hongyi-chen · Oct 5, 2026 · Oct 5, 2026 · Oct 5, 2026 · Oct 5, 2026 · Oct 5, 2026
diff --git a/.agents/references/terminology.md b/.agents/references/terminology.md
@@ -14,9 +14,6 @@ For the summary of the most critical terms (core features, Automation Platform t
 - **Agent Mode** — The mode where Warp interprets your input as a request to an Agent (not a shell command).
   *Usage note:* Not "agent mode" or "Agent-mode."
 
-- **Auto-detection Mode** — The mode where Warp automatically detects whether input is a command or a prompt.
-  *Usage note:* Useful in onboarding and "how it works" content.
-
 - **Block** / **Blocks** — Warp's structured unit of terminal output and history.
   *Usage note:* Use for navigation, sharing, and "how Warp organizes your terminal."
 
@@ -26,11 +23,8 @@ For the summary of the most critical terms (core features, Automation Platform t
 - **Prompt** — A natural-language request you give to an Agent.
   *Usage note:* Keep distinct from "command."
 
-- **Terminal Mode** — The mode where Warp interprets your input as shell commands.
-  *Usage note:* Use when contrasting with Agent Mode.
-
-- **Universal Input** — Warp's main input surface that supports both commands and Agent prompts.
-  *Usage note:* Use as the name of the feature, not "input box."
+- **terminal mode** — The mode where Warp interprets your input as shell commands.
+  *Usage note:* Use lowercase when contrasting with Agent Mode.
 
 - **Warp** — The agentic development environment for professional developers, built around a modern terminal and AI agents.
   *Usage note:* Use "Warp" as the product name. Add "AI terminal" only when you need the positioning shorthand. Do not use "Warp Terminal" unless specifically distinguishing from the Automation Platform.

diff --git a/.agents/skills/style_lint/style_lint.py b/.agents/skills/style_lint/style_lint.py
@@ -35,10 +35,10 @@
 # Feature names that are correctly Title Case (exceptions to sentence-case rule)
 PROPER_FEATURE_NAMES = {
     "Admin Panel", "Agent Management Panel", "Agent Mode", "Agent Profiles",
-    "Auto-detection Mode", "Cloud Agents",
+    "Cloud Agents",
     "Codebase Context", "Code Review", "Command Palette", "Global Rules",
     "Oz CLI", "Oz Platform", "Project Rules",
-    "Slash Commands", "Terminal Mode", "Universal Input", "Warp Drive",
+    "Slash Commands", "Warp Drive",
     "Warp Platform", "Automation Platform", "Warp Factories", "Factory MCP",
     "Computer Use", "Full Terminal Use", "Zero Data Retention", "Single Sign-On",
     "Blocks", "Block", "Tab Configs", "Tab Config",

diff --git a/AGENTS.md b/AGENTS.md
@@ -340,7 +340,7 @@ Captions orient the reader — they identify what the image shows so the reader
 - ✅ `<figcaption>Codebase indexing settings.</figcaption>`
 - ❌ `<figcaption>Codebase indexing settings in Warp. Easily track sync status and manage which folders are indexed for AI-powered context and suggestions.</figcaption>` (marketing language, too long)
 - ❌ `<figcaption>Click the toast to jump to the agent's session.</figcaption>` (procedural — belongs in body text)
-- ❌ `<figcaption>Universal Input's contextual input chips, from left to right: conversation management, node version, active directory, Git and code diffs, and 2 attached images.</figcaption>` (exhaustive list)
+- ❌ `<figcaption>The input toolbelt, from left to right: model selector, voice input, image attachments, and conversation controls.</figcaption>` (exhaustive list)
 
 ### Links, embeds, and cross-references
 - Use descriptive link text that explains what users will find. The anchor text should describe the destination or task, not the action of clicking.

