Monitor your n8n AI workflows.

n8n workflows often run on a schedule, in the background, after a handover. AgentPing tells you when one fails silently and what each AI run cost, using a webhook node, no SDK required.

Track your first AI workflow Read the n8n setup docs

Production AI in n8n fails quietly.

An n8n workflow can stop firing after an edit, stall on a slow step, or loop quietly while the rest of your automation looks fine. If it runs after a client handover, no one is watching it at all until something downstream breaks.

Wire it up in a few lines.

Add one HTTP Request node (or a final webhook step) that pings AgentPing. A bare ping gives you missed-run and failure alerts; pass the model and the token counts from your AI node and AgentPing prices the run for you, no cost maths in the workflow.

Install

install n8n 
no SDK, just an HTTP Request node

Instrument

example · http request node n8n 
# Heartbeat on every run (HTTP Request node, or curl from any step):
curl "https://eu.ingest.agentping.io/v1/ping?key=ping_…&agent=lead-enrichment&status=ok"

# Send the model + token counts from your AI node; we price it from your rate card:
curl "https://eu.ingest.agentping.io/v1/ping?key=ping_…&agent=lead-enrichment&status=ok\
&provider=openai&model=gpt-4o&input_tokens=1240&output_tokens=380"

# Already have a dollar figure? Pass cost_usd instead and it wins:
curl "https://eu.ingest.agentping.io/v1/ping?key=ping_…&agent=lead-enrichment&status=ok&cost_usd=0.0123"

Full setup, environment variables and options are in the n8n setup docs.

What AgentPing tracks for n8n.

  • Missed run alerts when a scheduled workflow does not fire on time.
  • Failure and stall detection for background flows.
  • Cost per AI run when the workflow calls a model.
  • A heartbeat from any workflow via a single webhook node.
  • Alerts to Slack, email or a webhook you already watch.
Read the n8n setup docs Heartbeat webhook docs

What you see in the dashboard.

  • A run list for n8n, 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 n8n output shows up as a falling line, not a support ticket.
Do I need an SDK for n8n?
No. Any n8n workflow can send a heartbeat or a run event from an HTTP Request node to a webhook. That is enough to get missed-run alerts and, when you include cost fields, per-run cost.
Can I monitor client workflows after handover?
Yes. This is a common case for automation agencies: add a heartbeat to the client workflow before handover, and you get alerted if it goes silent, even though you are no longer watching it day to day.
What does it cost to monitor n8n?
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 n8n AI workflows.

Send one run from n8n and see cost, status and latency. Then add an alert for cost spikes or missed runs.

Track your first AI workflow Read the n8n setup docs

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