This article provides a complete, practical walkthrough of the Manual Stickynote Automate Webhook 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:
   Automating Competitive AI Research: Using n8n and Perplexity to Compare n8n and Make
   
   Meta Description:
   Learn how to build an automated research assistant in n8n with the Perplexity AI API to compare automation platforms like n8n and Make. Discover the power of no-code workflows to generate AI-driven insights.
   
   Keywords:
   n8n automation, Perplexity AI, Make.com, no-code tools, workflow automation, n8n vs Make, AI content generation, competitive analysis, API workflows, automation platforms
   
   Third-Party APIs Used:
   - Perplexity AI (https://www.perplexity.ai)
   
   Article:
   
   Unlocking AI-Powered Research With n8n: A Workflow to Compare n8n and Make
   
   In today’s fast-paced automation landscape, staying ahead of the competition means more than just building workflows – it’s about integrating powerful third-party tools to leverage smart decision-making. One such combination is n8n and Perplexity AI. In this article, we walk through an n8n workflow built to automatically compare two major automation platforms—n8n and Make—using Perplexity AI’s Sonar large language model (LLM). The result? A fully automated research assistant at your fingertips.
   
   Overview: The Power of n8n + Perplexity AI
   
   This workflow demonstrates how low-code/no-code tools like n8n can work with AI language models to automate research and content generation. Specifically, the Perplexity AI API is called upon to analyze and compare the features of n8n and Make.com. You can adapt this powerful setup for your own domains, competitors, or comparison subjects.
   
   Here’s a breakdown of how the workflow operates:
   
   Step 1: Manual Trigger to Start the Workflow
   
   The workflow begins with a Manual Trigger node, allowing the user to test or manually initiate the automation. This is useful for experimentation, testing prompts, or even future extensions like cron jobs or webhooks.
   
   Step 2: Set Parameters
   
   The next stage involves a Set node named "Set Params". This node prepares the necessary parameters required by the Perplexity API. It defines three key variables:
   
   - system_prompt: The persona for the output, in this case, “You are an n8n fanboy.”
   - user_prompt: The actual query posed to the AI, set as “What are the differences between n8n and Make?”
   - domains: The URL scope to narrow the AI’s search — specified as “n8n.io, make.com.”
   
   By assigning these values, the automation defines both tone and scope, steering the AI conversation toward relevant and domain-specific content.
   
   Step 3: Send a Query to Perplexity AI
   
   Using the HTTP Request node labeled "Perplexity Request", the workflow sends a formatted prompt to Perplexity’s Sonar model via a POST request. Here’s what the API call includes:
   
   - Model: "Sonar", which is Perplexity’s most advanced publicly accessible model.
   - Messages: Contains a “system” and “user” message as defined earlier.
   - Temperature & Top_p: Tweaking randomness vs accuracy; our workflow prefers precision by setting temperature low (0.2).
   - Search_domain_filter: This key feature filters the AI’s research to n8n.io and make.com, ensuring focused comparison based on reputable domain sources.
   
   Additional configuration includes turning off image and related question generation, filtering results by recency (last month), and setting penalties for repetitive outputs.
   
   Note: API authentication is done using HTTP Header Auth by providing an Authorization key in the format Bearer pplx-xxxx. A Sticky Note node helps users remember to configure this through Perplexity’s dashboard and documentation.
   
   Step 4: Clean and Format the Output
   
   The last data processing step uses another Set node named "Clean Output". This extracts relevant content from the Perplexity JSON response:
   
   - output: Extracts the AI’s answer from the response’s choices array.
   - citations: Collects any source citations to validate the generated text.
   
   This separation is useful for feeding results into dashboards, sending via email, or integrating with apps like Slack or Notion.
   
   Why Use Perplexity?
   
   Perplexity AI shines in this context because it offers web-grounded LLMs. That means responses are backed by real citations and domain-specific knowledge. By filtering to n8n.io and make.com, you’re essentially training your temporary AI analyst to look only within those ecosystems — ideal for competitive intelligence or customer research.
   
   Future Extensions
   
   This simple but effective workflow is easily extendable. Here are a few ideas:
   
   - Replace the Manual Trigger with a Cron node to run comparisons weekly or monthly.
   - Store results in a Notion database or Google Sheet for historical tracking.
   - Send comparison results to a Slack channel or email inbox for internal reviews.
   - Expand the domain list to include other workflow tools like Zapier, Pipedream, or Workato.
   
   Conclusion: Research, Simplified and Automated
   
   By combining n8n’s powerful automation capabilities with Perplexity’s cutting-edge LLM, you can build intelligent workflows that go far beyond simple task automation. Whether you’re a product marketer, developer advocate, or workflow nerd, this pattern opens up endless opportunities for AI-powered research and decision-making.
   
   This workflow doesn't just answer questions—it creates structure around your research process and removes the bottlenecks associated with manual analysis. In the age of information overload, intelligent automation like this isn’t just helpful—it’s essential.
   
   Ready to tinker or go further? Grab your API key at Perplexity and jump into n8n. Your AI research assistant is just a few clicks away.
   
   — End of Article —

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.