What's new

What changed in the editor, newest first. Something you would like to see here? Tell us.

v2.1

The assistant edits shapes, not lines

Rewriting a line means retyping all of it, coordinates and all, so one slip moves a label — and the edit costs whatever that line is long, which on a traced path is thousands of characters. A minified drawing has no lines to address at all. The assistant can now write only what you asked to change instead, addressed by id, class or position: translating two hundred labels is one call to find them and one to rewrite them, and recolouring a traced drawing is a single edit. Line editing has not gone anywhere — it is still how the assistant works on a document that is mid-edit and not yet valid XML, where elements cannot be addressed at all.

Asking the assistant to translate a diagram and recolour it: it looks the labels up with query, rewrites them with set_text, and changes the fill once in the .box rule with set_style_rule.
New

The assistant moves, restyles, duplicates and deletes shapes by identity rather than by line number, so edits no longer depend on how the file is formatted.

New

Six new tools do that work: query to find out what is in the drawing, then set_text, set_attribute, set_style_rule, insert_element and remove_element to change it.

Improved

Recolouring a diagram exported from a design tool now changes the one rule in its style block, rather than trying to set a fill on each shape and appearing to do nothing.

New

It can look through the drawing to answer questions such as "where is the text?" instead of replying that it cannot find anything.

Improved

Text split across several tspans is now recognised as one label, so asking to change wording works on drawings exported from design tools.

Improved

Selecting a shape in the preview tells the assistant which element you picked, and the badge names that element instead of showing raw path data.

Improved

When a turn runs out of tool calls the assistant says so and offers to carry on, rather than stopping as though it had finished.

Fixed

Saving a document immediately after opening it no longer erases its owner.

Fixed

Safari and other WebKit browsers no longer stall on half-loaded pages or hang while saving.

Fixed

New opens a genuinely new document instead of reusing the previous document id and showing a blank canvas.

Fixed

The preview sizes drawings measured in percent correctly, and no longer shows a scrollbar for a drawing that fits.

A faster first paint, and a phone layout that behaves

Opening the editor used to mean watching "Loading…" while the code editor downloaded, and the page shifted about as pieces arrived. The first screen now shows your drawing straight away.

Improved

The editor shows your document immediately and swaps in the full code editor once it has arrived, instead of holding the screen on a loading message.

Improved

Phones pick their layout before rendering, so they no longer download the desktop code editor at all.

Improved

The header no longer jumps as the logo decodes, and the advert sits below the fold on phones rather than pushing the drawing down.

Fixed

The editor opens even when signing in fails, instead of leaving you on an empty page.

Fixed

The cookie banner no longer sits on top of dialog buttons.

A rebuilt model line-up

The model picker had grown into a list of near-identical options. It now offers one model per price point, grouped into free and pro tiers, with the credit cost of a request shown next to each.

The model picker grouped into Free and Pro tiers, each model showing what a request costs in credits.
New

The gpt-5.6 tiers are available, alongside Kimi-K2.6 on the free tier.

Improved

The picker is grouped into free and pro tiers and curated down to one model per price point.

Improved

Every model now reasons at high effort by default, which is the setting most edits benefit from.

Fixed

Declining an image modification no longer swallows the follow-up work the assistant had queued up.

Read the full announcement

Chat history moved to the cloud

AI conversations used to live in the browser, which meant they were gone if you switched device or cleared your data. They are now stored with your account, along with the drawing each message produced — so undo still works after a reload, and an unfinished drawing is waiting for you on the Files page.

The Files page with the new Drafts list, holding documents that have a conversation but were never saved.
New

Conversations continue after a reload, and on another device.

New

Drawings you never saved appear as drafts on the Files page instead of disappearing.

New

Guests can write a prompt before signing in; the prompt is sent for you once you are in.

Improved

Undo is derived from the drawing attached to each message, so the history survives a reload.

Improved

Conversations made before this change are carried up from the browser the next time you open the document.

Fixed

Deleting a document deletes its conversation with it.

Read the full announcement

AI features now need an account

Anonymous AI use was being abused faster than it could be paid for. AI features now require signing in, and every account gets a free monthly allowance of credits. The editor itself stays free and needs no account at all.

New

Signing in is required before using the AI assistant or buying credits.

Improved

A warning appears while your credit balance is running low, rather than at the moment a request fails.

Improved

Every place an SVG is put on the page now goes through one sanitizer, closing the gaps where a crafted drawing could run script.

Improved

Signing in redirects rather than opening a popup, which the stricter browsers were blocking.

v2.0

A rebuilt editor with an AI assistant

The editor was rewritten from the ground up: a resizable live preview, schema-aware autocomplete drawn from the W3C SVG specification, and an AI assistant that edits your drawing from a plain-language instruction — or draws one from scratch and vectorizes it.

The rebuilt editor: SVG source on the left with syntax highlighting, live preview on the right.
The AI assistant answering a plain-language edit request and offering the change as a diff to accept or reject.
An image generated from a text prompt, shown beside the editable SVG the vectorizer produced from it.
Icon search results, ready to insert into the drawing as inline SVG paths.
New

A rebuilt interface with a resizable live preview, a light and a dark theme, and a layout that works on a phone.

New

An AI assistant that edits your drawing from a plain-language instruction and shows the change as a diff before you keep it.

New

Image generation from a text prompt, vectorized in the browser into editable SVG paths.

New

Search across open-source icon sets and insert an icon as inline paths, with no external dependency.

New

Cloud storage for your drawings, with thumbnails and shareable links.

Improved

Autocomplete and hover documentation come from the W3C SVG specification, so they cover the whole element and attribute set.

Improved

Click an element in the preview to jump to its code, with a bounding box drawn around it.

Read the full announcement