AI UX DAILY
Saturday, May 16, 2026
4 stories · curated for designers
The stories
Today in AI Products
 GitHub |
May 15 |
GitHub launches experimental accessibility agent
GitHub is piloting a general-purpose accessibility agent designed to help developers catch and fix accessibility issues during development. The team shared lessons learned from building and testing the agent in real workflows.
| “ |
Study how GitHub is surfacing accessibility violations at the moment of creation rather than post-hoc. Consider building accessibility checks into your design handoff process or component library validation to catch issues before code review. — Designer's Takeaway |
 ChatGPT |
May 15 |
Personal finance experience lands in ChatGPT for Pro users
OpenAI launched a new personal finance feature for ChatGPT Pro users that securely connects financial accounts and provides AI-powered insights grounded in a user's actual financial data, goals, and priorities.
| “ |
Notice how this ties contextual data (real account info) to personalized guidance. Apply this pattern to your own financial, health, or planning tools by designing flows that pull live context first, then surface recommendations anchored to that specific user state rather than generic advice. — Designer's Takeaway |
 Figma |
May 15 |
10 common Figma component architecture mistakes erode design system quality
A new breakdown identifies ten patterns that quietly degrade Figma design systems, from overusing costly variant properties to misusing shapes instead of frames. The fixes involve proper use of slots, variables, modes, auto layout, and scoped state properties.
| “ |
Audit your design system's component structure this week against these ten mistakes (variants, slots, shapes vs. frames, state scoping). Even one fix like switching to slots or consolidating variant properties can measurably improve performance and maintainability for your whole team. — Designer's Takeaway |
 OpenAI |
May 15 |
Databricks integrates GPT-5.5 into enterprise agent workflows
Databricks is now using OpenAI's GPT-5.5 model for enterprise agent workflows after the model demonstrated state-of-the-art performance on the OfficeQA Pro benchmark, a measure of agent reasoning over office tasks.
| “ |
If you're designing enterprise agent flows (approval workflows, document review, automation dashboards), test how your interface adapts when the agent's reasoning capability improves. Better-performing models may surface more complex recommendations, so design progressive disclosure and explainability layers now rather than after launch. — Designer's Takeaway |
Today's Idea
Shift from catching errors after to preventing them before
Three themes emerged this week: accessibility checks moving left (GitHub), financial data grounding recommendations (ChatGPT), and design system quality eroding quietly (Figma). The common thread is prevention and context. Designers who embed validation, real data, and structural discipline into their workflows early will outpace those who rely on late-stage fixes. Start with your architecture and error-prevention surfaces this sprint.
Three things new at aiuxdesign.guide
Free AI UX audit, Courses, and a dedicated Patterns page
1. Free AI UX audit on the homepage. Paste a screenshot of any AI interface, drop your email, and get pattern-grounded findings instantly. Try the audit →
2. Guides are now Courses. The Claude Code Course gets updated every time Anthropic ships — same goes for Cursor, GitHub Copilot, and Claude Design. Browse all courses →
3. Patterns has its own page. All 36 AI UX patterns now live at /patterns with search and category filters.
Want unlimited audits?
We're looking for a small group of designers to run repeated audits and tell us where the tool's weak — what it misses, what it gets wrong, where the UX trips up. Hit reply with the word volunteer and we'll set you up with unlimited audit access in exchange for honest feedback.