wizards 0.4.7 → 0.5.1

package/apps/runtime/dist/docs/user/assistant.md

@@ -1,72 +1,77 @@
 ---
-title: Goose, the assistant
-description: The chat at the bottom of every studio page. It knows the app, sees the page you are on, shows you where things are and fills the space in.
-version: 0.3.7
+title: Goose, the help assistant
+description: The chat at the bottom of every studio page. Goose knows engenty wizards, sees the page you are on, shows you where things are and fills in the space.
+version: 0.5.0
 ---
 
-Goose, the assistant, stands at the bottom of every page of the studio but the editor, which has a
-conversation of its own. It thinks on the High class of Text & reasoning: your subscription,
-your keys or credits ([Models and account](./models.md)).
+Goose is still being tried out and doesn’t show in every studio yet. Where it is switched on, it
+works as described here.
 
-| Ask it | It |
+Goose stands at the bottom of every page of the studio except the editor, which has a chat of its
+own: the assistant that builds your wizard. Goose runs on the High class of Text & reasoning:
+your subscription, your own API keys or your credits ([Models and account](./models.md)).
+
+| Ask it | Goose |
 |---|---|
 | How something works | Reads this guide (the version you installed) and links the page |
 | Where something is | Opens the page and points at the place |
-| About your account | Looks up your plan, credits and what you used; it never buys or upgrades |
-| About templates | Searches the gallery and shows the ones it recommends as the gallery's cards under its answer. A card opens the template; make a wizard of it there |
+| About your account | Looks up your plan, credits and what you used. It never buys or upgrades anything |
+| About templates | Searches the templates and shows the ones it recommends as cards under its answer. A card opens the template, and you start a wizard from it there |
 | About your wizards | Looks at their runs, the failed ones too |
-| About models | Says what thinks and makes here, and what is missing |
+| About models | Says which models are set up here, and what is missing |
 | To fill in the space | Reads a website or your files ([Space](./space.md#have-it-filled-in)) |
 
-It sees the page you write from: where you are, what is open and what the page shows. It may put
-a value into a field for you; you check it and save. It does not press buttons.
+Goose sees the page you write from: where you are, what is open and what the page shows. It may
+put a value into a field for you; you check it and save. It doesn’t click buttons.
 
 ## Where it stands
 
 | | |
 |---|---|
-| At the bottom | The default. Click the field or the engenty, and the chat rises above it |
-| Closed | ✕ in the header: the engenty at the lower right; a click opens the chat where it last stood. Data and Results start closed |
-| Sidebar | Beside the page, on a window 1,520 pixels wide or more |
+| At the bottom | The default. Click the field, and the chat rises above it |
+| Closed | ✕ in the header closes it to “Ask Goose” at the lower right. A click opens the chat where it last stood. On Data and Results it starts there |
+| Sidebar | Beside the page, in a window 1,520 pixels wide or more |
 
-The buttons in the chat's header switch between them; the studio remembers your choice.
+The buttons in the chat’s header (“As a sidebar”, “Dock at the bottom”) switch between them. The
+studio remembers your choice.
 
-At the bottom, the chat moves out of the way of what it covers: drag it by the grip before its
-name (or the engenty, while it is folded). It stays where you put it. Near the bottom it snaps to
-the middle or the right; near the right side, higher up, it becomes the sidebar, and the
-sidebar's grip pulls it out again. A dashed outline shows where it will snap. The handle on top of
-the chat sets how tall the thread is; a click on it folds the chat away.
+At the bottom, you can move the chat out of the way of what it covers: drag it by its grip, or by
+Goose sitting on top of it. It stays where you put it. Near the bottom it snaps to the middle or
+the right. Near the right side, higher up, it becomes the sidebar, and the sidebar’s grip pulls it
+out again. A dashed outline shows where it will snap. The handle on top of the chat sets how tall
+the chat history is; a click on it folds the history away.
 
 ## Writing while it works
 
-You can write on while Goose answers. What you send waits above the field:
+You can keep writing while Goose answers. What you send waits above the field:
 
 | | |
 |---|---|
-| Enter | Goose reads it before its next step, and keeps what you asked before unless the message changes it |
+| Enter | Goose reads it before its next step. It keeps to what you asked before unless the new message changes it |
 | ⌘↩ (Ctrl+↩) | It goes out as the next question once the answer is done |
-| Send now | Stops the answer and sends it at once |
+| “Send now” | Stops Goose and sends it at once |
 
-The stop button stands where Send does while the field is empty.
+While Goose answers and the field is empty, the stop button stands where “Send” does.
 