diff --git a/public/assets/agent-platform/recreate-universal-input.gif b/public/assets/agent-platform/recreate-universal-input.gif
diff --git a/src/assets/agent-platform/classic-input-follow-up.png b/src/assets/agent-platform/classic-input-follow-up.png
diff --git a/src/assets/agent-platform/classic-input-new-convo.png b/src/assets/agent-platform/classic-input-new-convo.png
diff --git a/src/assets/agent-platform/follow-up-universal-input.png b/src/assets/agent-platform/follow-up-universal-input.png
diff --git a/src/assets/agent-platform/image-as-context-classic.png b/src/assets/agent-platform/image-as-context-classic.png
diff --git a/src/assets/agent-platform/image-as-context-universal.png b/src/assets/agent-platform/image-as-context-universal.png
diff --git a/src/assets/agent-platform/universal-input-new-convo.png b/src/assets/agent-platform/universal-input-new-convo.png
diff --git a/src/assets/terminal/active-directory-chip.png b/src/assets/terminal/active-directory-chip.png
diff --git a/src/assets/terminal/agent-mode-locked-universal-input.png b/src/assets/terminal/agent-mode-locked-universal-input.png
diff --git a/src/assets/terminal/agent-mode-suggestion-1.png b/src/assets/terminal/agent-mode-suggestion-1.png
diff --git a/src/assets/terminal/auto-detection-agent-mode-1.png b/src/assets/terminal/auto-detection-agent-mode-1.png
diff --git a/src/assets/terminal/auto-detection-off-agent-mode.png b/src/assets/terminal/auto-detection-off-agent-mode.png
diff --git a/src/assets/terminal/auto-detection-off-terminal-mode.png b/src/assets/terminal/auto-detection-off-terminal-mode.png
diff --git a/src/assets/terminal/auto-detection-terminal-mode.png b/src/assets/terminal/auto-detection-terminal-mode.png
diff --git a/src/assets/terminal/banner_for_auto-detection_first_experience.png b/src/assets/terminal/banner_for_auto-detection_first_experience.png
diff --git a/src/assets/terminal/conversation-management-chip-universal-input.png b/src/assets/terminal/conversation-management-chip-universal-input.png
diff --git a/src/assets/terminal/git-branch-chip.png b/src/assets/terminal/git-branch-chip.png
diff --git a/src/assets/terminal/images-as-context-chip.png b/src/assets/terminal/images-as-context-chip.png
diff --git a/src/assets/terminal/input-toolbar.png b/src/assets/terminal/input-toolbar.png
diff --git a/src/assets/terminal/node-version-chip.png b/src/assets/terminal/node-version-chip.png
diff --git a/src/assets/terminal/undo_my_git_commit.png b/src/assets/terminal/undo_my_git_commit.png
diff --git a/src/assets/terminal/universal-input-header.png b/src/assets/terminal/universal-input-header.png
diff --git a/src/assets/terminal/universal-input-terminal-mode.png b/src/assets/terminal/universal-input-terminal-mode.png
diff --git a/src/assets/terminal/universal-input.png b/src/assets/terminal/universal-input.png
diff --git a/src/assets/terminal/using-agents-universal-input.png b/src/assets/terminal/using-agents-universal-input.png
diff --git a/src/assets/terminal/warp-ai-permissions.png b/src/assets/terminal/warp-ai-permissions.png
diff --git a/src/assets/terminal/warp-ai-viewing-commands.png b/src/assets/terminal/warp-ai-viewing-commands.png
diff --git a/src/assets/terminal/zero-state-universal-input.png b/src/assets/terminal/zero-state-universal-input.png
diff --git a/src/content/docs/agents/capabilities/rules.mdx b/src/content/docs/agents/capabilities/rules.mdx
@@ -101,13 +101,13 @@ This ensures the most specific, project-relevant rules take priority over broade
   Add, edit, or delete any number of rules. Each rule can include:
   * Name (optional)
   * Description (what the rule does and when to apply it)
-* **From the Slash Commands menu:** `/add-rule` in Auto or Agent input modes to create a new Global Rule (automatically opens the Warp Drive Rules pane).
+* **From the Slash Commands menu:** Use `/add-rule` to create a new Global Rule (automatically opens the Warp Drive Rules pane).
 
