This article provides a complete, practical walkthrough of the Splitout Filter Monitor Triggered n8n agent. It connects HTTP Request, Webhook across approximately 1 node(s). Expect a Intermediate setup in 15-45 minutes. One‑time purchase: €29.

What This Agent Does

This agent orchestrates a reliable automation between HTTP Request, Webhook, handling triggers, data enrichment, and delivery with guardrails for errors and rate limits.

It streamlines multi‑step processes that would otherwise require manual exports, spreadsheet cleanup, and repeated API requests. By centralizing logic in n8n, it reduces context switching, lowers error rates, and ensures consistent results across teams.

Typical outcomes include faster lead handoffs, automated notifications, accurate data synchronization, and better visibility via execution logs and optional Slack/Email alerts.

How It Works

The workflow uses standard n8n building blocks like Webhook or Schedule triggers, HTTP Request for API calls, and control nodes (IF, Merge, Set) to validate inputs, branch on conditions, and format outputs. Retries and timeouts improve resilience, while credentials keep secrets safe.

Third‑Party Integrations

• HTTP Request
• Webhook

Import and Use in n8n

1. Open n8n and create a new workflow or collection.
2. Choose Import from File or Paste JSON.
3. Paste the JSON below, then click Import.
4. Show n8n JSON

   Title:  
   Discover Which AI Models Your n8n Workflows Use Automatically with This Smart Workflow
   
   Meta Description:  
   Use this custom n8n workflow to scan your entire n8n instance and identify which AI models are in use across all workflows. Automatically logs results in Google Sheets for quick reference and tracking.
   
   Keywords:  
   n8n, automation, AI models, workflow analysis, Google Sheets, OpenAI, model detection, automation tools, workflow audit, API integration
   
   Third-Party APIs Used:
   - Google Sheets API (via OAuth2 credentials)
   - n8n API (for fetching workflow definitions from the instance)
   
   Article:
   
   Use n8n to Monitor and Document AI Models Across All Workflows
   
   As more teams and developers integrate AI into their automation suites, it becomes increasingly difficult to keep track of which workflows are using which AI models. Whether you're using GPT-4, Claude, or another LLM (Large Language Model), visibility is key for performance optimization, auditing, and ensuring compliance. This is where an intelligent automation can make all the difference.
   
   Thanks to a contributor in the automation space (@darrell_tw_), there's now a powerful n8n workflow designed to automatically detect and document the use of AI models in your n8n instance — no manual digging required.
   
   Let’s break down how this workflow works and how it can help you streamline your AI workflow audits.
   
   🔧 What This Workflow Does
   
   This custom n8n workflow scans your entire n8n instance, identifies any node that references an AI model (via the model or modelId parameter), and records this information in a structured Google Sheet.
   
   In essence, it answers a core question:  
   💡 "Which AI model is being used where in my automation setup?"
   
   Here’s what it identifies:
   - The workflow name and ID
   - The node where the model is used
   - The model's identifier or name (depending on implementation)
   - A link to access or edit the specific node/workflow directly
   
   📁 Google Sheets Connection  
   All gathered data is logged to a Google Sheet, so you’ll have a persistent, centralized dashboard that keeps updating as your automations evolve.
   
   📈 Use Case Highlights
   
   Let’s say your organization adopts a new company-wide policy to use a different AI provider or model. Before you can update workflows, you need visibility. Instead of combing through dozens — or hundreds — of workflows manually, this workflow automatically shows you where changes need to happen.
   
   Here are some common use cases:
   - Migration from GPT-3.5 to GPT-4
   - Cost auditing of AI model usage
   - Detecting beta or deprecated models in active use
   - Building documentation and configuration management reports
   - Complying with data governance or AI ethics policies
   
   🔍 How It Works (Step-by-Step)
   
   1. Manual Trigger:  
   The workflow begins with a manual trigger node so you can test it without unnecessary executions.
   
   2. Fetch All Workflows:  
   Using the built-in n8n API node (with n8nApi credentials), the workflow fetches all workflows that belong to the current instance.
   
   3. Filter Relevant Workflows:  
   A filter node checks whether each workflow contains references to "modelId" — a key indicator of AI model usage. This avoids unnecessary processing of unrelated workflows.
   
