Dembrane · spashii · Jul 24, 2026 · Jul 24, 2026 · Jul 24, 2026 · Jul 24, 2026
diff --git a/.github/workflows/prod-deploy-docs.yml b/.github/workflows/prod-deploy-docs.yml
@@ -0,0 +1,58 @@
+# Publishes the user documentation site (docs/) to docs.dembrane.com when a
+# release tag is cut — the same gitops rhythm as the product: push to main
+# deploys docs.echo-next.dembrane.com (dev-deploy-docs.yml), a v*.*.* tag
+# deploys production.
+#
+# Built with the separately-tracked folder2website tool (same build as the
+# echo-next docs, different base URL). Deploys the static output to the
+# Vercel project that owns docs.dembrane.com via the Build Output API, so
+# no framework/build settings on the project can interfere.
+#
+# Required secrets: VERCEL_TOKEN, VERCEL_ORG_ID, VERCEL_PROJECT_ID_DOCS.
+name: prod-deploy-docs
+
+env:
+  VERCEL_ORG_ID: ${{ secrets.VERCEL_ORG_ID }}
+  VERCEL_PROJECT_ID: ${{ secrets.VERCEL_PROJECT_ID_DOCS }}
+
+on:
+  workflow_dispatch:
+  push:
+    tags: [ "v*.*.*" ]
+
+concurrency:
+  group: prod-deploy-docs-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  prod-deploy-docs:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          # folder2website reads git history for page metadata
+          fetch-depth: 0
+
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@v2
+
+      - name: Build docs site
+        run: bunx github:spashii/folder2website#main docs --out _docs-site --base-url https://docs.dembrane.com
+
+      - name: Install Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 22
+
+      - name: Install Vercel CLI
+        run: npm install --global vercel@latest
+
+      - name: Stage prebuilt static output
+        run: |
+          mkdir -p .vercel/output/static
+          cp -R _docs-site/. .vercel/output/static/
+          echo '{"version": 3}' > .vercel/output/config.json
+
+      - name: Deploy to Vercel (docs.dembrane.com)
+        run: vercel deploy --prebuilt --prod --token=${{ secrets.VERCEL_TOKEN }}
diff --git a/docs/_authoring/FACTS.md b/docs/_authoring/FACTS.md
@@ -244,9 +244,11 @@ Auth: `/login /register /check-your-email /verify-email /password-reset /request
   conversations; auto-select vs manual context; sources; templates (built-in + user templates);
   standard mode + *agentic mode* (tool use, separate agent service). Free-tier chat gate.
   `ENABLE_AGENTIC_CHAT = byEnv({production:false}, true)` - agentic OFF in production. Where
-  it's on, `/chats/new` is the *Ask home*: chat list + a question bar that filters chats and
-  creates one on Enter, a `Templates` insert menu, starter chips, and a
-  "Prefer the old chat? Start a Specific Details chat" escape hatch. Agentic runs show live
+  it's on, `/chats/new` is the *Ask home*: chat list + one question bar (headed "Where would
+  you like to start?") that filters chats and creates one on Enter, a `Templates` insert menu,
+  and a "Prefer the old chat? Start a Specific Details chat" escape hatch. The old Overview
+  mode is retired - unreachable in the new experience; Specific Details remains as the
+  classic fallback. Agentic runs show live
   progress, a Send↔Stop morph, named citation links ("{name}'s conversation" →
   `#chunk-` deep links), and documentation citations via a chooser modal
   ("Open documentation" / "Open chat documentation"). Agent tools (echo/agent, 20): inventory/

diff --git a/docs/building/index.md b/docs/building/index.md
@@ -6,9 +6,10 @@ audience: all
 
 # Building now
 
-These pages describe features that are *being built* - they are not available yet, not even
-on [dembrane next](../features/dembrane-next.md). Each one is written as a user story before
-the first line of code, and the build isn't done until the story works end to end.
+These pages describe features that are *being built* - most are not available yet, not even
+on [dembrane next](../features/dembrane-next.md); where an early piece has reached beta, the
+page says so. Each one is written as a user story before the first line of code, and the
+build isn't done until the story works end to end.
 
 Why publish them? Three reasons:
 
@@ -21,8 +22,11 @@ Why publish them? Three reasons:
 
 ## In progress
 
-- [The SMART loop](./smart-loop.md) - a dynamic canvas the assistant regenerates through
-  your session: live frames and answers on a rhythm, versions kept, improved by chat.
+- [The SMART loop](./smart-loop.md) - a living canvas the assistant regenerates through
+  your session: live frames and answers on a rhythm, versions kept, improved by chat. The
+  canvas is now in *beta* on dembrane next - off by default, and a host opts a project in
+  with the *Living canvas* switch under *Experimental* in project settings. Not in
+  production yet.
 