 ## One chat
 
-You have one chat, the same on every page and in every space, after a reload and on another
+You have one chat. It is the same on every page and in every space, after a reload and on another
 device. Nobody else in the team sees it.
 
-- **New chat** (the pen in the header, or the menu at the chat's name) clears the chat at once and
-  sums the old one up meanwhile. Goose keeps the summaries of your last chats in mind.
-- **Earlier chats** lists the closed ones to read. Ask about something you discussed before, and
-  Goose searches them.
+- **“New chat”** (the pen in the header, or the menu at the chat’s name) clears the chat at once
+  and summarises the old one in the background. Goose keeps the summaries of your last chats in
+  mind.
+- **“Earlier chats”** lists the closed ones, for you to read. Ask about something you discussed
+  before, and Goose searches them.
 
 ## Live chat
 
-**Talk** stands where Send does while the field is empty. The chat becomes a call: you speak, a
-pause sends what you said, and the answer is read aloud. Then it listens again; talking over it
-stops its voice.
+**“Talk”** stands where “Send” does while the field is empty. The chat becomes a call: you speak,
+a pause sends what you said, and Goose reads its answer aloud. Then it listens again. If you talk
+over it, it stops speaking.
 
-- Chrome and Safari turn your speech into text themselves. Other browsers record, and your
+- Chrome and Safari turn your speech into text themselves. Other browsers record it, and your
   model for voice notes writes it down.
-- The answer is read with your computer's voices, or with the speech model where one is set up
-  (the speaker button in the call).
+- Goose reads its answers with your computer’s voices, or with the speech model where one is set
+  up (the speaker button in the call).
 - Everything said stays in the chat as messages.

package/apps/runtime/dist/docs/user/build-a-wizard.md

@@ -1,91 +1,116 @@
 ---
 title: Build a wizard
-description: Describe what the wizard should do, or start from a template. Then change it in the conversation or step by step.
-version: 0.3.4
+description: Describe what the wizard should do, or start from a template. Then change it in the chat or step by step.
+version: 0.5.0
 ---
 
 ## Start one
 
-"New wizard" on the studio's first page gives three ways in:
+“New wizard” on the list of your wizards, or in the sidebar, opens the page “What should your
+wizard do?”. It gives you three ways in:
 
 | Way | How |
 |---|---|
-| Describe it | Answer "What should your wizard do?" in your own words and press "Build wizard" |
-| A template | Pick one below the text field. Search, or narrow by industry, result and capability |
-| A package | "Import a wizard package", at the foot of the page, takes a `.wizard` file someone exported |
+| Describe it | Write what the wizard should do in your own words and click “Build wizard” |
+| A template | Choose one under “Or start from a template”. Search, or narrow the list by industry, result and capability |
+| A wizard file | “Import a wizard file”, at the foot of the page, takes a `.wizard` file someone exported |
 
 A description that works says who enters what, what the wizard does with it, and what comes out:
 
-> Customers enter their product and audience, the wizard researches competitors and writes a
+> Customers enter their product and audience. The wizard researches competitors and writes a
 > positioning briefing as a PDF.
 
-You can change everything afterwards.
+You can change everything afterwards in the chat.
+
+### Before you build
+
+- **How it runs.** “Runs as” above the text field says how people will reach the wizard: as a
+  “Step-by-step wizard” unless you choose otherwise. The + beside it asks “How should it run?”
+  and lists the other channels this studio offers, for example “Chat”, “Live voice” or “Video
+  call”. One channel always stays on. The assistant builds the wizard for what you chose.
+- **Files.** Attach examples, price lists or screenshots with the + in the text field, or paste
+  or drop them there. They go into the wizard’s files, and the assistant looks at them.
+- **Dictation.** The microphone button lets you speak instead of type.
+- **Similar wizards.** While you type, the page lists up to ten of your own wizards and templates
+  that come close. “Open” opens one of yours, and “Use” starts from a template. This way you
+  don’t build again what is already there.
 
 ### Templates
 
 - A template shows how the wizard runs, how long a run takes, what it costs and what it needs
-  before you start from it.
-- "Not set up here" names a model this install has no way to yet, for example video. Set it up
-  under [Models & account](./models.md), or pick another template.
-- A star keeps a template on this computer, ready without a connection.
-- A wizard started from a template is your copy. Later changes to the template do not touch it.
+  before you start from it with “Start with this template”.
+- “Not set up here” names a model that isn’t set up on this computer yet, for example for video.
+  Set it up under [Models and account](./models.md), or choose another template.
+- A template marked “Pro” needs plugins that come with Pro on engenty.ai.
+- A star keeps a template on this computer, so you can use it without a connection.
+- A wizard started from a template is your copy. Later changes to the template don’t touch it.
 
