Published 31 August 2026 · Source dated 20 May 2026
Cursor and Claude Code speak the same Model Context Protocol, so an MCP server config you write once now works in both without changes. That's a genuinely useful shortcut for anyone juggling AI tools.
Coach
if you set up an MCP server for one AI tool, save the config file somewhere you can find it — you'll likely reuse it in the next tool you try.
Surf this topic: UCD methods (opens in a new tab)
Source: claudefa.st (opens in a new tab) ·
Jakob Nielsen's ten usability heuristics have been the backbone of UX critique since 1994. They're worth relearning properly, not just skimming the list.
nngroup.com (opens in a new tab)
Your move
Pick one screen from your own portfolio and run it against all ten heuristics — write down which one it breaks hardest, and fix that first.
AI tools can generate screens fast, but they don't validate usability — that's still on you. Classic heuristic evaluation is more relevant, not less, now that production speed has gone up.
nngroup.com (opens in a new tab)
Your move
before you ship your next AI-assisted screen, run a quick 10-point heuristic check against it and write down what fails.
More first drafts are arriving via AI agents, but the fundamentals of a good design critique haven't moved. IxDF's literature on critique still holds regardless of who — or what — made the first version.
interaction-design.org (opens in a new tab)
Your move
next time you review an AI-assisted design, ask 'what user problem does this solve?' before commenting on how it looks.
