is opt-in and configurable per agent.

Monitor your Laravel AI workflows.

Send one run from Laravel and see cost, status and latency. Then add an alert for cost spikes or missed runs.

Track your first AI workflow Read the Laravel SDK docs

Spend, cost attribution → Pulse, live monitoring → Verify, quality scoring →