 ## Related
 

diff --git a/docs/building/smart-loop.md b/docs/building/smart-loop.md
@@ -1,15 +1,20 @@
 ---
 title: The SMART loop (building now)
-description: A user story for the dynamic canvas - a live, versioned page the assistant regenerates every few minutes during a session, improved by chat.
+description: A user story for the living canvas - a live, versioned page the assistant regenerates every few minutes during a session, improved by chat. The canvas is now in beta on dembrane next.
 audience: all
 ---
 
 # The SMART loop
 
 > [!IMPORTANT]
-> This feature is *being built*. Nothing on this page is available yet - not even on
-> [dembrane next](../features/dembrane-next.md). It's published so you can see what's
-> coming and tell us early if the story misses your reality.
+> The living canvas at the heart of this story is now in *beta* on
+> [dembrane next](../features/dembrane-next.md). It's off by default for every project: a
+> host opts a project in with the *Living canvas* switch (marked *Beta*) under
+> *Experimental* on the General page of project settings. With the switch off there are no
+> canvas pages, no canvas abilities in chat, and no background regeneration. The canvas is
+> not in production yet; making it production-ready is a separate, upcoming effort. The
+> rest of this story is still being built. It's published so you can see what's coming and
+> tell us early if it misses your reality.
 
 The idea in one line: your sessions produce living artifacts, and those artifacts feed back
 into the session while it's still running. The story below is the acceptance test - the
@@ -184,4 +189,4 @@ moves. Her next wall starts from everything everyone learned.
 - [Building now](./index.md) - everything else in progress.
 - [Chat & Ask](../features/chat-and-ask.md) - the assistant this builds on.
 - [Reports](../features/reports.md) - the shape artifacts borrow.
-- [dembrane next](../features/dembrane-next.md) - where this lands first when it ships.
+- [dembrane next](../features/dembrane-next.md) - where the canvas beta is live today.
diff --git a/docs/features/account-and-security.md b/docs/features/account-and-security.md
@@ -70,12 +70,12 @@ The wider picture of who owns the data is in
 
 ## What the assistant remembers about you
 
-*[dembrane next only](./dembrane-next.md).* If you use [Ask's agentic mode](./chat-and-ask.md),
+*[dembrane next only](./dembrane-next.md).* If you use [Ask](./chat-and-ask.md),
 the assistant can save notes about how you like to work - saved during your chats, read back at
 the start of the next one. *Settings → Assistant* shows every note it keeps about you; only you
 see these, and *Remove* makes it forget one for every future chat. The assistant writes the
 notes; you can't edit them, only remove them. (Project and workspace notes have their own
-surfaces - see [chat & Ask](./chat-and-ask.md#agentic-mode-in-more-detail).)
+surfaces - see [chat & Ask](./chat-and-ask.md#more-than-analysis).)
 
 ## Your access at a glance
 

diff --git a/docs/features/chat-and-ask.md b/docs/features/chat-and-ask.md
@@ -1,6 +1,6 @@
 ---
 title: Chat & Ask
-description: Ask questions across your conversations and get answers with cited sources, using built-in or your own language model.
+description: Ask questions across your conversations and get answers with cited sources - one assistant that searches, reads, and shows its work.
 audience: host
 ---
 
@@ -18,37 +18,40 @@ Treat it as a deep-dive, not a one-shot search:
 
 It's best for comparing viewpoints, finding quotes, and testing a hunch.
 
-## Modes
+## One question bar
 
-Click *Ask question* in a project, then choose a *mode* - it sets how dembrane reads your
-conversations:
+> [!NOTE]
+> The new Ask experience is live on *[dembrane next](./dembrane-next.md)* and reaches
+> production with the next release.
 
-- *Overview* (beta) - reads across all conversations in the project for themes and patterns.
-  Best for open-ended exploration; it paraphrases rather than quoting.
-- *Specific Details* - you pick the conversations (or select all), optionally filtering by
-  [tag](./conversations-and-transcripts.md#tags), and answers come back with exact quotes and
-  citations. Best when you want precision: one session, one cohort, exact wording. If you're
-  already viewing one conversation when you start, it's selected for you.
-- *Agentic* (*[dembrane next only](./dembrane-next.md)*) - an assistant that works in steps:
-  it searches conversations, reads transcripts, and chains what it finds to answer harder
-  questions. A preview feature, not in production yet - see below for what it adds.
+Click *Ask question* in a project and Ask opens as a home for all your chats, with one
+input: *Where would you like to start?* Press Enter and your question becomes a new chat;
+typing in the same bar also filters your earlier chats, so it finds an old thread as easily
+as it starts a new one. A *Templates* menu inserts a saved prompt.
 
-Specific Details is the usual move once a project gets large and you want precision over breadth.
+The assistant works in steps: it searches conversations, reads
+[transcripts](./conversations-and-transcripts.md), and chains what it finds to answer harder
+questions (*"find every conversation where someone disagreed with the proposal and tell me
+why"*). While it works you see its progress step by step, and a *Stop* control replaces
+*Send* so you can halt a run that's going the wrong way. Answers cite their sources by name -
+*"Maria's conversation"*, *"Maria's transcript excerpt"* - and each link jumps to the exact
+place in the transcript.
 
