Reports

Essay · Interfaces

From text to visual: agents should show, not tell

Coding agents now do an hour of work and report it in twelve paragraphs. We think the answer to that is not shorter text. It is a different medium: a place you can walk through, where the agent points at what it means. Vision is our open-source experiment with that idea, built on Claude Code.

Andromeda · published November 3, 2026 · source on GitHub (MIT)

A dark canvas: a 3D halftone model of a software verification pipeline (a sandbox, a diff, a funnel, a grading box, a verdict, a landing stack), with numbered labels and a note from Claude in the margin.
An answer to "how does our grader decide if an agent's code works?", as Vision draws it: one world, eleven stops, Claude's note in the margin. You press → to step through.

The problem: answers got long

A year ago an assistant answered a question. Now an agent works for an hour, changes forty files, runs the tests and tells you about it. The telling is still a chat message. It has headings and bullets, and it is still a wall you skim.

The trouble is not length. It is that most of what an agent explains has a shape: steps that lead into each other, parts inside parts, something that goes round a loop and comes back. Prose is one-dimensional. Every shape has to be flattened into a sequence of sentences, and then unflattened again by the reader.

Why the medium is changing now

Three things changed at once.

Models can write the picture. A 3D scene is a description: these parts, here, labelled so, connected like this, seen in this order. That is structured text, which is exactly what models are good at producing. The model does not draw pixels. It writes the world, and a renderer draws it.

Models can check the picture. An agent can screenshot its own page in a headless browser, look at the image, see that a label is cramped or a part is hidden, and fix it. That loop is what makes generated visuals usable rather than decorative.

Rendering is free. A WebGL page in a panel beside the editor costs nothing to run. There is no service to call and no image model to pay for.

What an answer looks like in Vision

You ask a question in Claude Code. Claude writes a scene, builds it into a single page, captures every stop to check its own work, and puts it in a panel beside the chat. The world is drawn as halftone dots, light or dark.

A close-up of three plaques reading PASS, FAIL tampered, UNKNOWN beside a gavel, with Claude's note to the right listing the verdict rules and a dotted line pointing to the PASS plaque.
A stop about one part: the camera frames it at the right angle, and Claude's note sits at its height with a dotted line to it. The note never covers what it names.

Nothing plays by itself. You press → and ←, and Claude's mark walks to each part as you go. A stop about the whole rests in the corner; a stop about one thing points at that thing.

The same close-up with corner brackets around the FAIL tampered plaque and a small box beside it containing the typed question: why does a passing canary mean tampered?
Click a part and Claude's note turns into a box to ask about it. The question goes to Claude with the part's name and the current stop attached.

Click empty space and everything goes back to rest. Double-click it and a plain message box opens. While Claude is working, the world blurs and its mark turns in the middle. When it's done, the world comes back.

What we learned building it

Most of the work was not rendering. It was deciding what not to do.

Limits

An experiment, not a product. Vision is slow next to text: a detailed world takes one to three minutes to write, build and check. It works in Claude Code with VS Code (Cursor and Windsurf should work; we haven't tested them), and needs Python, Node and Chrome. The model still sometimes picks a weak layout or a forced object, and a one-line answer should stay one line. We have not measured whether people understand faster this way; that is the next question.

Try it

In Claude Code:

/plugin marketplace add ZekeVoigt/andromeda-vision-public
/plugin install vision@andromeda-vision

Then install the panel: download vision-0.3.0.vsix from the latest release and run Extensions: Install from VSIX…. Ask for something with a shape:

/vision how does a git rebase work

To make it the default, add a line to your CLAUDE.md saying that answers with structure should use /vision. It is MIT licensed; models keep their own licenses and are credited in each world.

Where this goes

We don't think text goes away. We think it becomes the floor rather than the ceiling: the agent picks the medium per answer, the way a good colleague decides between saying something, sketching it, and walking you over to the whiteboard. A yes is a word. A plan is steps. A system is a place.

The interesting part is the last one. Once the answer is a place, the conversation can happen inside it: you point, the agent points back, and the thing you're both talking about stays in view. That is closer to how people explain things to each other than any chat window has been.

If you try Vision, we'd like to hear where it helped and where it got in the way: open an issue.