Docs → Platforms → Lindy

Lindy Integration Guide

Connect Lindy workflows to OpsViz using the HTTP Request action. Track every AI task execution, cost, and token usage automatically.

How it works in 30 seconds

1.Create an agent in OpsViz → get your webhook URL (10 seconds)
2.Add one HTTP Request step to your Lindy workflow → paste the URL (2 minutes)
3.See costs, tokens, and alerts in real time (instantly)

Privacy note: OpsViz receives only operational metadata — event type, token counts, model name, cost, and duration. Your prompts, responses, user data, and AI provider credentials are never sent to OpsViz.

Set up with AI — copy and paste

The fastest way to add OpsViz monitoring is to paste this prompt into Lindy's conversational interface. It sets everything up automatically.

Using Lindy's conversational interface (recommended)

Lindy has a conversational setup — just tell it what you want in plain English. Start a conversation with your Lindy workflow and say:

At the end of my [workflow name] workflow, add a step that sends a POST request to [WEBHOOK_URL] with a JSON body containing: event_type as "task.completed", agent_name as "[workflow name]", and the model name, token counts, cost, and duration_ms (how long the task took) from the previous AI step. Send it and don't wait for the response, so monitoring never slows my workflow down.

Prerequisites

An active Lindy account
An OpsViz account with an agent created
Your OpsViz webhook URL (from the Agents page)

Copy your OpsViz webhook URL

In OpsViz, go to Agents → Your Agent → Webhook URL. Copy the full URL — in these guides we show it as [WEBHOOK_URL]

Add an HTTP Request step to your Lindy workflow

In your Lindy workflow, after the step that calls your AI model, add a Webhook or HTTP Request action.

• Method: POST
• URL: paste your OpsViz webhook URL
• Content-Type: application/json

Configure the request body

Set the JSON body, mapping fields from the previous step's output where available:

{
  "event_type": "task.completed",
  "agent_name": "My Lindy Workflow",
  "model": "{{model}}",
  "tokens_in": {{tokens_in}},
  "tokens_out": {{tokens_out}},
  "cost_usd": {{cost_usd}},
  "duration_ms": {{duration_ms}},
  "status": "success"
}

Only event_type is required — include the others when Lindy exposes them.

Handle errors (optional)

On any error branch in your workflow, add a second HTTP Request step with "event_type": "task.failed" and "status": "error" so failures are tracked too.

Test the integration

Trigger your Lindy workflow once and check your OpsViz dashboard. The event should appear within a few seconds.

That's it!

Events will appear on your OpsViz dashboard as they arrive. Check the webhook reference for full payload options.