nodetool-ai · georgi · Sep 11, 2026 · Sep 10, 2026 · Sep 10, 2026 · Sep 10, 2026
diff --git a/docs/BRAND.md b/docs/BRAND.md
@@ -22,7 +22,7 @@ change.
 
 - **Mission.** Give creators and developers control over multi-modal AI
   orchestration without platform lock-in, credit markups, or lost context.
-- **Primary tagline.** Open-source creative AI workspace.
+- **Primary tagline.** Open-source agent-first creative workspace.
 - **Intro.** Create and edit images, video, audio, and text with agents that
   work alongside you. Let them build and revise workflows, then inspect and
   edit the results yourself. Your project keeps the brief, assets, and edits

diff --git a/docs/SEO_STRATEGY.md b/docs/SEO_STRATEGY.md
@@ -325,7 +325,7 @@ Five gaps stand out:
   See §4.0.
 
 The existing meta setup is solid: `layout.tsx` already ships title/description/OG/Twitter tags and
-a keyword list (creative AI workspace, BYOK AI canvas, ComfyUI alternative, Weavy alternative,
+a keyword list (agent-first creative workspace, BYOK AI canvas, ComfyUI alternative, Weavy alternative,
 node-based AI canvas). `robots.txt` and `sitemap.ts` both exist. The problem is page count and
 content depth, not technical hygiene.
 

diff --git a/docs/comparisons.md b/docs/comparisons.md
@@ -4,7 +4,7 @@ title: "Why NodeTool: Comparisons vs ComfyUI, n8n & More"
 description: "Why NodeTool exists, what makes it unique, and how it compares to ComfyUI, Dify, Flowise, Langflow, n8n, and Figma Weave (formerly Weavy)."
 ---
 
-> NodeTool is the open-source creative AI workspace. It combines every major model, lets you use your own API keys, and puts everything on one simple canvas.
+> NodeTool is the open-source agent-first creative workspace. It combines every major model, lets you use your own API keys, and puts everything on one simple canvas.
 
 Just tell the built-in AI agent what you want to make. It will automatically build a workflow for you using image, video, audio, and text models working together. After it's built, you can easily change it yourself. You can use your own API keys, or run everything locally on your computer. It is completely open source (AGPL-3.0).
 
@@ -50,7 +50,7 @@ Read our full guides on how NodeTool compares to other tools:
 
 | Feature                        | NodeTool                                        | Figma Weave (formerly Weavy) | ComfyUI                                  |
 | ------------------------------ | ----------------------------------------------- | ---------------------------- | ---------------------------------------- |
-| **Category**                   | Open creative AI workspace                      | Closed SaaS creative canvas  | Image-focused node editor                |
+| **Category**                   | Agent-first creative workspace                      | Closed SaaS creative canvas  | Image-focused node editor                |
 | **License**                    | AGPL-3.0 (open source)                          | Proprietary SaaS             | GPL-3.0 (open source)                    |
 | **Runs on your machine**       | ✅ Mac, Windows, Linux desktop                  | ❌ Browser-only, hosted      | ✅ Local-first                           |
 | **Bring your own keys (BYOK)** | ✅ Use your own API keys for all providers      | ❌ Credits only, extra fees  | ⚠️ Hard to use cloud APIs                |

diff --git a/docs/global-chat.md b/docs/global-chat.md
@@ -60,10 +60,17 @@ The same composer generates more than text. Click the mode chip to switch betwee
 | **Edit Images** | Image-to-image edits on a dropped image |
 | **Generate Videos** | Text-to-video |
 | **Animate Image** | Turn a still image into a clip |
+| **Reference to Video** | One clip from several attached images and videos — a character plus a garment, a product plus a location, a clip whose motion the new shot follows |
 | **Generate Speech** | Text-to-speech with a voice picker |
 
 Each mode swaps in its own controls — resolution, aspect ratio, duration, voice — and attaches them to the message so the server routes to the right provider call.
 
+Reference to Video takes every image and video on the message, plus the
+reference image of any `@`-mentioned entity, so the prompt describes the action
+and the camera rather than the subjects. Its audio chip chooses between what the
+model scores and the first reference video's own track; only some models accept
+the second, and one that does not rejects the request.
+
 ---
 
 ## Mentions: @ for assets and entities

diff --git a/docs/index.md b/docs/index.md
@@ -1,11 +1,11 @@
 ---
 layout: home
-description: "Open-source creative AI workspace. Create images, video, audio, and text with agents, then inspect and edit their work. Keep your project context together."
+description: "Open-source agent-first creative workspace. Create images, video, audio, and text with agents, then inspect and edit their work. Keep your project context together."
 ---
 
 <section class="home-hero">
   <p class="eyebrow">NodeTool documentation</p>
-  <h1>Open-source creative AI workspace</h1>
+  <h1>Open-source agent-first creative workspace</h1>
   <p class="lead">
     Create and edit images, video, audio, and text with agents that work alongside
     you. Let them build and revise workflows, then inspect and edit the results