 ## The editor
 
 | Part | What it is for |
 |---|---|
 | The diagram, left | The steps as a flow with their branches. Click a step to open it |
-| Conversation | Say what should change. The assistant edits the flow and tells you what it did |
+| Chat | Say what should change. The assistant edits the flow and tells you what it did |
 | Steps | One step at a time: its texts, fields, tools and model class. Move it up or down, or delete it |
 | Files | What the wizard needs on every run: widget code, libraries, price lists. Upload your own or let the assistant write them |
-| Memory | What the wizard knows across all its runs: the notes AI steps with the "Pages" tool read and add to, and the tables of its shared lists |
+| Memory | What the wizard knows across all its runs: the notes that AI steps with the “Pages” tool read and add to, and the tables of its shared lists |
 | Runs | The test runs and live runs of this wizard |
 
-### In the conversation
+On a phone or a narrow window the panels sit in a sheet over the bottom of the diagram. Drag its handle to make it taller, or tap
+it to fold it away.
+
+A click on the wizard’s name in the top bar opens its own settings: its title, description and
+greeting, its avatar, and the language it speaks to people in. With “Automatic, from its texts”
+the wizard speaks the language its texts are written in.
+
+The ⋯ button in the top bar (“More”) duplicates the wizard, exports it, or deletes it. Only
+whoever manages the team can delete a wizard. The same menu is on the wizard’s card in the list.
+
+### In the chat
 
-- Write what should be different: "Ask for the delivery date on the first page", "Add a review
-  before the PDF".
+- Write what should be different: “Ask for the delivery date on the first page”, “Add a review
+  before the PDF”.
 - Attach files the assistant should look at: an example document, a price list, a screenshot.
 - Dictate instead of typing with the microphone button.
-- If the connection drops, what was already built is saved. Send the message again.
+- If the connection drops, what was already built is saved. Send your message again.
 
 ### Step by step
 
-Open a step from the diagram or under "Steps". What you can set depends on its type: see
+Open a step from the diagram or under “Steps”. What you can set depends on its type: see
 [Steps](./steps.md).
 
-"Add step" on a step in the diagram, or under "Steps", puts a new step after it. Say what it
-should do, pick its kind or leave it to the AI, and say when it comes: always, only if a
-condition holds, or when the AI decides so. "Create" lets the assistant build it in the
-conversation; "Insert empty" adds a blank step of the kind you pick, for you to fill.
+“Add step” on a step in the diagram, or under “Steps”, puts a new step after it. Say what it
+should do and choose its kind, or leave it to “AI chooses”. Then say when it runs: “Always”,
+“Only if…” a condition holds, or when “AI decides…”. “Create” lets the assistant build the step
+in the chat. “Insert empty” adds a blank step of the kind you choose, for you to fill in.
 
 ## When the wizard needs fixes
 
 A draft may be incomplete while you work on it. Before you test or share, the editor lists what
-is missing, for example a step that uses an answer asked only later, or a tool that is not
-installed here.
-"Let the assistant fix it" hands that list to the conversation.
+is missing, for example a step that uses an answer that is only asked later, or a tool that isn’t
+installed here. “Let the assistant fix it” hands that list to the chat.
 
-If a step needs a model this install has no way to, the editor says which. A wizard whose every
-path needs it cannot start; if only one branch needs it, choose another path when testing.
+If a step needs a model that isn’t set up here, the editor names the step and the model, and
+“Set up models” takes you there. If every path of the wizard needs that model, the wizard can’t
+start. If only one branch needs it, choose another path when you test.
 
 ## What makes a good wizard
 
-- Write for people who are not technical: plain words, titles phrased as questions.
-- Few pages, one theme per page, at most five fields. Ask only what the result needs.
+- Write for people who are not technical: use plain words, and phrase titles as questions.
+- Keep to few pages, one theme per page and at most five fields. Ask only what the result needs.
 - Put a review before anything expensive, such as video, and before the final result.
 - Let the phone do the typing: a photo instead of a description, the location instead of an
   address form, a voice note instead of a long text.
-- Money belongs in a line-items field. The wizard computes net, VAT and total itself; a model
-  never does.
+- Put money in a line-items field. The wizard works out net, VAT and total itself; a model never
+  does.
 - Facts from the web need a research step before the step that writes.
 
