News

Editorial dispatches and the latest from design tool blogs and changelogs.

Subscribe via RSS

New tools and editorial dispatches, straight to your inbox.

Showing 66 items ·RSS checked 17 Nov 2026
Lovable
Lovable · ↗

Lovable gives every draft its own disposable database

A draft on a project with Lovable's built-in backend now gets a backend of its own, pre-filled with example data. Test a change that touches real data — a new field, a new table — without it reaching your live app; accept the draft and Lovable applies the change to the real database before publishing, then drops the test data. It's the kind of unglamorous safety work that decides whether a tool like Lovable is for demos or for things people actually run: the build-by-describing-it pitch only holds up if changing your mind does not mean breaking production.

Figma
Figma · ↗

How 1Password uses Figma Make to design for trust and certainty

From autofill to AI agent approvals, every 1Password interaction counts. Here's how the design team uses Figma Make to design moments users trust.

Figma
Figma · ↗

AI’s role in the creative process

Which parts of the creative process can AI do for us—and which do we insist on keeping for ourselves?

Figma
Figma · ↗

How 3D transforms and Figma’s agent brought a launch video to life

See how Figma’s Brand Studio team combined 3D design, agent-built plugins, shaders, and motion to create a video together on the canvas.

+107 more from Figma →
Framer
Framer · ↗

Framer's agent can now generate the image or shader you describe

Ask Framer's agent for a custom image, texture, or illustration, or describe a shader — halftone, bokeh, CRT, pencil, a custom effect you saw somewhere — and it builds it, tweaks an existing one, or chains the two together: generate an image, then push it through a generated shader. Useful for exactly the job this category is good at right now — producing a specific visual asset on request — not for replacing the taste that decides whether the result is any good.

Wonder
Wonder · ↗

Wonder's comments aren't just discussion, they're a way to brief the agent

Pin feedback anywhere on the canvas, thread the discussion, and @mention Wonder in the thread to have the agent make the change directly — everyone in the file sees it live. Claude Code, Codex, and Cursor can also read, reply to, and resolve those same threads over the Wonder MCP, so a comment isn't just a note to a human, it's an instruction any connected agent can act on.

Wonder
Wonder · ↗

Wonder admits the canvas isn't enough once you're actually building

Dev view gives Wonder's chat the whole window: files, terminal, diffs, and the pull request sitting beside the conversation, with one button to commit, push, open a PR, or merge once checks pass. Switch back to the canvas any time; it's the same worktree and the same agent either way. It's the clearest sign yet that Wonder's "design and code on one canvas" pitch was always going to hit a wall once the work stopped being exploratory and started needing to ship.

v0
v0 · ↗

v0 will now check its own code for security holes, if you ask

v0 can review the code it just changed, or the riskiest code in the project, for missing auth checks, injection, and SSRF, cross-checking each finding against the rest of the project and suggesting a fix it will not apply without approval. It's a tacit admission of something that's been true since AI codegen got good at producing code that compiles: looking right and being safe to ship are different problems. The catch is it's opt-in. Someone still has to think to ask.

Lovable
Lovable · ↗

Lovable's agent now works on a schedule, not just on request

Automations let Lovable take care of recurring jobs — a morning check of your published sites, a weekly new-signups summary, a Friday list of your oldest backlog items — on whatever cadence you set, posting results back into the chat. Available on Free, Pro, and Business. Lovable's agent isn't only something you prompt anymore — it also runs unattended and reports back.

Penpot
Penpot · ↗

Complex enterprise UX and UI at scale: The case for design infrastructure

Learn how open, self-hostable design infrastructure helps enterprise teams scale UX and UI, reduce vendor lock-in, and connect design to code with Penpot.

Lovable
Lovable · ↗

Lovable apps can now take your money

Connect your Lovable app to PayPal and it can run checkouts, take donations, or handle bookings without a developer wiring up a payment gateway by hand. That's the detail that's mattered the whole time: a demo that looks finished but can't charge a customer isn't shippable. This closes that gap for anyone building a real small business inside Lovable, not just a pitch deck.