 <VideoEmbed url="https://www.loom.com/share/3a49462c01e149cf9c040130cebe1184?hideEmbedTopBar=true&hide_owner=true&hide_share=true&hide_title=true" title="Rules Demo (legacy) with just Global Rules. Project rules can also be found there." />
 
 #### Project Rules
 
-* **When in a directory, set up Project Rules with a slash command:** Use `/init` in Auto-Detection or Agent Mode to:
+* **When in a directory, set up Project Rules with a slash command:** Use `/init` to:
   * Begin indexing your codebase or display indexing status
   * Generate an `AGENTS.md` file with initial context, or
   * Link an existing Rules file to `AGENTS.md`

diff --git a/src/content/docs/agents/capabilities/slash-commands.mdx b/src/content/docs/agents/capabilities/slash-commands.mdx
@@ -1,11 +1,11 @@
 ---
 title: Slash Commands
 description: >-
-  Use Slash Commands in Agent Mode or Auto-Detection Mode to quickly run
+  Use Slash Commands in terminal mode or Agent Mode to quickly run
   built-in actions or saved prompts without leaving the input field.
 ---
 
-Slash Commands are quick actions and saved prompts you can invoke by typing `/` in Agent Mode or Auto-Detection Mode. They provide instant access to built-in actions like starting conversations, creating environments, switching models, opening static flows, and running saved prompts from Warp Drive.
+Slash Commands are quick actions and saved prompts you can invoke by typing `/` in terminal mode or Agent Mode. They provide instant access to built-in actions like starting conversations, creating environments, switching models, opening static flows, and running saved prompts from Warp Drive.
 
 <figure>
 ![Slash Commands menu](../../../../assets/agent-platform/slash-commands-menu.png)
@@ -39,7 +39,7 @@ In addition to static commands, the menu also shows [Agent Prompts](/knowledge-a
 ### Tips
 
 * **Context-aware:** Many Slash Commands use your current working directory or file selection as context.
-* **Quick access:** Use `/` from anywhere in Agent Mode or Auto-Detection Mode to avoid navigating through menus.
+* **Quick access:** Use `/` from terminal mode or Agent Mode to avoid navigating through menus.
 
 ### Example of using a Slash Command
 

diff --git a/src/content/docs/agents/local-agents/agent-context/images-as-context.mdx b/src/content/docs/agents/local-agents/agent-context/images-as-context.mdx
@@ -13,18 +13,7 @@ To provide visual context, you can attach images directly to an agent prompt. Th
 
 You can attach images in the following ways:
 
-* Using the **image upload button** found on the toolbelt (either on the bottom left or right), depending on which input mode you're using:
-
-<figure>
-![Attaching 5 images on the new "Universal" input (bottom left toolbelt)](../../../../../assets/agent-platform/image-as-context-universal.png)
-<figcaption>Attaching images in Universal Input.</figcaption>
-</figure>
-
-<figure>
-![Attaching 4 images on the "Classic" input (bottom right)](../../../../../assets/agent-platform/image-as-context-classic.png)
-<figcaption>Attaching images in Classic Input.</figcaption>
-</figure>
-
+* Select the **image upload button** in the agent input.
 * Copy and paste images directly (e.g. right-click an image > "Copy image" or copy from a file manager) into Warp.
 * Drag and drop images, such as from a file manager or screenshot utility.
 

diff --git a/src/content/docs/agents/local-agents/agent-context/using-to-add-context.mdx b/src/content/docs/agents/local-agents/agent-context/using-to-add-context.mdx
@@ -13,7 +13,7 @@ Use the @ symbol in agent prompts to reference files, folders, code symbols, War
 You can attach specific files, folders, code symbols, Warp Drive objects, and blocks from other sessions as context to a prompt using the @ symbol. When you’re inside a **Git repository**, typing @ opens a context menu that allows you to search for and select files or directories to include.
 
