🚀 AI Chat Agent for Automated Google Calendar Scheduling (n8n) 🚀 🚀 Project Summary Built a multilingual, conversational AI Scheduling Agent in n8n that autonomously manages calendar appointments. The agent processes natural language chat messages, references historical context using a memory node, and directly creates, retrieves, or cancels events in Google Calendar based on user intent. 🔥 🔥 The Outcome & Business Value Zero-Touch Appointment Booking: Completely automated the client scheduling funnel, handling bookings, lookups, and cancellations without human administrative overhead. Context-Aware Conversations: Integrated persistent memory so the AI agent remembers past interactions within the chat session for a smooth, human-like user experience. Rapid Multi-Intent Execution: Routes complex user requests (e.g., "cancel my appointment") to the correct backend function, executing the entire database update in under 2.5 seconds. 🔥 🔥 How It Works User Trigger: Initiated instantly when a text or chat message is received from a client. AI Cognitive Layer: An AI Agent node orchestrates the workflow, leveraging an OpenAI Chat Model for reasoning and a Simple Memory block to track conversation history. Dynamic Tool Routing: The agent analyzes the user's intent and dynamically selects the correct operational tool to execute live changes: agendar_cita (Create Google Calendar Event) obtener_citas (Get/Find Google Calendar Event) cancelar_cita (Delete/Cancel Google Calendar Event)

0

17

Cover image for 🚀 Automated AI Document Processing

🚀 Automated AI Document Processing & ATS Pipeline (n8n) Project Summary Replaced a manual candidate screening process with a fully automated, n8n-orchestrated backend pipeline. The system automatically intercepts incoming applications, uses OpenAI to analyze documents, updates databases, and triggers client communication—cutting manual data entry down to zero. The Outcome & Business Value Eliminated Manual Data Entry: Automated 100% of resume parsing, document conversions (Docs to PDF), and data extraction tasks. Instant Candidate Screening: Integrated an OpenAI Chat Model Decider to evaluate incoming resumes against job descriptions in real-time with zero human delay. Automated Sync & Follow-Ups: Automated instant logging to Google Sheets and launched immediate multi-path email responses based on candidate status. How It Works (System Architecture) Phase 1 (Ingestion & Extraction): Captures files via webhooks/emails ➡️ Cleans data via custom code nodes ➡️ Parallel-processes files to extract raw text ➡️ Uses AI structured parsing to match applicants to open roles. Phase 2 (Database & Delivery): Routes structured applicant data ➡️ Upserts matching rows into a centralized tracking database ➡️ Triggers dynamic conditional emails back to candidates.

1

47

Cover image for 🚀 Telegram Content Bot +

🚀 Telegram Content Bot + Image Pipeline for Swedish Hunting Brand Built a fully automated content system for Huntway, a premium Swedish hunting and outdoor lifestyle brand, replacing a manual content creation process with an intelligent daily workflow powered by Make.com (http://Make.com), Claude AI and Telegram. 🔥 The Problem The client had a growing archive of over 4,500 professional hunting images with no structured way to use them for daily content. Every Instagram, Pinterest and editorial post required manually browsing the archive, selecting an image, writing a caption and posting — a process that was eating significant time each week. 🧠 What Was Built A complete end-to-end content automation system with three connected parts: The first part is an image analysis pipeline that automatically analyses every new photo added to Dropbox using Claude AI. Each image is tagged across 34 fields including season, weather, mood, clothing colours, subject, weapon visibility, Pinterest safety and dog detection — all stored in a structured Airtable database of 4,521 images. The second part is a daily content bot running on Telegram. The client types "suggest" and the bot checks today's actual weather and season in Sweden, filters the image library and sends two relevant suggestions — one featuring a man and one featuring a woman or group. The client picks one, selects the content format (Instagram, Pinterest or Editorial) and receives a caption generated by Claude AI in the correct voice, language and length for that platform. The third part is an intelligent suggestion engine that tracks which images have been shown each day to avoid repetition, filters out weapon-containing images automatically when Pinterest is selected, and groups similar weather conditions to ensure suggestions are always available regardless of the specific conditions outside. 🔥 The Impact What previously took manual browsing and writing time now takes under a minute. The client has a searchable library of 4,500+ tagged images, daily content suggestions matched to real Swedish weather and season, and platform-specific captions generated on demand — all from a simple Telegram message. 🚀 Stack Make.com (http://Make.com) — Telegram — Claude AI (Anthropic) — Airtable — Dropbox — OpenWeatherMap API

1

42

Make.com (https://Make.com) workflow for booking appointments

0

56

Emmanuel Akinfesola

Web Designer, Webflow Developer, Low-Code/No-Code