+17 more from Lovable →
Cursor
Cursor · ↗

Cursor starts building the internal tools nobody wants to build

A cloud agent in Cursor can now scaffold a web app, provision a Postgres database, wire up SSO, and publish it behind a shareable link, with admins getting visibility into every deployed app and secret and the power to block or unpublish on sight. The use cases Cursor lists are telling: event registration, onboarding, sales dashboards. This isn't Cursor chasing your product. It's Cursor chasing Retool's job — the internal tool nobody budgeted an engineer for.

Framer
Framer · ↗

Framer's agent harness now runs in parallel

Reading, deciding, and editing now happen at once instead of one after another — half the tool calls, a third less cached-token use per message. The same harness is exposed over MCP, so any agent connecting to Framer gets the same speed-up.

Framer
Framer · ↗

Framer hands its agent the A/B test

Convert's agent can now create, edit, and analyse funnels and A/B tests on its own, and set country-based triggers so overlays can target visitors by region. Framer's agent is moving past layout and copy into running the experiment itself.

+8 more from Framer →
Penpot
Penpot · ↗

Digital sovereignty for business: A practical guide to controlling your tech infrastructure

Vendor lock-in, proprietary formats, and shifting regulations put your business at risk. Learn how digital sovereignty helps you control your tech stack on your own terms.

Wonder
Wonder · ↗

Wonder rebuilds its canvas to edit your actual live app, not a mockup of it

Instead of generating a new app from a prompt, Wonder's new canvas points at your real codebase and renders the live app directly: click through it at phone, tablet, or desktop size, edit elements in place, and the agent writes the change back to the code. It also now works with your own Claude Code or Codex subscription rather than a bundled model. Most canvas-to-code tools generate a plausible-looking screen and hope the code holds up; working on the live app instead is a more honest attempt at the actual problem. Still alpha-stage, but worth watching.

Penpot
Penpot · ↗

What is declarative design and why is it the future?

Declarative design means setting rules a design follows, not detailing how it looks in every situation. Let’s compare it to other approaches (with examples!)

+31 more from Penpot →
Spline
Spline · ↗

Spline opens its 3D scenes to agents that never open the editor

Spline shipped a cloud-hosted remote MCP server, so Claude, ChatGPT, and other agents can build and publish 3D scenes in a live project without anyone opening the editor — until now, MCP access meant running the desktop app locally. The same release adds a PBR materials pass with HDR lighting and native PBR/animation export to iOS and Android. Agents working directly in the canvas has been spreading through 2D UI design all year; 3D has resisted it longer. Opening the room to agents and the work being any good are two different things.

Magic Patterns
Magic Patterns · ↗

Magic Patterns rebuilds around a canvas, not a chat box, and says the agent shouldn't drive

MagicOS keeps every direction, PRD, and rejected idea on one spatial canvas instead of letting it vanish into a chat log, and adds parallel task coordination and voice input. Their words: the canvas should be yours, the agent should be your collaborator, not the one driving, a stance against the autonomous-AI-does-everything pitch most of this category is currently selling.

Cursor
Cursor · ↗

Cursor's new Projects mode turns it into a standing team of agents, not a pair programmer

A coordinator agent plans a feature or migration, delegates the pieces to subagents, and keeps working in the cloud after you've closed your laptop — it can even pick up new work on its own when it spots a Slack message or a pull request. It's in beta, and the real question is whether the coordination holds up on an actual codebase rather than a demo. But the shift in posture is unmistakable: Cursor wants to be infrastructure you leave running, not a tool you sit down with.

Magic Patterns
Magic Patterns · ↗

Magic Patterns adds PDF upload, so a spec or deck can brief the agent directly

Drop in a spec, deck, or doc and Magic Patterns's agent treats it as context for what it builds next, instead of you retyping the brief into a prompt box. It's a small addition, and the category still cannot get output to shipping fidelity on its own, but starting from the document a team actually wrote is a real workflow fix, not a demo trick.

Onlook
Onlook · ↗

The future of design tooling in the age of AI

Everyone Coded. Nobody Curated.