 :::note
-Attaching context with @ works in **both natural language mode** (when interacting with Agents) and **classic terminal commands** for referencing file paths.
+Attaching context with @ works in **Agent Mode** and in **terminal mode** when referencing file paths.
 :::
 
 **Note**: the search in the @-context menu is always relative to the root of the Git repository, even when you're working in a subdirectory. This means you can reference _any_ file or folder tracked in the repo, regardless of the current working directory.

diff --git a/src/content/docs/agents/local-agents/interacting-with-agents/index.mdx b/src/content/docs/agents/local-agents/interacting-with-agents/index.mdx
@@ -26,29 +26,15 @@ To access conversations across devices, share them with teammates, or restore pa
 
 ### Staying in a conversation (follow-ups)
 
-By default, if you ask an AI query immediately after interacting in Agent Mode, your query is sent as a **follow-up** to the current conversation.
-
-* In **Classic Input**, you'll see both the pink highlight bar on the left side of the block and a bent follow-up arrow (↳) next to your input. The conversation input chip also shows which conversation you are in.
-* In **Terminal and Agent modes** (the default), the conversation view provides a dedicated space for multi-turn interactions. The conversation panel shows which conversation you are in.
+By default, if you ask an AI query immediately after interacting in Agent Mode, your query is sent as a **follow-up** to the current conversation. The conversation view provides a dedicated space for multi-turn interactions, and the conversation panel shows which conversation you are in.
 
 **To follow-up on a previous conversation:**
 
 * Simply continue prompting the agent if you are already in an active conversation.
 * Open the **Conversations menu** (`⌘+Y` on macOS, `Ctrl+Shift+Y` on Windows/Linux), select a conversation, and then enter your query.
-* Alternatively, click the pink conversation chip in the input field to resume.
 
 You don't have to wait for the agent to finish before lining up your next prompt. With [prompt queueing](/agents/local-agents/interacting-with-agents/prompt-queueing/), you can queue follow-ups while the agent is still responding and have them send automatically in order.
 
-<figure>
-![Continuing an Agent conversation in Classic Input (with indicator)](../../../../../assets/agent-platform/classic-input-follow-up.png)
-<figcaption>Continuing an agent conversation in Classic Input.</figcaption>
-</figure>
-
-<figure>
-![Continuing an Agent conversation in agent conversation view](../../../../../assets/agent-platform/follow-up-universal-input.png)
-<figcaption>Continuing an agent conversation in the conversation view.</figcaption>
-</figure>
-
 #### Agent tips in the input
 
 While the Warp Agent is thinking and processing your request, Warp may surface short tips with helpful workflows and ways to use Warp. These tips appear under the Warping indicator.
@@ -72,47 +58,29 @@ The "New Conversation" item disappears once you start searching for an actual co
 
 ### Starting a new conversation
 
-Warp automatically creates a new conversation in a few situations. For example, if you ask an AI query after running a shell command or if three hours pass without activity, Agent Mode will start a fresh conversation.
-
-Visual indicators differ slightly depending on input mode:
-
-* In **Classic Input,** a new conversation begins when there is no follow-up arrow (↳) next to your input.
-* In **Terminal and Agent modes**, starting a new conversation opens a fresh conversation view. Use the conversation panel to see all active and past conversations.
+Warp automatically creates a new conversation in a few situations. For example, if you ask an AI query after running a shell command or if three hours pass without activity, Agent Mode will start a fresh conversation. Starting a new conversation opens a fresh conversation view. Use the conversation panel to see all active and past conversations.
 
 <Tabs>
   <TabItem label="macOS">
     You can also start a new conversation manually at any time:
 
-    * In **Classic Input**, press `⌘+I` or press `Backspace` while in follow-up mode.
-    * In **Terminal and Agent modes**, press `⌘+Enter` to start a new conversation, or use the `/new` slash command.
+    * Press `⌘+Enter` to start a new conversation, or use the `/new` slash command.
     * Open the **Conversations Menu** using `⌘+Y` and select "New Conversation".
   </TabItem>
   <TabItem label="Windows">
     You can also start a new conversation manually at any time:
 
