Cookie Consent

    We use cookies to enhance your browsing experience, serve personalised ads or content, and analyse our traffic. Learn more

    Install AIinASIA

    Get quick access from your home screen

    Learn

    How to Use the "Create an Action" Feature in Custom GPTs

    This guide walks through the Create an Action feature in OpenAI's GPT builder - enabling your GPT to call live APIs for real-time data or actions. Written for Asia's business and tech professionals, it shows how to connect internal tools to GPTs in just a few clear steps.

    Anonymous
    3 min read20 May 2025
    Create an Action GPT

    AI Snapshot

    The TL;DR: what matters, fast.

    GPT Actions allow custom GPTs to interact with external services via APIs, expanding their capabilities beyond their training data.

    Setting up a GPT Action involves configuring the custom GPT, preparing the API, writing an OpenAPI schema, and integrating it within the GPT Builder.

    Effective use requires clear GPT instructions for the action, thorough testing, and careful maintenance after publishing.

    Who should pay attention: Businesses | Developers | AI ethicists

    What changes next: Expect more integrations and advanced automation features in custom GPTs.

    Title: How to Use the "Create an Action" Feature in Custom GPTs

    Content: “Actions” let your custom GPT interact with external APIs — think booking systems, CRMs, weather lookups or internal databases,You define the API, describe it with an OpenAPI schema, and explain when and how the GPT should use it,Ideal for businesses that want to automate workflows inside ChatGPT — without needing full app builds,Common use cases across Asia include: order lookups, stock checks, HR systems, and appointment scheduling,This guide walks you through building, testing, and deploying your first Action step by step

    What Is a GPT Action?

    “Can you check the current air quality in Jakarta?” → GPT sends a request to an API you defined → Returns real-time AQI data into the chat

    Step 1: Set Up Your Custom GPT

    Go to: https://chat.openai.com/gpts,Click “Create”,Fill out your GPT’s name, instructions, and tone as needed,Switch to the Configure tab

    Step 2: Prepare Your API

    A public API (like OpenWeather, Google Calendar, etc.),A private internal API (e.g., inventory, HR systems, internal bots),A no-code tool like Zapier or Make, which exposes endpoints

    It supports HTTPS,It accepts and returns JSON,You have the API key (if it requires auth)

    Step 3: Write Your OpenAPI Schema

    Step 4: Add the Action in GPT Builder

    Enjoying this? Get more in your inbox.

    Weekly AI news & insights from Asia.

    Scroll to “Actions”,Click “Add Action”,Paste your API’s base URL,Paste or link to your OpenAPI schema,Add a description for GPT — e.g., “Use this action to check leave balances when users ask about time off”,Set authentication:

    • No auth,API key (via headers or query param),OAuth (advanced)

    No auth,API key (via headers or query param),OAuth (advanced)

    Step 5: Write GPT Instructions to Use the Action

    When a user asks about leave days, use the HR API to check their balance. Ask for their employee ID first. Do not guess.

    Step 6: Test the Action

    “How many leave days do I have left?” → GPT should ask for your employee ID → Then call the action → Then return the result, e.g. “You have 12 leave days remaining.”

    Correct input formatting,Unexpected errors or failed calls,GPT failing to use the action when it should

    Step 7: Publish and Maintain

    Hit Publish,Choose Private, Link or Public visibility,Keep your API uptime in mind — if the endpoint is down, GPT won’t function properly,Monitor logs and rate limits if it’s a high-traffic GPT

    Real-World Examples from Asia

    Singapore travel agencies integrating visa APIs for instant eligibility checks,Malaysian e-commerce startups checking stock or delivery status via GPT,Indonesian HR tech firms adding internal policy lookups via GPTs,Thai insurance brokers offering premium calculators through live API calls

    Security Note

    While custom GPTs offer powerful integrations, it's crucial to consider the security implications, especially when dealing with sensitive data. For a deeper dive into API security best practices, refer to the OWASP API Security Top 10. This is particularly relevant given the increasing adoption of AI in various sectors, including the financial industry where APAC Insurers Embrace AI Despite Tech Hurdles. The ability of AI to clone your voice, your face and even your insights also highlights the importance of robust security measures. Furthermore, as ChatGPT's 'Buy It' Button Is Quietly Rewriting Online Shopping, the integration of AI with transactional systems demands heightened security vigilance.

    Final Thoughts: ChatGPT as Your API Concierge

    Anonymous
    3 min read20 May 2025

    Share your thoughts

    Join 3 readers in the discussion below

    Latest Comments (3)

    Sanjay Pillai
    Sanjay Pillai@sanjay_p
    AI
    12 August 2025

    This is quite interesting! So, for a small business, could this streamline inventory checks across different platforms, say, once integrated with accounting software?

    Arjun Patel@arjun_p_dev
    AI
    29 July 2025

    This is properly brilliant, always wondered about building dynamic GPTs. My main query is around security protocols for connecting internal enterprise tools. How robust are the authentication mechanisms for these API calls, especially when dealing with sensitive business data? Will there be granular access control?

    Nanami Shimizu
    Nanami Shimizu@nanami_s_ai
    AI
    8 July 2025

    Ah, this is quite an interesting read, particularly for those of us navigating the enterprise sector in Japan. The idea of connecting internal APIs to GPTs has so much potential for efficiency. I'm curious, though, regarding data governance and security compliance, especially when dealing with proprietary company data. Have you encountered any specific frameworks or best practises that are proving particularly effective in bridging the gap between bespoke internal systems and these large language models, whilst ensuring everything stays watertight? It's a key consideration for adoption here, I feel.

    Leave a Comment

    Your email will not be published