Artificial Intelligence tools and workflows
### 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 its interaction 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 the context of the human-to-user conversation and is set to provide after-sales assistance. A 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. For this, we can use Redis as a simple key-value store. * When no state is set, the user is directed through an onboarding step to attain their details. Once complete, the agent will transfer the user to a human agent - technically, all this involves is an update to the session state and a message to another chat forwarding the user's details. * During this human state, the agent cannot reply to the user and must wait until the human transfers the conversation back. The human can do this by replying to the human-in-the-loop message with a summary of their conversation with the user. This session state now changes to bot and the context is implanted in the agent's memory so that the agent can respond to future questions. * At this stage of the conversation, the agent is now expected to handle and help the user with after-sales questions. The user can at any time request transfer back to the human agent, repeating the previous steps as necessary. ### How to use * Plan your user journey! Here is a very basic example of a sales inquiry with at most 3 states. More thought should be developed when many more states are involved. * You may want to better log and manage session states so no user is left in limbo. Try connecting the user and sessions to your CRM. * Note, the Onboarding agent and After-Sales agent have separate chat memories. When adding more agents, it is recommended to continue having separate chat memories to help focus between states. ### Requirements * Telegram for chatbot & interface * Redis for session store and chat memory * OpenAI for AI agent ### Customizing this workflow * Not using Telegram? This template works with WhatsApp and other services with equivalent functionality.
This workflow enables seamless interaction with internal documents using a chat interface powered by Ollama. It leverages Supabase for vector storage and Google Drive for document ingestion, facilitating real-time updates and context-aware responses.
This n8n workflow streamlines the process of scraping web articles and saving them to a Notion database using Google Gemini AI and Browserless. It automates the organization of web content, reducing manual effort and enhancing productivity.
Streamline the creation of daily security briefings by automating the transformation of Wazuh alerts into executive summaries using AI. This workflow reduces manual reporting time and bridges the gap between technical data and business insights.
This workflow automates the process of scraping book data from a website, extracting key information, and populating it into a Google Sheets spreadsheet. It leverages Jina for web scraping, OpenAI for data extraction, and n8n for workflow automation.
Streamline the integration of MCP with Airtable using n8n to automate updates and changes, ensuring your AI Agents are always in sync with your data.
Efficiently parse and analyze research papers using PDF Vector and GPT-4, storing insights in a database for easy access and reference.
This workflow automates the process of generating content for multiple social media platforms by monitoring YouTube channels, extracting transcripts using AI, and creating tailored posts for LinkedIn, Twitter, Threads, and Instagram.
This n8n workflow automates the process of extracting and analyzing YouTube video details and transcripts using AI. It allows users to interact with an AI agent for insightful video content analysis and summarization.
This workflow is designed to streamline the process of creating, managing, and automating events in Google Calendar using the MCP server. By utilizing this automation, users can efficiently manage their calendars, ensuring events are created, upda...
Streamline your graphic design process by automating AI image generation and review using Ideogram and OpenAI. This workflow ensures high-quality images are efficiently vetted and organized.
Transform user text inputs into high-quality AI-generated images using a Telegram bot integrated with Google's Gemini 2.0 Flash. This workflow enhances prompts for artistic detail and delivers images directly to Telegram.
Leverage AI to interact with documents in multiple formats, including PDFs, Word, Excel, and text files. This workflow uses Retrieval-Augmented Generation (RAG) to provide accurate and context-aware responses to user queries.
This workflow automates the ingestion of documents from Google Drive, vectorizes them using OpenAI embeddings, stores them in Pinecone, and facilitates chat-based retrieval through LangChain agents.
Streamline the creation of short videos using AI for scriptwriting, image generation, and avatar customization. This workflow automates video production for social media and marketing, saving time and ensuring consistent quality.
Convert text descriptions into cinematic videos using Google Veo3 via Leonardo.ai, enhanced by Claude 4's prompt engineering. Automate video creation and storage in Google Drive.
Transform natural language queries into valid BigQuery SQL and execute them to retrieve live results, streamlining data access for non-technical users.
Streamline your workflow by automating the delivery of AI-generated data summaries directly to Slack. This n8n workflow leverages a Super Assistant to compile and send recurring digests from your connected data sources.
Seamlessly generate AI-powered videos using HeyGen's avatars and voice cloning capabilities directly within n8n. Ideal for content creators and marketers looking to automate personalized video messages.
This n8n workflow automates the creation and publishing of LinkedIn posts using AI-generated content ideas and feedback loops to ensure brand consistency. Ideal for marketers and creators aiming to maintain a strong LinkedIn presence without manual effort.
This n8n workflow automates code reviews for GitHub pull requests using OpenAI's language models and coding best practices stored in Google Sheets. It streamlines the review process by generating AI-powered comments and labeling reviewed pull requests.
Transform your WhatsApp into an AI-powered image generator. Send a text message with your idea, and this workflow will create a detailed prompt using Gemini 2.5 Pro, generate an image with Gemini 2.0 Flash, and send it back to your chat.
This workflow leverages AI to generate SQL queries using only the database schema, enhancing security by avoiding direct data access.
This workflow sets up a Retrieval-Augmented Generation (RAG) pipeline using n8n, enabling dynamic interaction with a vector store to provide context-aware responses.
Our automation experts build tailored workflows for your exact stack and process.