Codex
Codex · ↗

Codex 0.128.0: persistent goals and 90% faster task completion

Codex v0.128.0 ships persisted /goal workflows with TUI controls for long-running tasks, plus container caching that cuts median task completion time by 90%. Richer permission profiles and plugin marketplace improvements round out the release.

Zed
Zed · ↗

Zed 1.0: the Rust-built GPU-accelerated editor hits its first stable release

The former GitHub Atom team ships Zed 1.0, adding parallel AI agents, bookmarks, and a dedicated ‘disable all AI features’ mode for developers who want pure speed. Built on the custom GPUI framework, it stays native where Electron-based editors cannot.

GitHub Copilot
GitHub Copilot · ↗

GitHub Copilot for Visual Studio gets cloud agents, a Debugger agent, and chat history

The April Visual Studio update adds cloud agent sessions that create PRs while you work locally, a Debugger agent that validates fixes against live runtime behaviour, user-level custom agent definitions, and a chat history panel.

Cursor
Cursor · ↗

Cursor launches Security Review with AI agents that scan every PR and codebase for vulnerabilities

Cursor Security Review enters beta for Teams and Enterprise plans, adding two always-on AI agents: Security Reviewer (checks every PR for auth regressions, prompt injection, and privacy risks inline at the diff) and Vulnerability Scanner (scheduled codebase scans with Slack alerts). Both support MCP integration with existing SAST and secrets scanners.

+2 more from Cursor →
Midjourney
Midjourney · ↗

Midjourney V8.1 launches on Discord and the web with improved sharpness

After the alpha period, V8.1 is now live on both Discord and midjourney.com with improved sharpness and quality in HD mode, SREFs, and Moodboards. SD is the temporary default while the team manages server capacity.

Rive
Rive · ↗

Rive AI Agent goes free — Ask mode and hourly-recharging credits

Rive updated its in-editor AI Agent with more efficient models that cost significantly fewer credits to run, and added an Ask mode for quick questions that do not need full agent invocation. Free plan users now get AI Agent access with credits that recharge every hour.

Windsurf
Windsurf · ↗

Devin for Terminal: Windsurf's AI agent goes CLI

Windsurf made its Devin agent available as a CLI tool for all subscribers — local codebase access, cloud handoff, and up to 30% more token-efficient than Cascade.

Motiff
Motiff · ↗

Motiff editor winds down, pivoting to AI plugin

Motiff announced its UI editor will fully discontinue on June 23, 2026, following its settlement with Figma. The team is transitioning to delivering AI capabilities as a plugin rather than a standalone design tool.

Midjourney
Midjourney · ↗

Midjourney opens 2K high-res rating to tune V8.1 and V8.2

Midjourney is running its first community image-ranking session at full 2K resolution, asking users to compare pairs of images to help tune upcoming aesthetic improvements in V8.1 and V8.2 toward natively HD output.

GitHub Copilot
GitHub Copilot · ↗

GitHub Copilot drops premium requests in favour of AI Credits from June 1

GitHub is replacing premium request units with token-based AI Credits from June 1. Subscription prices stay the same — $10/mo Pro, $39/mo Pro+ — but usage is now metered on tokens consumed, giving organisations pooled budgets and finer cost control.

Tokens Studio
Tokens Studio · ↗

Tokens Studio v2.11.5: variable scopes sync with Studio platform

Variable scopes and code syntaxes now sync from the Studio platform, and per-mode rem-to-pixel scaling is available. A focused release for teams running serious design token pipelines.

Google Stitch
Google Stitch · ↗

Google open-sources DESIGN.md, a file format for feeding brand systems to AI coding agents

Google Labs released DESIGN.md as an Apache 2.0 open-source format — a single YAML + markdown file that encodes a brand's design tokens and explains how to use them, so AI coding agents like Claude Code, Cursor, and Copilot generate on-brand UI from the project root.

Jitter
Jitter · ↗

Displacement Shaders add organic wave distortion to Jitter animations

Jitter added displacement shaders — a new animation type that applies organic, wave-like distortion to any element. You control amplitude, offset, repeat, and direction for both start and end states, making it useful for fluid reveals, ambient backgrounds, and motion-graphic transitions.