Figma's blog says Affirm's team used the MCP server and Code Connect to rebuild major product flows in under two days. It's real evidence AI-agent collaboration is becoming normal practice — though we can't confirm it's yet a stated UK hiring requirement.
try the Figma MCP server workflow on one small file this week, then write one sentence for your CV or portfolio notes about what you learned from working alongside an AI agent.
Canva's 2026 trend report is packed with nostalgic and 'Americana' visual directions worth a look. Treat it as inspiration, not a brief — the real skill is picking what fits your actual project.
skim Canva's 2026 trends report, pick exactly one trend that fits your current project brief, and write a one-line justification for why it fits — skip the rest.
Figma's Dev Mode MCP server (beta) feeds your file's components and variables straight to AI coding tools, so generated code matches your design system. It's live now on Dev/Full seats — Penpot has no equivalent yet.
open one component in Dev Mode, check whether its variables and styles are named clearly enough that a stranger (or an AI) could use them correctly — tidy up one if not.
Stills shipped a Figma plugin that drops in real licensed stock photos without leaving your file. It's part of their 2026 trend report push toward raw, human imagery over polished stock.
install the Stills plugin (or any stock-image plugin) in Figma, swap one placeholder image in a portfolio file for a real licensed photo, and see if the piece reads as more finished.
Model Context Protocol is the open standard now used by Cursor, Claude and Figma to let AI agents read and write design files without bespoke integrations. It's moved past experimental status into everyday dev and design tooling in the past few weeks.
Recent discussion around product and design hiring suggests employers increasingly expect candidates to show how they use AI tools in their process, alongside core UX fundamentals, rather than treating it as a bonus skill. This is a shift in expectation, not a confirmed universal requirement.
As AI agents speed up how quickly screens get produced, the risk is shipping untested assumptions faster than before. Core usability testing method hasn't changed — it's more necessary, not less.
Figma's MCP server exposes your actual components and tokens to connected AI agents, meaning generated screens and code are only as on-brand as your library is well-organised. Sloppy naming or orphaned styles now show up directly in AI output.
Figma has shipped a native design agent that works directly on the canvas alongside you, plus an MCP server that pushes code onto canvas and pulls designs back into code. Both stay grounded in your existing components and tokens rather than generating from scratch.
Microsoft has made the GitHub Copilot harness generally available inside Copilot Studio, letting it orchestrate models, tools, memory and MCP servers together. It's a sign that MCP is becoming standard plumbing for agent workflows, not just a dev-tool novelty.
UK design job listings and industry coverage are increasingly expecting junior candidates to show comfort with AI-assisted workflows, not just tool proficiency. It's showing up as a baseline expectation rather than a nice-to-have.
With so much noise about AI speeding up design, lightweight usability testing remains one of the most reliable ways to catch real problems early. It's an established method, not a new trick, and it still beats guessing.
As AI agents start reading design systems directly through MCP-style integrations, teams are cleaning up token naming and documentation so agents (and humans) don't misread intent. It's a quieter but real shift in design-system hygiene.
Figma now ships a canvas agent that works alongside you inside a file, plus an MCP server that lets external agents read and write Figma designs. Both are shipped features you can use today, not a roadmap promise.
OpenAI's rundown of AI-native companies shows agents handling onboarding and account management end-to-end, with humans still deciding what matters. It's a useful reality check against pure agent hype.
Next time you use an AI tool for a task, write down the one decision point where a human still had to check the output — that's the skill worth naming in interviews.
Design Week's coverage of a recent CBI report points to a gap between design businesses talking about AI and actually using it in delivery. For junior job seekers, that gap is where you can stand out.
NN/g's ongoing usability research keeps making the same unglamorous point: watching real users still catches problems AI critique tools can't. It's not exciting, but it's still the job.
Figma folded its MCP server and canvas agent into normal release notes months ago — it's now a working feature, not a keynote demo. If you're on Figma + Penpot, this is currently a Figma-only advantage worth understanding.
A widely-shared breakdown maps out the architecture patterns behind today's AI agents — from browser-using agents to multi-agent systems talking to each other. Useful vocabulary for understanding what's happening inside tools like Figma's agent or Cursor.
Next time an AI agent's output in Figma or Cursor surprises you, try to guess which 'pattern' it's using — it's a quick way to build intuition for where these tools break.
We looked for UK design job listings explicitly asking for MCP or AI-agent experience and couldn't verify any yet. The underlying tooling shift is real and dated, though, so it's worth getting ahead of it quietly.