-## Agentic mode, in more detail
+## The classic chat: Specific Details
 
-*[dembrane next only](./dembrane-next.md).* On dembrane next, *Ask* opens as a home for all
-your chats: your chat list with a question bar on top. Typing filters your earlier chats;
-pressing Enter asks the question as a new chat. A *Templates* menu inserts a saved prompt, and
-if you'd rather pick conversations yourself there's a one-click way to start a classic
-*Specific Details* chat instead.
+Prefer to pick the conversations yourself? One click on *Prefer the old chat? Start a
+Specific Details chat* starts a classic chat: you choose the conversations (or select all),
+optionally filtering by [tag](./conversations-and-transcripts.md#tags), and answers come
+back in one pass with exact quotes and citations. Best when every answer should come from
+the same fixed set: one session, one cohort, exact wording. If you're already viewing one
+conversation when you start, it's selected for you.
 
-While the assistant works you see its progress step by step, and a *Stop* control replaces
-*Send* so you can halt a run that's going the wrong way. Answers cite their sources by name -
-*"Maria's conversation"*, *"Maria's transcript excerpt"* - and each link jumps to the exact
-place in the [transcript](./conversations-and-transcripts.md).
+The old *Overview* mode has been retired: its job - themes and patterns across all
+conversations - is covered by simply asking the assistant.
+
+## More than analysis
 
-Beyond answering questions, it can:
+Beyond answering questions, the assistant can:
 
 - *Check what's live* - ask *"is anyone recording right now?"* and it reads the same live
   status as the [monitor](./recording.md#watch-it-live-the-monitor).
@@ -126,5 +129,6 @@ Most teams use all three: explore with Ask, see the landscape in the library, pu
 - [Tiers & billing](./tiers-and-billing.md) - Free limits, Innovator BYO, Changemaker+ built-in analysis.
 - [MCP & bring-your-own-LLM](./mcp-and-bring-your-own-llm.md) - connect your own model on
   Innovator (coming soon).
-- [dembrane next](./dembrane-next.md) - preview features like agentic mode, not in production yet.
+- [dembrane next](./dembrane-next.md) - preview features like the new Ask experience, not in
+  production yet.
 - For a host's walkthrough, see [chat & Ask for hosts](../users/host/chat-and-ask.md).
diff --git a/docs/features/dembrane-next.md b/docs/features/dembrane-next.md
@@ -23,9 +23,10 @@ now, so you always know whether something you read about is actually available t
 
 | Feature | What it is | Where |
 |---|---|---|
-| *Agentic mode* (in Ask) | An assistant that works in steps - searching, reading transcripts, checking live status, answering from the docs, and proposing settings changes for your review. Ask opens as a home for your chats, with named citations and a Stop control. | [Chat & Ask → Agentic mode](./chat-and-ask.md#agentic-mode-in-more-detail) |
+| *The new Ask experience* | Ask opens as a home for your chats with one question bar, and the assistant works in steps - searching, reading transcripts, checking live status, answering from the docs, and proposing settings changes for your review - with named citations and a Stop control. The classic Specific Details chat stays one click away. | [Chat & Ask](./chat-and-ask.md#one-question-bar) |
 | *Assistant memory & context* | The assistant saves notes (you view and remove them in user, project, and workspace settings) and takes standing guidance from a workspace-wide *assistant context*. | [Account & security](./account-and-security.md#what-the-assistant-remembers-about-you), [managing your workspace](../users/host/managing-your-workspace.md#give-the-assistant-standing-context) |
 | *The Monitor* | A live view of a session: the participant flow from QR scan to recording, live recordings with audio warnings, and transcription progress. | [Recording → Watch it live](./recording.md#watch-it-live-the-monitor) |
+| *The living canvas* (beta) | A live page the assistant builds and regenerates during a session. Off by default for every project: a host opts a project in with the *Living canvas* switch under *Experimental* in project settings. | [The SMART loop](../building/smart-loop.md) |
 
 If the table is short, that's a good sign: most of dembrane is the same on next and
 production. Only genuinely in-progress features live here.

diff --git a/docs/users/host/account-and-settings.md b/docs/users/host/account-and-settings.md
@@ -54,7 +54,7 @@ save repeating yourself and keep projects consistent for compliance. See
 ## Assistant
 
 *[dembrane next only](../../features/dembrane-next.md).* If you use
-[Ask's agentic mode](./chat-and-ask.md#agentic-mode), the assistant can save notes about how
+[Ask](./chat-and-ask.md#more-than-analysis), the assistant can save notes about how
 you like to work. The *Assistant* section shows everything it remembers about you - only you
 see these notes - and *Remove* makes it forget one for good. It writes the notes during your
 chats; you can't edit them here, only remove them.