Editorial illustration for ChatGPT's New UI Lets Users Build Custom Tools Like a Plane Seat Explorer
ChatGPT's New UI Builds Custom Tools on the Fly
ChatGPT's New UI Lets Users Build Custom Tools Like a Plane Seat Explorer
OpenAI rolled out a new ChatGPT interface on Wednesday called "Intelligent UI," which swaps the usual text-and-link response for custom visual tools built on the fly. The update runs on GPT-6, OpenAI's latest model, which started reaching paying subscribers the same day and arrives for free users Thursday.
Wired got early access to the interface before launch. Ask for a diagram of a slug, and ChatGPT builds an interactive anatomy chart with clickable labels for parts like the tentacles and foot. Ask about rent in San Francisco, and it generates a calculator with sliders for income and expenses, showing what a given apartment would actually cost against take-home pay.
The most useful example involved travel. Trying to avoid an exit row on an upcoming flight, a reporter asked ChatGPT to compare cabin layouts across four Alaska and Delta planes. It returned a tappable seat map, exit rows flagged in green, each seat clickable for more detail.
Not every answer gets this treatment. OpenAI says the model decides when a visual tool actually helps, rather than defaulting to graphics for every query.
Chatbot experiences have increasingly become multimodal, meaning that text, images, and voice blend into one user experience. OpenAI's launch of an updated ChatGPT that's easier on the eyes and more interactive for over a billion users signals that the multimodal era is here.
Why this matters
OpenAI building generative UI directly into ChatGPT changes the calculus for anyone making chatbot wrapper apps or custom internal tools. If GPT-6 can spin up a working seat-comparison widget on the fly, the market for bespoke "ask our AI about X" interfaces that developers have been charging for just got smaller overnight. For founders, the lesson is that any product whose main value is "we put a nice UI on top of an LLM answer" needs a harder moat, because OpenAI is now shipping that layer natively, to paid users today and free users tomorrow.
Researchers should watch how OpenAI decides when to render a tool versus text, since that judgment call is itself a hard problem and the failure modes (irrelevant widgets, broken layouts, wasted compute) aren't addressed yet. Worth tracking: how often this "intelligent" UI picks the right format versus defaulting to walls of text anyway, and whether this pattern of model-generated interfaces shows up in competitors like Gemini or Claude before the year is out.
Related Reading
Browse all OpenAI news →
LLMs & Generative AI ChatGPT's 'Nerdy' tweak rewards goblin metaphors in answers, study finds
LLMs & Generative AI Google to End Free Access to Gemini AI for Non-Subscribers
LLMs & Generative AI AI Engineers Face Rising Costs, Need New Strategies for Efficiency
Related Topic OpenAI's GPT Transcribe Cuts Error Rate to 3.31%, Improving on GPT-4o
Open Source
Related Topic OpenAI Developer: AI Agent "Swarms" Waste Tokens, Create "Coordination Tax
AI Tools & Apps
From Archives Liquid AI's New d1-3B Model Processes Images in 35 ms for Edge Inspection
From Archives Anthropic's Claude Haiku 5.5 model arrives with drastic price cuts
From Archives OpenAI Launches Decisions API for GPT-6-Luna
Business & Startups
From Archives OpenAI’s Alexander Embiricos to Speak at TechCrunch Disrupt 2026
Business & Startups
Common Questions Answered
What is the new Intelligent UI feature in ChatGPT and how does it differ from the previous interface?
OpenAI's new Intelligent UI replaces the traditional text-and-link response format with custom visual tools that are built on the fly by the AI. Instead of just providing text answers, ChatGPT can now generate interactive diagrams and widgets, such as an anatomy chart for a slug with clickable labels, making responses more visual and interactive for users.
Which OpenAI model powers the new Intelligent UI and when did it become available?
The new Intelligent UI runs on GPT-6, OpenAI's latest model, which started reaching paying subscribers on the day of the interface launch and became available to free users the following day. This represents a significant upgrade in ChatGPT's capabilities compared to previous versions.
What does the multimodal era mean for ChatGPT users according to this update?
The multimodal era means that text, images, and voice now blend seamlessly into one unified user experience within ChatGPT. OpenAI's launch of the Intelligent UI to over a billion users signals that this shift toward more interactive and visually rich chatbot experiences is now mainstream.
How does the Intelligent UI impact the market for custom chatbot wrapper applications and internal tools?
The ability of GPT-6 to generate working widgets and custom interfaces on the fly significantly reduces the market opportunity for developers who have been charging for bespoke "ask our AI about X" wrapper applications. Founders of such products now face increased competition from OpenAI's built-in generative UI capabilities and need to develop stronger competitive advantages beyond simply adding a nice interface to LLM responses.
Further Reading
- ChatGPT is getting a lot more visual, with the launch of a new interface - TechCrunch
- The New ChatGPT Is More Show Than Tell - WIRED
- GPT-6 for All: Your ChatGPT Answers Are Getting a Very Visual Makeover - CNET
- OpenAI Brings GPT-6 With Intelligent UI to All ChatGPT Tiers - Unite.AI
- OpenAI's GPT-6 Turns ChatGPT Replies Into Interactive Apps for 1.2B Users - AlphaSignal