 ## Take it with you
 
-The download icon in the editor's top bar exports the wizard as a package (`.wizard`): its steps
-and its files. "Import a wizard package" on the "New wizard" page of any studio takes it in.
+“Export as a wizard file (.wizard)” in the wizard’s ⋯ menu downloads its steps and its files as
+one file. “Import a wizard file” on the “New wizard” page of any studio takes it in.
 
-The share dialog downloads a package too, under Website → "Without an account: as a package":
-the published version (the draft while there is none), for a WordPress site that runs it
-without an account; with "Take the knowledge along" the space's pages go with it as files. See
-[WordPress](./wordpress.md#without-an-account).
+The share dialog downloads a wizard file too, under “Website” → “Without an account: as a
+package”. It holds the published version, or the draft while there is none, for a WordPress site
+that runs it without an account. With “Take the knowledge along”, the space’s pages go with it
+as files. See [WordPress](./wordpress.md#without-an-account).

package/apps/runtime/dist/docs/user/command-line.md

@@ -1,79 +1,82 @@
 ---
 title: Command line
-description: The wizards command — start, setup, status, update — and the install's settings file.
-version: 0.3.4
+description: The wizards command – start, setup, status, update – and the settings file on your computer.
+version: 0.5.0
 ---
 
 ## Commands
 
-| Command | Does |
+| Command | What it does |
 |---|---|
-| `wizards` | What runs, and a menu: open the studio, restart and stop while it runs, "Start as service" or "Start here" (in this terminal) while it does not; update, which restarts what runs into the new version; "Service settings" (start at login); connect AI apps, status, setup, help. The first time, the setup runs first. Needs a terminal |
-| `wizards start` | Starts it and opens the studio. It runs in that terminal; Ctrl-C stops it. The first time, the setup runs first |
-| `wizards studio` | Opens the studio in your browser. When it does not run, it starts as a service first |
-| `wizards setup` | The guided setup again: your account, an AI client to think with, the browser and ffmpeg, start at login, your AI apps. `--local` leaves the account out ([Local only](./local-only.md)) |
-| `wizards account` | How the install stands to your account: signed in as whom, which team, the credits. `sign-in` shows a code and opens the browser; `sign-out` disconnects the install |
-| `wizards open` | Lets this browser into the running studio. `--print` only shows the link; it works once, within a minute |
-| `wizards status` | What is installed and what runs, with the browser the app uses for PDF, PNG and websites |
-| `wizards doctor` | Status, and what is wrong |
-| `wizards logs [n]` | The last lines the running install printed (100, or `n` up to 2000); keys and tokens are taken out |
-| `wizards report` | Sends status, model settings (never a key) and the last 500 log lines to your [linked account](./models.md#account), so support can look at what went wrong. Nothing is sent unless you run it. The command names the report's id; without a linked account it says to link one under Settings → Account |
-| `wizards stop` | Stops it. The data is kept |
-| `wizards restart` | Stops it and starts it again; after an update, the new version. When it does not run, it starts as a service |
-| `wizards update` | Installs the newest version |
-| `wizards autostart on` / `off` | Starts it at login, or no longer. A LaunchAgent on macOS, a systemd user service on Linux |
+| `wizards` | Shows what is running, and a menu. While it runs, you can open the studio, restart or stop it; while it doesn’t, “Start in the background” or “Start here” (in this terminal). Then “Update”, which restarts it into the new version, “Start at login”, “Connect AI apps”, “Account”, “Status”, “Setup” and “Help”. The first time, the setup runs first. It needs a terminal |
+| `wizards start` | Starts it and opens the studio. It runs in that terminal, and Ctrl-C stops it. The first time, the setup runs first |
+| `wizards studio` | Opens the studio in your browser. If it isn’t running, it starts in the background first |
+| `wizards setup` | Runs the guided setup again: your account, an AI client, the browser and ffmpeg, start at login, your AI apps. `--local` leaves the account out ([Local only](./local-only.md)) |
+| `wizards account` | Shows the account this computer is signed in to: who, which team, the credits. `sign-in` shows a link and a code and opens your browser; `sign-out` disconnects this computer |
+| `wizards open` | Signs this browser in to the running studio. `--print` only prints the link; it works once, within a minute |
+| `wizards status` | Shows what is installed and running, with the browser it uses for PDF, PNG and websites |
+| `wizards doctor` | Shows the status and checks for problems |
+| `wizards logs [n]` | Prints the last lines engenty wizards printed while running (100, or `n` up to 2000). Keys and tokens are taken out |
+| `wizards report` | Sends the status, the model settings (never a key) and the last 500 log lines to your [account](./models.md#account), so support can see what went wrong. Nothing is sent unless you run it. The command names the report’s ID. If this computer isn’t signed in, it tells you to sign in under Settings → Account or with `wizards account sign-in` |
+| `wizards stop` | Stops it. Your data is kept |
+| `wizards restart` | Stops it and starts it again; after an update, that is the new version. If it isn’t running, it starts in the background |
+| `wizards update` | Installs the latest version |
+| `wizards autostart on` / `off` | Starts it when you log in, or stops doing so. It is a LaunchAgent on macOS and a systemd user service on Linux |
 | `wizards connect [app …]` | Adds your wizards to your [AI apps](./ai-apps.md): every app found, or the ones you name |
 | `wizards disconnect [app …]` | Takes them out again |
-| `wizards mcp` | The MCP server over stdio. AI apps start it; you do not |
+| `wizards mcp` | Runs the MCP server over stdio. AI apps start it; you don’t |
+| `wizards validate <path …>` | Checks wizards without the studio: `.wizard` files, unpacked wizard files, or a wizard’s JSON. `--json` prints the problems as JSON. A space’s connectors and plugins are checked when you import it |
 
