Analyze USD/JPY rates with AI and Tavily news search for email reporting
Needs changesWhat this workflow does
This AI workflow has 8 nodes and runs on a schedule (every 4 hours). Along the way it connects OpenRouter Chat Model, HTTP Request and Gmail. It also calls api.exchangerate-api.com and api.tavily.com over HTTP.
How it runs
Trigger: On a schedule (every 4 hours).
- Set (Fields) — Configure me (Edit Fields (Set)): sets or maps fields
- Fetch USD/JPY rate (HTTP) (HTTP Request): calls api.exchangerate-api.com
- Analyze USD/JPY (AI agent) (AI Agent): runs an AI agent, with model: LLM provider (configure); 1 tool (Tool: Search Forex News (Tavily)); output parser: Tool: Structured Output Parser
- Send results via Gmail (Gmail): uses Gmail
Services it uses
HTTP calls to: api.exchangerate-api.com, api.tavily.com
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- HTTP Request Tool (legacy) in Tool: Search Forex News (Tavily): replace with HTTP Request node connected to the AI Agent's Tool input.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| HTTP Request Tool (legacy) Tool: Search Forex News (Tavily) | HTTP Request node connected to the AI Agent's Tool input |
Nodes used (8)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - HTTP Request Tool
@n8n/n8n-nodes-langchain.toolHttpRequest - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Gmail
n8n-nodes-base.gmail - Edit Fields (Set)
n8n-nodes-base.set - HTTP Request
n8n-nodes-base.httpRequest
From the author
Who’s it for Traders, operations teams, and finance-minded founders who want a low-maintenance USD/JPY monitor that blends live pricing with short, news-aware AI commentary—delivered straight to email on a reliable cadence. How it works / What it does On a…