OpenAI Introduces Apps in ChatGPT with New SDK

Oct 6, 2025
OpenAI has launched a new feature allowing developers to build apps directly within ChatGPT, using the newly introduced Apps SDK. This initiative aims to enhance user interaction by integrating services like Spotify and Zillow into ChatGPT conversations.

OpenAI has launched a new feature that allows developers to build applications directly within ChatGPT, as announced on their website. This new capability is facilitated by the Apps SDK, which is now available in preview for developers.

The integration allows users to access interactive applications from various companies such as Booking.com, Expedia, Spotify, Figma, Coursera, Zillow, and Canva directly within ChatGPT. Users can call up these apps by name during their conversations, enhancing the interactivity and personalization of their ChatGPT experience.

The Apps SDK is built on the Model Context Protocol (MCP), enabling developers to connect their data sources to AI systems. This open standard allows for the creation of apps that can render interactive interfaces within ChatGPT's responses. OpenAI plans to expand the availability of these apps and introduce monetization options in the future.

Currently, the apps are available to all logged-in ChatGPT users outside of the EU, with plans to extend access to EU users soon. OpenAI emphasizes the importance of privacy, requiring developers to collect only the minimum necessary data and to be transparent about permissions.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.