Published 13 September 2026 · Source dated 11 May 2026
Before installing another MCP-connected plugin because everyone's talking about it, it's worth understanding what the protocol actually does — give an AI tool a standard way to read your files and tools without bespoke glue code for each integration.
A plain-English explainer video from earlier this year breaks down Model Context Protocol without the hype: it's a standard way for AI tools (Claude, Cursor, Copilot) to read structured data from apps like Figma, instead of every integration needing custom code written from scratch.
As a junior designer, you don't need to build an MCP server. You need to know enough to explain the difference between 'the AI can see my Figma file's actual structure now' and 'I pasted a screenshot into ChatGPT and hoped.' That distinction — structured context versus guesswork — is the actual skill worth having, and it's a method question as much as a tooling one: it changes how you brief AI tools on any task.
Coach
watch the explainer, then write a two-sentence version in your own words — you'll use it in interviews sooner than you think.
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.
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.
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.