-    * In **Classic Input**, press `Ctrl+I` or press `Backspace` while in follow-up mode.
-    * In **Terminal and Agent modes**, press `Ctrl+Shift+Enter` to start a new conversation, or use the `/new` slash command.
+    * Press `Ctrl+Shift+Enter` to start a new conversation, or use the `/new` slash command.
     * Open the **Conversations Menu** using `Ctrl+Shift+Y` and select "New Conversation".
   </TabItem>
   <TabItem label="Linux">
     You can also start a new conversation manually at any time:
 
-    * In **Classic Input**, press `Ctrl+I` or press `Backspace` while in follow-up mode.
-    * In **Terminal and Agent modes**, press `Ctrl+Shift+Enter` to start a new conversation, or use the `/new` slash command.
+    * Press `Ctrl+Shift+Enter` to start a new conversation, or use the `/new` slash command.
     * Open the **Conversations Menu** using `Ctrl+Shift+Y` and select "New Conversation".
   </TabItem>
 </Tabs>
 
-<figure>
-![Starting a new Conversation in Classic Input](../../../../../assets/agent-platform/classic-input-new-convo.png)
-<figcaption>Starting a new Conversation in Classic Input.</figcaption>
-</figure>
-
-<figure>
-![Starting a new Agent Conversation in agent conversation view](../../../../../assets/agent-platform/universal-input-new-convo.png)
-<figcaption>Starting a new Agent Conversation in agent conversation view.</figcaption>
-</figure>
-
 ## Context window management
 
 Every conversation with an agent consumes tokens stored in a **context window**. The context window (sometimes called _context length_) is the amount of text (measured in tokens) that a large language model (LLM) can process at one time. **The size of the context window depends on the model you are using.**

diff --git a/...t/docs/agents/local-agents/interacting-with-agents/terminal-and-agent-modes.mdx b/...t/docs/agents/local-agents/interacting-with-agents/terminal-and-agent-modes.mdx
@@ -83,8 +83,6 @@ The shortcuts shown on this page use macOS keybindings. For Windows and Linux sh
 
 Agent controls appear only when you're in a conversation, keeping your terminal clean otherwise.
 
-In the previous UI, agent controls were always present. With Terminal and Agent modes, these controls are hidden by default and appear **once you enter an agent conversation.**
-
 :::note
 Agent conversation views are identified with an alternative background color and the input toolbelt showing model selector, voice input, and image attachment buttons.
 :::
@@ -305,11 +303,6 @@ For more forking methods and use cases, see [Conversation Forking](/agents/local
 
 If you prefer to type natural language at any point in a terminal session and have it automatically routed to an agent, you can configure this using the "default mode for new sessions" setting.
 
-<figure>
-![Using Agent as your default for new tab sessions](/assets/agent-platform/recreate-universal-input.gif)
-<figcaption>Using Agent as your default for new tab sessions.</figcaption>
-</figure>
-
 ### 1. Set new tabs to open in agent view
 
 By default, new tabs and panes open in terminal mode. To launch directly into an agent conversation instead:

diff --git a/src/content/docs/getting-started/quickstart/customizing-warp.mdx b/src/content/docs/getting-started/quickstart/customizing-warp.mdx
@@ -20,7 +20,6 @@ Use the quick-reference table to find what you need, or browse the sections belo
 | Vertical tabs | **Settings** > **Appearance** > **Tabs** | Switch to a sidebar tab layout for more horizontal space |
 | Tab configs | **Settings** > **Features** or `/` menu | Save and restore tab layouts with startup commands |
 | Settings file | **Open settings file** button in the Settings footer | Edit [`settings.toml`](/terminal/settings/) directly for version control and scripting |
-| Input format | **Settings** > **Appearance** > **Input** | Choose Standard or Classic |
 | App icon | **Settings** > **Appearance** > **Icon** | Pick a custom icon (macOS) |
 | Font & text | **Settings** > **Appearance** > **Text** | Change font, size, and cursor style |
 | Agent autonomy | **Settings** > **Agents** > **Profiles** | Set what the agent can do without asking |
@@ -54,7 +53,6 @@ Organize your workspace with tabs, panes, and window configurations.
 
