Research topics using OpenRouter AI agents with Serper search and Jina AI reports

by Open Paws ✓ · 264 views · created 2026-01-06 · Market Research, AI RAG

What this workflow does

This AI workflow has 36 nodes and runs when an HTTP POST request hits its webhook URL (plus 1 other trigger). Along the way it connects Jina AI, OpenRouter Chat Model and HTTP Request. It also calls google.serper.dev and api.semanticscholar.org over HTTP.

How it runs

Trigger: When an HTTP POST request hits its webhook URL (plus 1 other trigger).

1. Set Prompt (Edit Fields (Set)): sets 2 fields: prompt, source
2. Searching For Information (AI Agent): runs an AI agent, with model: Qwen, OpenRouter Chat Model; 8 tools (Think, Serper API, XPostScraper, LinkedinScraper…)
3. Retry if Tools Not Used (If): checks a condition and branches into true / false
4. Writing Report (AI Agent): runs an AI agent, with model: Opus, Auto Fallback; 1 tool (Think Tool)
5. Retry if Response Empty (If): checks a condition and branches into true / false
6. Set Report (Edit Fields (Set)): sets 2 fields: Final Report, Retrieved Documents
7. Verifying Report (Basic LLM Chain): sends a prompt to an LLM, with model: Sonnet, Auto Fallback; output parser: Structured Output Parser
8. If: checks a condition and branches into true / false
9. If: checks a condition and branches into true / false
10. Fixing Hallucinations (AI Agent): runs an AI agent, with model: Opus, Auto Fallback; 1 tool (Think Tool)

…plus 5 more steps. See the full node list below.

Services it uses

Jina AIOpenRouter Chat ModelHTTP Request

HTTP calls to: google.serper.dev, api.semanticscholar.org

Before you upgrade to n8n 3.0

Nodes used (12)

• Jina Ai Tooln8n-nodes-base.jinaAiTool
• Think Tool@n8n/n8n-nodes-langchain.toolThink
• OpenRouter Chat Model@n8n/n8n-nodes-langchain.lmChatOpenRouter
• Ifn8n-nodes-base.if
• Http Request Tooln8n-nodes-base.httpRequestTool
• Edit Fields (Set)n8n-nodes-base.set
• AI Agent@n8n/n8n-nodes-langchain.agent
• Webhookn8n-nodes-base.webhook
• Execute Workflow Triggern8n-nodes-base.executeWorkflowTrigger
• Structured Output Parser@n8n/n8n-nodes-langchain.outputParserStructured
• Respond to Webhookn8n-nodes-base.respondToWebhook
• Basic LLM Chain@n8n/n8n-nodes-langchain.chainLlm

From the author

Who is this for This workflow is designed for researchers, analysts, and knowledge workers who need to: - Gather comprehensive information on complex topics from multiple web sources - Get AI-synthesized insights rather than raw search results - Ensure…

View the original on n8n.io → Check your own copy