   4. Batch Scanning:  
   Each filtered workflow is processed in a loop (SplitInBatches node), ensuring performance doesn’t degrade, even if you have many workflows. There’s also a warning about performance if you manage 100+ workflows.
   
   5. Node-Level Analysis:  
   The workflow uses a SplitOut node to isolate the nodes within each workflow, then examines each individually using another filter. It looks for:
       - nodes containing `parameters.model`  
       - or `parameters.modelId`  
   
   6. Extract Key Information:  
   In a Set node labeled "Edit Fields", the workflow constructs a detailed data object for each match, including:
       - node name  
       - model ID or name  
       - workflow name and ID  
       - direct URL to the node in your n8n instance  
   
   7. Save Results to Google Sheet:  
   Two key Google Sheets operations are performed:
       - The sheet is cleared at the beginning to avoid duplicate entries.
       - Findings are appended as structured rows via the Google Sheets API, authenticated with a personal OAuth2 credential.
   
   🧠 Customization Tips
   
   - Replace the placeholder domain token {Your-n8n-domain} with your actual n8n instance domain inside the Set node to generate valid workflow URLs.
   - To make the dashboard even more interactive, you could connect this to a Notion database, BI tool, or trigger email alerts if specific models are found.
   
   📌 Important Notes
   
   - Since this uses internal APIs and processes many items, it is advised not to run too frequently, especially on large-scale n8n instances (100+ workflows).
   - The creator helpfully includes sticky notes in the workflow itself, noting where to customize for your own domain and giving credit for its creation.
   
   👤 About the Creator
   
   This workflow was built by Darrell (@darrell_tw_), an automation and AI-focused engineer who actively contributes tooling to the cloud automation community. You can connect and follow updates via his website or social media platforms (X, Threads, Instagram).
   
   🚀 Wrap-Up
   
   This clever automation fills a critical gap for teams working with multiple AI models across automation workflows. By integrating AI model tracking into your operational tools, you enhance transparency and enable more agile decision-making in scaling or adapting your tech stack.
   
   Whether you're managing a few automations or an enterprise deployment, this n8n workflow is a vital tool for sustainably growing your AI footprint.
   
   Try it out. Improve your visibility. Automate your audits.
   
   👉 BONUS: View and copy the workflow on Darrell's official channels:
   Website: https://www.darrelltw.com  
   GitHub or n8n.io templates (if available in the future)
   
   Start using automation to manage automation — it’s automation inception at its finest.

5. Set credentials for each API node (keys, OAuth) in Credentials.
6. Run a test via Execute Workflow. Inspect Run Data, then adjust parameters.
7. Enable the workflow to run on schedule, webhook, or triggers as configured.

Tips: keep secrets in credentials, add retries and timeouts on HTTP nodes, implement error notifications, and paginate large API fetches.

Validation: use IF/Code nodes to sanitize inputs and guard against empty payloads.

Why Automate This with AI Agents

AI‑assisted automations offload repetitive, error‑prone tasks to a predictable workflow. Instead of manual copy‑paste and ad‑hoc scripts, your team gets a governed pipeline with versioned state, auditability, and observable runs.

n8n’s node graph makes data flow transparent while AI‑powered enrichment (classification, extraction, summarization) boosts throughput and consistency. Teams reclaim time, reduce operational costs, and standardize best practices without sacrificing flexibility.

Compared to one‑off integrations, an AI agent is easier to extend: swap APIs, add filters, or bolt on notifications without rewriting everything. You get reliability, control, and a faster path from idea to production.

Best Practices

• Credentials: restrict scopes and rotate tokens regularly.
• Resilience: configure retries, timeouts, and backoff for API nodes.
• Data Quality: validate inputs; normalize fields early to reduce downstream branching.
• Performance: batch records and paginate for large datasets.
• Observability: add failure alerts (Email/Slack) and persistent logs for auditing.
• Security: avoid sensitive data in logs; use environment variables and n8n credentials.

FAQs

Can I swap integrations later? Yes. Replace or add nodes and re‑map fields without rebuilding the whole flow.

How do I monitor failures? Use Execution logs and add notifications on the Error Trigger path.

Does it scale? Use queues, batching, and sub‑workflows to split responsibilities and control load.

Is my data safe? Keep secrets in Credentials, restrict token scopes, and review access logs.