Custom GPTs & AI Automation is a course in building specialised AI assistants with GPT Builder, using instructions, knowledge files and GPT Actions, then automating workflows with n8n, Make and Zapier. It suits regular ChatGPT users, IT and operations teams and team leads, and you leave with a Custom GPT and an automated workflow built around your own tasks.
Many organizations already use ChatGPT fluently in daily work but remain stuck typing the same prompts every day, copying and pasting data between systems, and getting inconsistent output whenever a different person uses it. The next step that makes a real difference is not using AI more skillfully but stopping the repeated prompting altogether, by wrapping the organization's knowledge and workflows into ready-to-use specialized AI assistants and setting up systems so AI works on its own from start to finish. This course guides learners to build Custom GPTs, AI assistants that carry the organization's persona, knowledge and rules, from writing instructions and uploading knowledge to connecting GPT Actions that call real
external systems. It then steps up to AI automation with platforms like n8n, Make and Zapier, connecting data from many systems (Google Workspace, Gmail, LINE, databases and MCP connectors) and building workflows where AI processes every step, running on schedule or on events without anyone clicking. All content is taught through workshops on real tasks, focusing on choosing worthwhile automation, managing security, cost and PDPA, and finishes with a capstone project where learners assemble a Custom GPT into an automation workflow as their own end-to-end automated system. (2 days, 6 hours per day, 12 hours in total, Intermediate to Advanced level, prior ChatGPT or generative-AI use recommended, no programming required.)
Course Details
A 2-day course, 6 hours per day (12 hours in total), delivered as a hands-on workshop with a capstone project. Intermediate to Advanced level. Learners take home their own Custom GPT, automation workflow templates, and a security, cost and PDPA checklist.
Section 1: Overview of Custom GPTs and AI Assistants in the Organization
Section 2: Building Your First Custom GPT with GPT Builder
Section 3: Instructions and Knowledge for Accurate, Consistent Answers
Section 4: GPT Actions Connecting the Custom GPT to External Systems
Section 5: Testing, Publishing and Standardizing GPT Usage
Section 6: AI Workflow Automation Concepts and Choosing Worthwhile Tasks
Section 7: Automation Platforms - n8n, Make and Zapier
Section 8: Building Your First Workflow with AI in the Steps
Section 9: Connecting Real Data with Connectors and MCP
Section 10: Multi-step Automation and Orchestration
Section 11: Security, Cost, PDPA and Capstone Project
No public rounds are open right now. Join the waiting list and we will contact you first when the next round opens, or ask us on LINE. Or call 02-570-8449 or 088-807-9770
Open GPT Builder and choose whether to build through conversation (Create) or set it up yourself (Configure). Give it a name and description, write instructions covering role, scope, workflow and answer format, upload documents as knowledge, enable the capabilities you need, such as web search or Code Interpreter, and add conversation starters. Test it in Preview, refine until the answers are consistent, then share it with your team.
GPT Actions connect a Custom GPT to external APIs: you describe the endpoints with an OpenAPI schema and configure authentication such as an API key or OAuth. When a user asks something, the GPT decides which API to call, for example to check an order status, look up a customer or record an entry, so it works with live data rather than general knowledge alone. Grant only the access needed and require confirmation before important actions.
Zapier is the easiest to use, with a very large catalogue of ready-made app connections, and suits simple workflows of a few steps. Make shows workflows visually and handles conditions, loops and complex data in more detail. n8n is a highly flexible node-based tool that accepts custom code and can be self-hosted on your own servers, which helps when data must stay in-house. Choose by task complexity, team skills and data policy.
It suits regular ChatGPT users who want to stop repeating the same prompts, IT, operations and digital teams setting up automation, team leads and project managers looking to cut repetitive work, and marketing, sales, HR or customer service teams with heavy routines. You should have used ChatGPT and understand your own workflow. Programming is not required, though reading JSON or having called an API helps with GPT Actions and webhooks.
You will be able to build a Custom GPT with GPT Builder, write instructions that give consistent answers, add knowledge so it answers from your organisation's own information, connect GPT Actions to external APIs, share it with agreed team standards, and build AI-powered automated workflows in n8n, Make or Zapier while managing security, API costs and PDPA. Participants who complete the training receive a Certificate of Completion with its own number, which can be verified online.
Yes. It can be run in-house for your team, with examples adapted to your own work, such as building Custom GPTs from your organisation's actual manuals and policies and designing automated workflows from each department's routine tasks. You can request a quotation from this page, or contact us on LINE @itgenius or by phone on 02-570-8449.
AI tools are now part of everyday work: chat assistants such as ChatGPT, Gemini, Claude and Microsoft Copilot, research tools such as NotebookLM, and AI that creates images, slides, video and audio. Yet many people still use AI only for general questions, get…
Many organizations have already invested in AI tool licenses for their staff, only to find that actual usage is low. Most employees use AI only for general question-and-answer and never connect it to their daily work, so the return does not justify the…
As AI moves from a question-answering chatbot to an AI agent that actually does the work, Claude is one of the standout tools right now - especially for working with long documents, deep reasoning, and the new Cowork Mode that lets Claude access folders on…
