All articles
84 published

Creative Tooling
Figma's Agent Goes on the Meter, and Discarded Drafts Pay the Bill
From 6 October 2026 the Figma agent draws AI credits it can't price in advance and never refunds on undo. That bills hardest for the throwaway drafts it was sold to produce.

Development
MCP Error Messages Written for Humans Hurt the Smartest Agents Most
A 28 September 2026 preprint finds MCP servers' developer-facing error steps make capable agents fail more, and that naming a server tool in the step fixes it.
Development
PixelLeak: The Screenshot Request That Leaked Internal UIs
Glow's PixelLeak report found 13,000+ internal screenshots in public GitHub repos. The cause was a routine review request, and the fix sits in your agent's skill files.

Design Engineering
USWDS Wants AI to Test Accessibility. Agencies Inherit the Gap
The U.S. Web Design System plans to automate accessibility testing with AI. The manual layer it may replace was checked once upstream, so the work could move to agency teams.

Prototyping
Google's Vibe-Design Agent Fix Restores Exploration, but Nobody Can Score It
A Google-affiliated team rebuilt exploration inside a commercial vibe-design agent. Offline it broadened output; live, users complained less but corrected more, and exports stayed unproven.

Design Engineering
37signals' Basecamp 5 Passed Every Pull Request Review, Then Broke
At 37signals, AI-agent pull requests for Basecamp 5 each passed review, but together they wrecked the architecture, exposing who wasn't watching the whole system.

Product Design
Google's AI Teammate Study Warns Against What Ando Just Launched
Google's five-month study of a proactive AI 'teammate' found unprompted DMs and interruptions broke trust — the exact behaviors Ando's new Slack rival sells as its pitch.

Product Design
Figma's Own Trial Finds Figma Make Mostly Helps PMs, Barely Designers
Figma's own randomized trial found only a marginal, fragile time saving for designers using Figma Make, versus a robust 35% saving for product managers.

Prototyping
AI Prototypes Lost the Signal That Said They Were Disposable
AI prototypes now look shipped, not sketched, which studies from Mozilla and Purdue show gets users to react honestly but stops teams asking for changes.

Development
The SWE-Bench Leaderboard Can No Longer Tell Models Apart
Two September 2026 papers, days apart, find SWE-bench Verified can't statistically separate its top coding agents, and the harness deciding the score resets with every model swap.

Development
Spotify Says Its PR Thresholds No Longer Apply
Spotify's 16 September retrospective argues its PR-size and complexity warning signs may be outdated, not broken, but nobody has re-derived them.

Design Engineering
WebMCP's Second Interface: Nothing Keeps It True to the First
Chrome's WebMCP trial and Shopify's default agent tools give sites a second, agent-only interface, but nothing enforces that it still matches the one people click.