Can AI Review Your Design Better Than a Designer? We Tested Zeplin’s AI Design Review

Will your users still click on your navigation menu — or just ask their browser to handle it? With the October 2025 launch of ChatGPT Atlas, OpenAI introduces a fundamentally new way of using the web. And if users are changing how they interact with digital products, your product needs to evolve too.

ChatGPT Atlas isn’t just another sleek web browser. It’s a paradigm shift — a browser designed around conversation and intelligent delegation. And that means user experience (UX) teams need to rethink how interfaces are built and evaluated.

What Is ChatGPT Atlas?

Atlas is OpenAI’s new desktop browser experience, currently available to ChatGPT Plus, Team, and Enterprise users.

Its core features include:

• AI-first interface – Instead of searching, clicking, and scrolling, users can simply ask Atlas to find, explain, summarize, or act.
• Direct page interaction – Atlas can analyze, summarize, and even interact with websites by filling out forms, navigating UI elements, or extracting relevant content.
• App integrations – Users can connect tools like Notion, Google Drive, or Outlook for deeper context.
• Context-aware personalization – Atlas remembers user preferences and activity for more relevant, personalized responses over time.

This shifts the browser’s role from passive window to active assistant — which has significant implications for UX teams.

What Does This Mean for UX Design?

In a traditional UX model, users click through interfaces. In Atlas, users delegate tasks to AI. This changes how interfaces are perceived, used, and valued.

Key shifts for product and UX teams include:

• Interfaces become optional – Atlas might bypass much of the interface entirely. If users can ask, “Find me the best offer,” Atlas may never show your landing page, unless it’s structured to surface through AI.
• AI becomes a secondary user – Designers must now consider two audiences: the human and the AI acting on their behalf. Interfaces must be machine-readable, semantically structured, and contextually understandable.
• New behavior patterns – Instead of browsing, users issue commands. “Book my usual train” or “Submit that leave request for next Friday” are now common behaviors.

This is a UX environment where visibility, context, and actionability for AI become just as crucial as for humans.

How Can Product Teams Prepare for Atlas and AI-first Browsing?

Here are four high-impact areas where digital teams can take action:

1. Audit for AI-readiness
   Ensure that your content and UI elements (e.g., CTAs, form fields, product specs) are clear, well-structured, and easy for AI models to parse and understand.
2. Test with AI agents
   Incorporate usability testing that includes AI agents like GPT-4.5 to perform key user tasks. This helps identify areas where AI may fail to interpret or interact with your product.
3. Redefine success metrics
   Metrics like click-through rate or bounce rate may lose meaning when AI bypasses traditional navigation. New KPIs such as AI task completion or prompt-to-action success rates are emerging.
4. Explore new business opportunities
   By designing for both humans and AI, you open doors to accessibility, automation, and AI-augmented workflows that differentiate your product in the marketplace.

Final Thoughts

ChatGPT Atlas isn’t a vision of the future — it’s here. And it changes the rules for how users engage with digital experiences. To remain competitive, product teams must begin designing for AI-enhanced behavior now.

UX GIRL’s Recommendation:

If your product needs to stay visible, understandable, and actionable in an AI-first browsing world, it’s time to adapt.

At UX GIRL, we support teams with:

• AI-readiness UX audits
• Agent-based usability testing
• Strategic workshops on hybrid (human + AI) experience design

Let’s future-proof your product — together.

‍

In the high-speed world of Agile, where user expectations evolve faster than sprint cycles, clear communication is not just a nice-to-have — it’s critical. Yet even in well-functioning teams, UX designers and developers often struggle to stay perfectly aligned. The result? Beautifully crafted prototypes that don’t quite behave as intended once implemented, or ambiguous flows that leave testers guessing.

Enter Gherkin — a simple, structured language that can help bridge the gap between design, development, and product.

What is Gherkin (and why should UX designers care)?

Gherkin is a structured, plain-language format used to write behavior-driven development (BDD) scenarios, typically used by QA and dev teams to write automated tests. But its value goes far beyond testing.

Its real strength lies in its simplicity — it describes user behavior in a "Given–When–Then" format, making it the perfect candidate for aligning cross-functional teams around how a feature should behave.

Example:

This isn’t code — it’s user intent, written in plain English. And that makes it a powerful communication tool for designers.

How UX Designers Can Use Gherkin to Document Intent

Designers don’t need to become developers to leverage Gherkin. Instead, they can use it to clearly define interaction logic — supplementing wireframes, prototypes, and user flows with behavior-driven context.

By embedding Gherkin-style scenarios into design documentation or user stories, designers ensure that the team understands not just what the interface looks like, but how it should behave.

Here’s a UX-specific example:

This format reduces ambiguity and ensures that design intentions translate into correct implementations.

What’s in it for your team (and your bottom line)?

Introducing Gherkin into the UX process may feel like an extra step, but it pays off. Studies show that reducing ambiguity in handoffs and requirements can lead to major efficiency gains.

• Fewer misunderstandings: A McKinsey report found that companies improving requirement clarity saw up to a 40% increase in team productivity (Source: McKinsey & Company).
  