 Configure how you type and interact with the terminal input.
 
-* **[Standard vs Classic input](/terminal/input/classic-input/)** - Standard input provides easier access to AI features and is the default for new users. Classic input resembles a traditional terminal prompt. Switch between them in **Settings** > **Appearance** > **Input**.
 * **[Keyboard shortcuts](/getting-started/keyboard-shortcuts/)** - Warp supports common shortcuts and lets you create custom ones. Manage them from **Settings** > **Keyboard shortcuts**, or import keybindings from another terminal during [migration](/getting-started/migrate-to-warp/).
 * **[Vim keybindings](/terminal/editor/vim/)** - Enable Vim keybindings for keyboard-driven text editing in the input editor.
 * **Tab key behavior** - Configure what `Tab` does in **Settings** > **Features**. Options include accepting autosuggestions or triggering completions.

diff --git a/...rkflows/how-to-run-3-agents-in-parallel-summarize-logs-analyze-pr-modify-ui.mdx b/...rkflows/how-to-run-3-agents-in-parallel-summarize-logs-analyze-pr-modify-ui.mdx
@@ -43,7 +43,7 @@ In the demo, we run three parallel workflows:
            ```
        I'd like to make a coding change. Please create a new branch to do this.
 
-       What i want to do is for the Universal Developer Input, remove the border and background if it's being rendered in the same pane that is not focused. Please look at the reference file and at the attached screenshot. In the screenshot, you'll see what it looks like right now - there are two equally prominent input areas, even though one is focused and one is not. What I want to do is make the non-focused one not have a border and not have a background. 
+       I want to remove the border and background from the input when it's rendered in a pane that is not focused. Please look at the reference file and the attached screenshot. In the screenshot, there are two equally prominent input areas, even though one is focused and one is not. Make the non-focused input omit its border and background.
 
        Please check out this linear issue for more information. Also, give me a plan before you make any changes.
        ```

diff --git a/...uides/build-an-app-in-warp/building-a-real-time-chat-app-github-mcp-railway.mdx b/...uides/build-an-app-in-warp/building-a-real-time-chat-app-github-mcp-railway.mdx
@@ -34,13 +34,12 @@ The project: a **real-time chat application** built with **Python (FastAPI)** an
    Warp is free for macOS, Linux, and Windows. Download it from the [Warp homepage](https://www.warp.dev/) and sign in with an account.
    :::
 
-   Once you open Warp, you’ll see three core modes:
+   Once you open Warp, you can work in two modes:
 
-   * **Auto Mode** – Detects whether you’re typing a command or an AI prompt
-   * **Terminal Mode** – For standard shell commands only (`ls`, `pwd`, etc.)
-   * **Agent Mode** – For conversational AI prompts (`build me an app`, `add feature X`, etc.)
+   * **Terminal mode** - Run shell commands such as `ls` and `pwd`.
+   * **Agent Mode** - Ask the agent to build an app, add a feature, or complete another natural-language request.
 
-   You can switch modes using the top-bar buttons.
+   When auto-detection is enabled, Warp detects whether your input is a shell command or an agent request and routes it accordingly.
 
    Pro tip: Enable voice input for natural prompting or attach screenshots when debugging UI issues.
 

diff --git a/src/content/docs/guides/build-an-app-in-warp/building-warps-input-with-warp.mdx b/src/content/docs/guides/build-an-app-in-warp/building-warps-input-with-warp.mdx
@@ -30,7 +30,7 @@ So I thought: _“What if I just Warp it?”_
 
 #### 1. Locating the Git diff chip code
 
-Inside the universal input, there’s a small Git Diff chip — it shows your current branch and open changes. It was one pixel too tall. That tiny visual bug drove me nuts, so I used Warp to find where it lived.
+Inside Warp's input, there’s a small Git Diff chip — it shows your current branch and open changes. It was one pixel too tall. That tiny visual bug drove me nuts, so I used Warp to find where it lived.
 
 Warp searched across the entire codebase and found references inside: