AI UX DAILY
Sunday, July 12, 2026
4 stories · curated for designers
The stories
Today in AI Products
| Jul 10 |
NNG names 5 qualities that separate trustworthy chatbots from frustrating ones
Nielsen Norman Group published research identifying five qualities that define effective site-specific AI chatbots: handoff willingness, flexibility, proactivity, emotional responsiveness, and transparency. The framework is based on observed user behavior across chatbot interactions and is intended to help teams evaluate and prioritize chatbot design decisions. Each quality maps to a specific failure mode that erodes user trust when missing.
| “ |
Audit your current chatbot or AI assistant against all five qualities and identify which one is weakest, then prioritize fixing that gap in your next sprint. — Designer's Takeaway |
| Jul 10 |
Decagon used Figma MCP and Figma Make to scale a new design system at speed
Decagon, a fast-growing customer experience platform, published a case study with Figma explaining how they used Figma MCP and Figma Make to build and scale a new design system while keeping pace with rapid product requests. The team used AI-assisted generation to move from near-zero to a functioning, populated design system faster than a traditional component-by-component approach would allow. The write-up is specific about which Figma AI tools they used and at what stage of the process.
| “ |
Apply this workflow by using Figma Make to generate initial component variants in bulk, then use MCP to connect your design system tokens directly to code, cutting the back-and-forth between design and engineering during a system buildout. — Designer's Takeaway |
| Jul 09 |
A new framework argues mental health app designers should resist common UI trends
Smashing Magazine published a piece by Kat Homan introducing an evaluation framework specifically for mental health app UI. The argument is that patterns designed to capture attention or signal modernity often work against the core needs of distressed users: reducing cognitive load, building trust, and providing a sense of calm and refuge. The framework gives designers a concrete lens for deciding when a popular pattern is inappropriate for their specific user context.
| “ |
Before shipping a trendy interaction pattern in a health, wellness, or safety-critical product, run it through the question: does this reduce cognitive strain and build trust, or does it just look current? — Designer's Takeaway |
| Jul 09 |
OpenAI ships ChatGPT Work, a long-horizon agent that takes action across apps and files
OpenAI launched ChatGPT Work, an agent mode that can take actions across a user's apps and files, stay engaged on a single project for hours, and turn a stated goal into finished output. Unlike previous ChatGPT features, it is explicitly framed around multi-step, extended work sessions rather than single-turn responses. This represents a meaningful shift in how OpenAI is positioning ChatGPT: less as a chat interface and more as an autonomous collaborator for complex tasks.
| “ |
Consider how your own product's AI features handle long tasks: if a user starts something that takes more than a few minutes, does your UI show clear progress, allow graceful interruption, and surface a readable summary of what the agent did when it finishes? — Designer's Takeaway |
Today's Idea
Trust is the design variable that matters most right now
Three of today's four stories, NNG's chatbot qualities, the mental health UI framework, and ChatGPT Work's long-horizon agent model, all circle the same question: how does a user know they can rely on this thing? Transparency, appropriate restraint, and visible progress are not nice-to-haves. They are the core design work in AI products right now, and each of them requires deliberate decisions at the screen level, not just at the model level.
Stop shipping AI slop
Audit your AI design against 36 patterns
Drop a screenshot, get specific gaps and a Claude Code prompt to fix them. Free, no signup for the first audit.
Audit your design →