-| Option | Does |
+| Option | What it does |
 |---|---|
 | `--yes`, `-y` | Asks nothing and installs nothing optional |
+| `--local` | Sets up without an account, so nothing leaves this computer ([Local only](./local-only.md)) |
 | `--client <name>` | Installs this AI client without asking: `codex`, `claude`, `gemini`, `cursor` |
 | `--no-open` | Starts without opening the browser |
-| `--service`, `-s` | Starts it as a service: detached from the terminal, and the command returns. `wizards stop` stops it; its output goes to `logs/runtime.log` |
-| `--version`, `--help` | |
+| `--background`, `-s` | Starts it in the background (`--service` still works): detached from the terminal, and the command returns. `wizards stop` stops it, and its output goes to `logs/runtime.log` |
+| `--version`, `-v` | Prints the version |
+| `--help`, `-h` | Lists every command |
 
-Started in a terminal, it runs while that terminal is open; Ctrl-C stops it. With
-`wizards start --service` it keeps running after the terminal closes. If it already
-runs, `wizards start` opens the running one instead of starting a second.
+When you start it in a terminal, it runs while that terminal is open, and Ctrl-C stops it. With
+`wizards start --background` it keeps running after the terminal closes. If it is already
+running, `wizards start` opens the running one instead of starting a second.
 
 ## Where things are
 
-| Path | Holds |
+| Path | What it holds |
 |---|---|
-| `~/.engenty/wizards` | The install. `ENGENTY_HOME` moves `~/.engenty` |
+| `~/.engenty/wizards` | Everything engenty wizards installed. `ENGENTY_HOME` moves `~/.engenty` |
 | `~/.engenty/wizards/data` | Your wizards, results and files. See [Your data](./data.md) |
 | `~/.engenty/wizards/.env` | The settings file |
-| `~/.engenty/wizards/plugins` | [Plugins](./plugins.md) of this install |
-| `~/.engenty/wizards/logs` | Logs: `install.log`, `update.log`, `runtime.log` when it runs as a service, `autostart.log` when a Mac starts it at login |
-| `~/.engenty/wizards/tools`, `runtime` | Its own Node.js, and the app |
+| `~/.engenty/wizards/plugins` | [Plugins](./plugins.md) on this computer |
+| `~/.engenty/wizards/logs` | Logs: `install.log`, `update.log`, `runtime.log` when it runs in the background, `autostart.log` when a Mac starts it at login |
+| `~/.engenty/wizards/tools`, `runtime` | Its own Node.js, and engenty wizards itself |
 | `~/.engenty/wizards/bin/wizards` | The command; `~/.local/bin/wizards` links to it |
 
 ## Settings
 
-Most settings are in the studio. The settings file `~/.engenty/wizards/.env` holds what the
-studio does not: one `NAME=value` per line. Restart after a change.
+You change most settings in the studio. The settings file `~/.engenty/wizards/.env` holds what
+the studio doesn’t: one `NAME=value` per line. Restart engenty wizards after a change.
 
