OpenAI released ChatGPT Plugins in March 2023 to a limited preview. By May, hundreds of plugins were available. The concept: give ChatGPT tools that let it access real-time data, execute code, and interact with external services.
The plugin architecture
ChatGPT plugins use OpenAPI specifications. You define an API, describe it in a manifest file that tells ChatGPT what the API does and how to call it, and ChatGPT learns to use your API within conversation. When a user's question is best answered by calling your API, ChatGPT does so and incorporates the result into its response. The architecture is simple: REST APIs with semantic descriptions.
The killer plugin use case
The most immediately impactful plugins were code execution (the built-in Code Interpreter, later Advanced Data Analysis) and web browsing. Code Interpreter let ChatGPT run Python code to do data analysis, create charts, and process uploaded files. Web browsing let ChatGPT retrieve current information beyond its training cutoff. These two plugins, both built by OpenAI, addressed the two biggest limitations of the base model.
Third-party plugin reality
Third-party plugins had uneven adoption. Expedia, Kayak, and OpenTable plugins for travel and restaurant booking were intuitive use cases. But the general pattern of reaching for a ChatGPT plugin to do something that a direct website visit would do faster was not compelling for most users. The plugin ecosystem peaked in enthusiasm in early 2023 and then settled into a smaller set of genuinely useful integrations.
The transition to GPTs
OpenAI deprecated the ChatGPT plugin system in favour of GPTs (custom ChatGPT agents) in November 2023. GPTs incorporate the concept of knowledge files and actions (the renamed plugin system) into a more coherent product. The evolution from plugins to GPTs reflected what OpenAI learned about how users wanted to interact with customised AI capabilities.