Explain Me Anything

Ask for any process. Watch it drawn.

A model writes a few lines, our code draws them. Try your own question.

Live showcaseOpen the app on its own page, for recording and sharing

Opens a full-screen panel. You bring your own API key and it stays in your browser.

How it works

  1. You ask for any process.How does logging in with an identity provider work?
  2. A model writes a few lines.
    flowchart LR
      U([The user]):::user -->|opens app| App[Web app]:::app
      App -->|redirect| IdP[Identity provider]:::server
      IdP -->|login form| U
      U -->|credentials| IdP
    and 4 more linesThis one is saved, no model ran.
  3. Our macro pack lays them out and draws the picture.5 boxes, 8 arrows.
  4. You see it, with the steps as text.8 steps. First: The user connects to Web app for opens app.
Log in with an identity provider: Arch motion: Architecture diagram. 5 nodes, 8 connections and 0 message payloads (8 steps).
A saved example, drawn instantly. No model ran.

Drawn by one of our macro packs, not by a model.

Show the steps
  1. The user connects to Web app for opens app.
  2. Web app connects to Identity provider for redirect.
  3. Identity provider connects to The user for login form.
  4. The user connects to Identity provider for credentials.
  5. Identity provider connects to Web app for one-time code.
  6. Web app connects to Token endpoint for code.
  7. Token endpoint connects to Web app for token.
  8. Web app connects to Resource API for token.

Assistant avatar shows a happy face because the result arrived.You open the app, it sends you to your identity provider, and a one-time code is swapped for a token.

Good to know

Limits

Drawings have at most 12 boxes, 16 arrows and 4 groups. Our code checks each drawing against these limits before it shows it.

Where the saved examples come from

Saved examples. The diagram text and the drawing were made by our own private tools, which are not published. The panel behind the Try it button shows a model's own reply instead.

The drawing is done by one of our macro packs: ordinary code, not a model. The same text always gives the same picture.

For developers: both catalog routes and details

A macro pack, in our catalogue, is a bundle of small pieces of code that turn a few lines of text into finished pictures. This one turns Mermaid into an animated SVG. "Macro pack" is our term; A2UI itself calls the building blocks components.

The demo with both catalog routes

The demo

Two routes, one page. Choose how to see it below, or open this page with the custom catalog route already chosen.

  • Basic catalog
  • Custom catalog (proposed)
  • Route: stock Image
  • Route: motion_arch atom
  1. You ask for a process
  2. A model writes a few lines of Mermaid
  3. Our code lays it out and draws it
  4. The host shows it
Show it as

STORED, scripted example, no model ran

Assistant avatar shows a happy face because the result arrived.You open the app, it sends you to your identity provider, and a one-time code is swapped for a token.

Log in with an identity provider: Arch motion: Architecture diagram. 5 nodes, 8 connections and 0 message payloads (8 steps).
A stock Basic Catalog Image. Drawn by our code from Mermaid; no model was called. The animation plays once.

The same diagram sent as a motion_arch atom and drawn by our own renderer as inline SVG, not as a picture. A host needs a renderer with our catalog registered; we have not tested that on the official renderers.

The same diagram as text

  1. The user connects to Web app for opens app.
  2. Web app connects to Identity provider for redirect.
  3. Identity provider connects to The user for login form.
  4. The user connects to Identity provider for credentials.
  5. Identity provider connects to Web app for one-time code.
  6. Web app connects to Token endpoint for code.
  7. Token endpoint connects to Web app for token.
  8. Web app connects to Resource API for token.
What the model wrote
flowchart LR
  U([The user]):::user -->|opens app| App[Web app]:::app
  App -->|redirect| IdP[Identity provider]:::server
  IdP -->|login form| U
  U -->|credentials| IdP
  IdP -->|one-time code| App
  App -->|code| Tok[Token endpoint]:::server
  Tok -->|token| App
  App -->|token| API[Resource API]:::server

Saved examples. The diagram text and the drawing were made by our own private tools, which are not published. The panel behind the Try it button shows a model's own reply instead.

How the live demo works and where your data goes

Try it yourself

Type a question. Your own Gemini key asks the model from this tab, the model writes a short diagram as text, our drawing service draws it, and you get the picture and the steps.

  1. Your question
  2. Your key calls the model
  3. Our Worker draws
  4. Picture and steps

Where your data goes

  • Your question goes to Google (the Gemini API), under Google's terms, using your key. We never receive it.
  • Free-tier prompts may be read by Google's reviewers. As of 16 November 2026, Google's Gemini API terms say that on the free tier "human reviewers may read, annotate, and process your API input and output", and that Google uses the content to improve its products. Paid use is treated differently. Check Google's current terms before you rely on any of this.
  • The diagram text the model writes (not your key, not your question) goes to our drawing service. It draws the picture and keeps no copy. It writes one log line per request with the route, the result code, the size of the request and whether it was refused, and it keeps a count of drawings per day. It does not log the text, any key or the check token, and our code does not log your address. To limit abuse it counts requests under a one-way hash of your address and the date.
  • Your key stays in this tab. It is held in memory, sent only to Google, never put in the address and never sent to us. A browser extension or a script on this page could read it, so use a throwaway key and delete it afterwards.