-| Setting | Does | Default |
+| Setting | What it does | Default |
 |---|---|---|
 | `APP_URL` | The address you open. Links and sign-ins use it | `http://localhost:24368` |
-| `API_PORT` | The port | `24368`; if taken, the next free one up to `24387` |
-| `CHROME_PATH` | The browser for PDF and PNG exports and steps on websites: Chrome, Edge, Chromium or Brave | The first one found: on a Mac Google Chrome, Microsoft Edge, Chromium, Brave in `/Applications` or `~/Applications`; on Linux `google-chrome`, `chromium`, `chromium-browser`, `microsoft-edge` on the PATH. `wizards status` names it |
+| `API_PORT` | The port | `24368`; if it is taken, the next free one up to `24387` |
+| `CHROME_PATH` | The browser for PDF and PNG exports and steps on websites: Chrome, Edge, Chromium or Brave | The first one found: on a Mac Google Chrome, Microsoft Edge, Chromium or Brave in `/Applications` or `~/Applications`; on Linux `google-chrome`, `chromium`, `chromium-browser` or `microsoft-edge` on the PATH. `wizards status` names it |
 | `FFMPEG_PATH` | ffmpeg for MP4 videos | `ffmpeg` |
 | `OLLAMA_URL` | Where Ollama answers | `http://127.0.0.1:11434/v1` |
-| `PLUGINS_DIR` | Folders with plugins, comma-separated. Set, it replaces the default | `~/.engenty/wizards/plugins` |
-| `PLUGINS_WATCH` | `0`: plugins no longer load again when their files change | `1` |
-| `GEOCODER_URL` | Names the place of a location (street, town). Unset, a location is coordinates only and no position leaves your computer | unset |
-| `LIMIT_DEFAULT_DAILY_RUNS` | Runs a day a shared link allows unless the wizard says otherwise | `50` |
-| `LIMIT_VISITOR_RUNS_PER_HOUR` | Runs an hour one visitor can start | `6` |
-| `RESULT_TTL_DAYS` | Days the result of a run over a wizard's link is kept | `7` |
-| `STORE_TTL_DAYS` | Days what a wizard keeps for a person stays when unused | `400` |
+| `PLUGINS_DIR` | Folders with plugins, comma-separated. If you set it, it replaces the default | `~/.engenty/wizards/plugins` |
+| `PLUGINS_WATCH` | With `0`, plugins no longer load again when their files change | `1` |
+| `GEOCODER_URL` | Finds the place of a location (street, town). If it is not set, a location is only coordinates, and no position leaves your computer | not set |
+| `LIMIT_DEFAULT_DAILY_RUNS` | How many runs a day a shared link allows, unless the wizard sets its own limit | `50` |
+| `LIMIT_VISITOR_RUNS_PER_HOUR` | How many runs one visitor can start in an hour | `6` |
+| `RESULT_TTL_DAYS` | How many days the result of a run over a wizard’s link is kept | `7` |
+| `STORE_TTL_DAYS` | How many days what a wizard keeps for a person stays when nobody uses it | `400` |
 
 The OAuth clients of the built-in connectors go here too: see [Connectors](./connectors.md).
 Every setting, with what it is for, is in
 [.env.example](https://github.com/engenty/wizards/blob/main/.env.example).
 
-The command line hands the app only a short list of your terminal's variables. A key your shell
-exports for another project does not reach it: put it into the settings file, or enter it in
-the studio.
+The command passes engenty wizards only a short list of your terminal’s variables. A key your
+shell exports for another project doesn’t reach it: put it into the settings file, or enter it
+in the studio.

package/apps/runtime/dist/docs/user/connectors.md

@@ -1,13 +1,14 @@
 ---
 title: Connectors
-description: Services a wizard works in for the person who runs it — built in, from the registry, or over MCP.
-version: 0.3.2
+description: Services a wizard works in for the person who runs it – built in, from the registry or over MCP.
+version: 0.5.0
 ---
 
-Settings → Connectors lists the services the space's wizards can work in. A connector is used
-with the account of the person who runs the wizard: they connect it during a run, on a page that
-asks for it. Each space has its own connectors; in a team on engenty.ai, the owner and the admins
-add and remove them.
+Settings → Connectors lists the services the space’s wizards can work in. A wizard uses a
+connector with the account of the person who runs it: they connect their account during the run,
+on a page that asks for it. Each space has its own connectors. In a team on engenty.ai, the owner
+and the admins add and remove them. In the cloud, a space you publish from your computer shows
+its connectors without letting you change them: you change them on your computer.
 
