This n8n template demonstrates an approach to perform bot-to-human handoff using Human-in-the-loop functionality as a switch. In this experiment, we play with the idea of states we want our agent to be in which controls it's interacton with the user. First state** - the agent is onboarding the user by collecting their details for a sales inquiry. After which, they are handed-off / transferred to a human to continue the call. Second state** - the agent is essentially "deactivated" as further messages to the bot will not reach it. Instead, a canned response is given to the user. The human agent must "reactivate" the bot by completing the human-in-the-loop form and give a summary of their conversation with the user. Third state** - the agent is "reactivated" with context of the human-to-user conversation and is set to provide after sales assistance. An tool is made available to the agent to again delegate back to the human agent when requested. How it works This template uses telegram to handle the interaction between the user and the agent. Each user message is checked for a session state to ensure it is guided to the right stage of the conversation.
Tags
Call n8n Workflow Tool
Chat Memory ManagerCCode
Information Extractor
OpenAI Chat ModelRelated workflows
See all AI Automation→
AI: Summarize podcast episode and enhance using Wikipedia
The workflow automates the process of creating a summarized and enriched podcast digest, which is then sent via email. Note that to use this template, you need to be on n8n version 1.19.4 or later.
Turn support emails into FAQ drafts with Gmail, OpenAI, Sheets and Docs
Quick overview This workflow monitors a Gmail inbox for new support-style emails, uses OpenAI to extract a reusable FAQ question and safe draft answer, logs results to Google Sheets, and then creates a Google Docs draft and/or Gmail review drafts for a human reviewer. How it works Polls Gmail every 5 minutes for unread emails matching the configured support-related search query. Cleans the email content by stripping quoted replies, signatures, and HTML to produce a concise plain-text body. Sends the cleaned email and product context to OpenAI to extract a structured FAQ candidate (question, draft answer, category, score, sensitivity flag, tags, and recommended action). Calculates a routing status based on the FAQ score threshold and sensitivity/recommended action, and prepares draft text for a Google Doc and reviewer email. Appends every processed email and extracted fields to a Google Sheets tab for tracking and reporting. If the candidate is strong, creates a Google Docs FAQ draft, inserts the draft content, and creates a Gmail draft notification to the reviewer with the document link. If the candidate needs manual handling, creates a Gmail draft to the reviewer with the review n
Suggest meeting slots using AI
The purpose of this n8n workflow is to automate the process of identifying incoming Gmail emails that are requesting an appointment, evaluating their content, checking calendar availability, and then composing and sending a response email. Note that to use this template, you need to be on n8n version 1.19.4 or later.