  
• Faster onboarding: Gherkin scenarios give new team members immediate context for how the product should behave.
  
  
• Better alignment with business goals: Stakeholders can validate behavioral flows early — even before development starts.
  
  
• Improved testability: QA teams can use Gherkin to write automated or manual tests directly aligned with design.
  
  

Gherkin becomes a shared language between design, product, dev, and QA — cutting down feedback loops and minimizing rework.

How to Start Using Gherkin in Your Design Process

You don’t need to overhaul your workflow overnight. Start small:

1. Pick one key user flow — such as login, checkout, or onboarding.
   
   
2. Write 1–3 scenarios in Given–When–Then format.
   
   
3. Share them during refinement or planning with developers and testers.
   
   
4. Attach the scenarios to your design files or link them in your backlog.
   
   

This lightweight addition can dramatically improve alignment — even in teams that already communicate well.

Design Is Behavior — Not Just Visuals

UX is about more than how things look — it's about how they work. While wireframes and prototypes show structure and visuals, they often leave room for interpretation when it comes to logic, rules, and edge cases.

Gherkin helps designers express interaction logic in a way that’s unambiguous and testable. And in an Agile team, that means fewer assumptions, faster delivery, and better user outcomes.

At UX GIRL, we encourage product teams to experiment with Gherkin as a way to reduce misalignment and build stronger bridges between design and development. You don’t need to be technical — you just need to care about clarity.

What’s Next?

Ready to give your design handoffs a boost? Start with a single Gherkin scenario for your next feature. Use it to open a conversation between design, dev, and QA. You might be surprised how quickly your team aligns when you’re finally speaking the same language.

Need help integrating UX practices like Gherkin into your Agile process? Reach out to UX GIRL — we help teams turn design decisions into product clarity.

‍

Conversational AI has changed the rules of user experience. With OpenAI Apps SDK, teams can now create embedded applications that live directly inside ChatGPT — offering users seamless, intelligent, and contextual support.

But building these apps isn't just about writing smart code. It's about designing meaningful, intuitive interactions. That’s why OpenAI published official design guidelines — and why UX GIRL is here to help you translate them into real results.

What Are ChatGPT Apps and the Apps SDK?

ChatGPT apps are mini-tools that users can access directly in the ChatGPT interface. They allow users to perform tasks, analyze data, create documents, fetch information from external sources, and more — all within the flow of conversation.

The Apps SDK lets developers define these app interactions using JavaScript while maintaining full compatibility with the ChatGPT interface. But to deliver real value, apps need to feel intuitive — and that’s where UX comes in.

The Core Design Principles from OpenAI

OpenAI’s UX guidelines are built on six core principles. Here’s what they mean in practice, with insights from the UX GIRL team:

Clarity is key

Your app’s interface must clearly communicate what it does, how it works, and what users can expect. Avoid vague labels or overloaded screens. Guide users with simple language and clean layout.

Respect the user’s intent

Let users take the lead. Your app should support user goals, not hijack the conversation. Avoid aggressive prompts or forced flows.

Make progress visible

Users need feedback. Loading indicators, success confirmations, and microinteractions help users trust the process — especially in a conversational UI.

Minimize user effort

Reduce friction wherever possible. Use smart defaults, context-aware suggestions, and auto-filled values to streamline user input.

Be consistent

ChatGPT has a defined look and tone — follow it. Use system UI components and maintain consistency in voice, spacing, and layout.

Fail gracefully

Errors are inevitable. Design them to be informative and friendly. Offer users clear explanations and next steps without making them feel lost.

How Product Teams Can Apply These Guidelines

Following these principles doesn’t require a full UX overhaul — but it does require strategic thinking. Here are two practical ways your team can implement them:

1. UX-aligned development workflow:

• Define realistic user conversations and app responses early.
• Prototype conversations using mock UIs or prompt flows.
• Test early and often — even with basic, Wizard-of-Oz style setups.
• Build in real-time feedback elements (confirmation messages, visual states).

2. UX checklist for Product Owners:

• Does the user always know what they can do next?
• Are all actions and outcomes clearly explained?
• Is app progress or system state visible?
• Is tone and layout consistent with ChatGPT?
• Do error messages guide users constructively?

The Unique UX Challenges of Designing Inside a Chat Interface

Unlike traditional apps, ChatGPT apps don't rely on menus, tabs, or visual hierarchies. Users interact through text — with fluid, nonlinear intent. This makes context one of the biggest UX challenges.

Small design gaps (e.g., unclear responses or missing context) can lead to confusion. That’s why good conversational design includes scenario testing, intelligent defaults, and visible state changes — even without a traditional UI.

Final Takeaways

Designing inside ChatGPT isn’t just about building functionality — it’s about earning user trust through clarity, empathy, and consistency.

At UX GIRL, we recommend:

• Start with a small MVP to test a focused user goal.
• Use OpenAI’s design principles as a design audit tool.
• Involve UX early — especially for dialogue design and testing.
• Don’t rely on AI to do everything. Guide the user intentionally.

Building with Apps SDK? Let UX GIRL help you design AI-powered experiences that convert, engage, and delight.