 ## Built in
 
@@ -20,11 +21,12 @@ add and remove them.
 | HubSpot | A token they enter |
 | S3 | Keys they enter |
 
-A connector marked "not set up" needs something from the install first: the page says what.
-The OAuth services need a client of your own, entered in the install's settings file. Google is
-the exception on a local install: without a Google client of its own, Gmail, Drive, Calendar and
-Contacts connect through your engenty account, which holds the client. Connecting then asks you
-to sign in to the account first (Settings → Account).
+The OAuth services need an OAuth client of your own, which you enter in the settings file of
+engenty wizards. A built-in connector shows up in the list once it can be connected, so a service
+without its client doesn’t appear. Google is the exception on your computer: without a Google
+client of your own, Gmail, Drive, Calendar and Contacts connect through your engenty account,
+which holds the client. Connecting then asks you to sign in to the account first (Settings →
+Account).
 
 | Service | Settings |
 |---|---|
@@ -34,52 +36,55 @@ to sign in to the account first (Settings → Account).
 | GitHub | `GITHUB_OAUTH_CLIENT_ID`, `GITHUB_OAUTH_CLIENT_SECRET` |
 
 - Give each client the redirect address `<your address>/api/connect/callback`.
+  `CONNECT_REDIRECT_URL` sets a different one.
 - For Google, enable the APIs you use and add their scopes to the consent screen.
-- A connection asks only for what the wizard's actions need.
+- A connection asks only for what the wizard’s actions need.
 
-Where the settings file is: [Command line](./command-line.md#settings).
+You find the settings file under [Command line](./command-line.md#settings).
 
 ## From the registry
 
 Any other service comes from the [integrations.sh](https://integrations.sh) registry:
 
-1. Search the service, for example Notion or Stripe.
-2. "Import" takes it in, from its API description or its MCP server.
-3. Its actions appear, marked as "reads", "changes" or "deletes". Some services list them only
-   once an account is connected; "Reload actions" asks the service again.
+1. Search for the service, for example Notion or Stripe.
+2. “Import” adds it from its API description or its MCP server.
+3. Its actions appear, marked as “reads”, “changes” or “deletes”. Some services list them only
+   once an account is connected. “Reload actions” asks the service again.
 
-A service that needs an OAuth client of your own says so: remove it and import it again with
-"Own OAuth client".
+If a service needs an OAuth client of your own, it says so. Remove it and import it again with
+“Your own OAuth client”.
 
-The editor's chat does the same while it builds a wizard: ask it to work with a service, and it
-finds and imports the connector. So does an [AI app](./ai-apps.md) connected to engenty wizards.
+The editor’s chat does the same while it builds a wizard: ask it to work with a service, and it
+finds and imports the connector. An [AI app](./ai-apps.md) connected to engenty wizards can do
+this too.
 
 ## What a wizard may do
 
-A wizard names the actions it uses; without a list it uses only those that read. During a run:
+A wizard names the actions it uses. Without a list, it uses only the actions that read. During a
+run:
 
-| The action | Happens |
+| The action | What happens |
 |---|---|
-| Reads | Runs without asking, unless the wizard says to ask |
-| Changes something | The person confirms each call, or allows it for the rest of the run. A wizard can let it run without asking |
-| Deletes | The person confirms it like a change. A wizard can never let it run without asking |
+| Reads | It runs without asking, unless the wizard says to ask |
+| Changes something | The person allows each call, or chooses “Allow for the rest of this run”. A wizard can let it run without asking |
+| Deletes | The person allows it like a change. A wizard can never let it run without asking |
 
-## The person's mailbox
+## The person’s mailbox
 
-A wizard can ask for the person's mailbox and read it: search mails, read them, keep
-attachments. It never writes. The person picks how to connect:
+A wizard can ask for the person’s mailbox and read it: search emails, read them and keep
+attachments. It never writes. The person chooses how to connect:
 
-| Way | Needs from the install |
+| Way | What engenty wizards needs |
 |---|---|
 | Any mailbox over IMAP | Nothing |
-| "Gmail" button | The Google client, with the Gmail API enabled and the scope `gmail.readonly`; on a local install without one, your engenty account |
-| "Outlook" button | The Microsoft client, with the delegated permission `Mail.Read` |
+| “Gmail” button | The Google client, with the Gmail API enabled and the scope `gmail.readonly`. On your computer without one, your engenty account |
+| “Outlook” button | The Microsoft client, with the delegated permission `Mail.Read` |
 
 ## Connected systems
 
-The section also holds "Connected systems": MCP servers of your own, each with a name,
-its MCP address and, if the server wants one, an authorization header. AI steps read from and write to
-these systems only where you allow the server on the step.
+This section also holds “Connected systems”: MCP servers of your own, each with a name, its MCP
+URL and, if the server wants one, an authorization header. AI steps read from and write to these
+systems only where you allow the server on the step.
 
