build log
n8n AI Agent Series
The process, not just the result. by Umaima Tariq · 2 updates
- #1 · 26 Aug 2026
Level 1 AI Agent in n8n (Gemini + Tools + Memory)
Just built a custom Level 1 AI Agent using n8n! 🚀 Here is what's running under the hood: - LLM Model: Google Gemini Chat Model - Memory: Window Buffer Memory for conversation context - Tools: Custom HTTP Request tool fetching live web data (Wikipedia API) & Calculator tool In this demo, the agent autonomously decides to call the HTTP tool to fetch live information about Tesla and formats the output smoothly. Feedback and suggestions for Level 2 features are welcome!Open update - #2 · 28 Aug 2026
Level 2 Orchestrator + Sub-Agent System in n8n
Upgraded my n8n multi-agent setup to Level 2! 🚀 This architecture features a central Orchestrator Agent that delegates complex requests to specialized Sub-Agents: Orchestrator Agent: Parses user prompt and breaks down tasks. Research Agent: Handles deep-dive research with Google Gemini & web tools. Writer Agent: Synthesizes research into structured, final reports. In this demo, a prompt requesting a detailed report on AI in healthcare gets routed, researched, and formatted autonomously. Next up: Level 3!Open update