 This is the other direction of [AI apps](./ai-apps.md): here engenty calls other servers, there
 your AI app calls engenty.

package/apps/runtime/dist/docs/user/create-account.md

@@ -1,47 +1,52 @@
 ---
 title: Create an account
 description: Your team, its space and your wizards live in your account at engenty.ai. Sign up with an invitation code, answer four questions, build.
-version: 0.3.4
+version: 0.5.0
 ---
 
-engenty wizards is in a closed beta: a new account needs an invitation code. "Get started" on
-[engenty.ai](https://engenty.ai) takes your e-mail and puts you on the list; the code comes by
-mail as soon as a seat is free. With a code, the same step opens the sign-up.
+engenty wizards is in a closed beta, so a new account needs an invitation code. “Get started” on
+[engenty.ai](https://engenty.ai) takes your email and puts you on the list. The code comes by
+email as soon as a seat is free. Once you have a code, the same button opens the sign-up.
 
 ## Sign up
 
-1. Type the code at [account.engenty.ai/sign-up](https://account.engenty.ai/sign-up). The link
-   in the invitation mail has it filled in.
-2. Sign in with Google, GitHub, or a link by mail. There is no password.
+1. Enter the code at [account.engenty.ai/sign-up](https://account.engenty.ai/sign-up). The link
+   in the invitation email has it filled in.
+2. Sign in with Google, GitHub or a link by email. There is no password.
 3. The studio opens at [engenty.ai/studio](https://engenty.ai/studio).
 
 Your account is a **team**: it holds your credits, your spaces and, on the Team plan, your
-colleagues. It starts with credits, some of which end on a date; the account pages at
+colleagues. It starts with credits, and some of them expire on a set date. The account pages at
 [account.engenty.ai](https://account.engenty.ai) show them.
 
 ## The first visit
 
-The studio asks four things, one per page. Each but the first can be skipped and changed later.
+The studio asks four things, one per page. You can skip each one after the first and change it
+later.
 
 | Page | Asks | Goes to |
 |---|---|---|
-| Who you are | What your team is called: your company, your club, or just your name | The team's name at account.engenty.ai |
-| About you & your brand | Your website. engenty reads your name, what you do, your logo and colours from it; or you write a line about yourself | [Space → Info & brand](./space.md#info--brand) |
-| Knowledge | Documents the wizards may look things up in: price lists, your terms, an FAQ | [Space → Knowledge](./space.md#knowledge) |
-| Your space | Nothing: it explains the space that holds all of this, "Meine Wizards" | — |
+| Who you are | “What’s your team called?”: your company, your club or just your name | The team’s name at account.engenty.ai |
+| About you & your brand | “Where can the wizards read about you?”: your website. engenty reads your name, what you do, your logo and colours from it, or you write a line about yourself | [Space → Info & brand](./space.md#info--brand) |
+| Knowledge | “What should the wizards know?”: documents the wizards may look things up in, such as price lists, your terms or an FAQ | [Space → Knowledge](./space.md#knowledge) |
+| Your space | Nothing. It explains the space that holds all of this, “My wizards” (“Meine Wizards” in German) | – |
 
-Then "Build your first wizard" opens the studio's start: describe a task in a sentence, or pick
-a template. See [Build a wizard](./build-a-wizard.md).
+Then “Build your first wizard” opens the page for a new wizard: you describe a task in a
+sentence, or start from a template. See [Build a wizard](./build-a-wizard.md).
 
 ## What the cloud does
 
-- Wizards built here run behind a link that works day and night, on the team's credits.
-- Share links, the tag for your website, QR codes and the channels of [Test and share](./test-and-share.md) work as on an install.
-- What the wizards think with is the team's: [Models and account](./models.md).
+- Wizards you build here run behind a link that works day and night, on the team’s credits.
+- Share links, the tag for your website, QR codes and the channels of [Test and share](./test-and-share.md) work as they do on your computer.
+- The team decides what the wizards run on: see [Models and account](./models.md).
 
 ## Also on your computer
 
-The same account works on your own computer: [install](./install.md) engenty wizards there and
-sign in during the setup. It thinks with your Claude, ChatGPT, Gemini or Cursor subscription,
-reads your local files and browses for you; what you publish there runs in the cloud too, behind
-the same links. "Also on your computer" on the studio's start page mails you the command.
+The same account works on your own computer: you [install](./install.md) engenty wizards there
+and sign in during the setup. It then runs on your Claude, ChatGPT, Gemini or Cursor
+subscription, reads your files and browses the web for you. What you publish there runs in the
+cloud too, behind the same links. In the cloud studio that space is marked “Edited on your
+computer.” and you only look at it there: you change it on your computer.
+
+On the studio’s start page, the “Also on your computer” card has “Email me the command”, which
+sends you the install command.