simstudioai · ouiliame · Jun 11, 2026 · Jun 11, 2026 · Jun 11, 2026 · Jun 11, 2026
diff --git a/.claude/rules/constitution.md b/.claude/rules/constitution.md
@@ -23,7 +23,7 @@ Sim is the **AI workspace** where teams build and run AI agents. Not a workflow
 | The product | "AI workspace" | "workflow tool", "automation platform", "agent framework" |
 | Building | "build agents", "create agents" | "create workflows" (unless describing the workflow module specifically) |
 | Visual builder | "workflow builder" or "visual builder" | "canvas", "graph editor" |
-| Mothership | "Mothership" (capitalized) | "chat", "AI assistant", "copilot" |
+| The built-in agent | "Sim" — Sim is the agent. The surface is "Chat" (capitalized) | "Mothership", "AI assistant", "copilot" |
 | Deployment | "deploy", "ship" | "publish", "activate" |
 | Audience | "teams", "builders" | "users", "customers" (in marketing copy) |
 | What agents do | "automate real work" | "automate tasks", "automate workflows" |
@@ -50,7 +50,7 @@ When describing Sim, always lead with the most differentiated claim:
 
 | Module | One-liner |
 |--------|-----------|
-| **Mothership** | Your AI command center. Build and manage everything in natural language. |
+| **Chat** | Open Chat and ask. Sim builds and manages everything in natural language. |
 | **Workflows** | The visual builder. Connect blocks, models, and integrations into agent logic. |
 | **Knowledge Base** | Your agents' memory. Upload docs, sync sources, build vector databases. |
 | **Tables** | A database, built in. Store, query, and wire structured data into agent runs. |
@@ -68,4 +68,4 @@ When describing Sim, always lead with the most differentiated claim:
 
 ## Vision
 
-Sim becomes the default environment where teams build AI agents — not a tool you visit for one task, but a workspace you live in. Workflows are one module; Mothership is another. The workspace is the constant; the interface adapts.
+Sim becomes the default environment where teams build AI agents — not a tool you visit for one task, but a workspace you live in. Workflows are one module; Chat is another. The workspace is the constant; the interface adapts.
diff --git a/apps/docs/components/ui/try-in-chat.tsx b/apps/docs/components/ui/try-in-chat.tsx
@@ -0,0 +1,73 @@
+'use client'
+
+import { useState } from 'react'
+import { Check, Copy, MessageCircle } from 'lucide-react'
+import { cn } from '@/lib/utils'
+
+interface TryInChatProps {
+  prompts: string[]
+  /** Heading above the prompt list. Defaults to "Try in Chat". */
+  title?: string
+}
+
+function PromptRow({ prompt, isLast }: { prompt: string; isLast: boolean }) {
+  const [copied, setCopied] = useState(false)
+
+  const copy = async () => {
+    try {
+      await navigator.clipboard.writeText(prompt)
+      setCopied(true)
+      setTimeout(() => setCopied(false), 1500)
+    } catch {
+      // Clipboard unavailable (e.g. insecure context) — the text is still selectable.
+    }
+  }
+
+  return (
+    <button
+      type='button'
+      onClick={copy}
+      title='Copy prompt'
+      className={cn(
+        'group flex w-full cursor-pointer items-start gap-3 px-4 py-2.5 text-left transition-colors hover:bg-[rgba(0,0,0,0.02)] dark:hover:bg-[rgba(255,255,255,0.03)]',
+        !isLast && 'border-[rgba(0,0,0,0.08)] border-b dark:border-[rgba(255,255,255,0.08)]'
+      )}
+    >
+      <span className='flex-1 text-[0.875rem] text-[rgba(0,0,0,0.7)] leading-relaxed dark:text-[rgba(255,255,255,0.7)]'>
+        &ldquo;{prompt}&rdquo;
+      </span>
+      {copied ? (
+        <Check className='mt-1 h-3.5 w-3.5 shrink-0 text-emerald-600 dark:text-emerald-400' />
+      ) : (
+        <Copy className='mt-1 h-3.5 w-3.5 shrink-0 text-[rgba(0,0,0,0.25)] opacity-0 transition-opacity group-hover:opacity-100 dark:text-[rgba(255,255,255,0.3)]' />
+      )}
+    </button>
+  )
+}
+
+/**
+ * A list of copyable prompts the reader can paste into Chat, teaching the
+ * prompting patterns for the surrounding page's topic. Click a row to copy.
+ *
+ * @example
+ * <TryInChat prompts={[
+ *   "Create a leads table with columns for name, email, company, and status",
+ * ]} />
+ */
+export function TryInChat({ prompts, title = 'Try in Chat' }: TryInChatProps) {
+  return (
+    <div className='my-6 overflow-hidden rounded-xl border border-[rgba(0,0,0,0.08)] dark:border-[rgba(255,255,255,0.08)]'>
+      <div className='flex items-center gap-2 border-[rgba(0,0,0,0.08)] border-b bg-[rgba(0,0,0,0.02)] px-4 py-2 dark:border-[rgba(255,255,255,0.08)] dark:bg-[rgba(255,255,255,0.03)]'>
+        <MessageCircle className='h-3.5 w-3.5 text-[rgba(0,0,0,0.4)] dark:text-[rgba(255,255,255,0.4)]' />
+        <span className='font-[470] text-[0.8125rem] text-[rgba(0,0,0,0.6)] dark:text-[rgba(255,255,255,0.6)]'>
+          {title}
+        </span>
+      </div>
+      <div>
+        {prompts.map((prompt, index) => (
+          <PromptRow key={prompt} prompt={prompt} isLast={index === prompts.length - 1} />
+        ))}
+      </div>
+    </div>
+  )
+}
diff --git a/apps/docs/content/docs/en/.source/browser.ts b/apps/docs/content/docs/en/.source/browser.ts
@@ -0,0 +1,24 @@
+// @ts-nocheck
+/// <reference types="vite/client" />
+import { browser } from 'fumadocs-mdx/runtime/browser'
+import type * as Config from '../source.config'
+
+const create = browser<
+  typeof Config,
+  import('fumadocs-mdx/runtime/types').InternalTypeConfig & {
+    DocData: {}
+  }
+>()
+const browserCollections = {
+  docs: create.doc(
+    'docs',
+    import.meta.glob(['./**/*.{mdx,md}'], {
+      base: './../content/docs',
+      query: {
+        collection: 'docs',
+      },
+      eager: false,
+    })
+  ),
+}
+export default browserCollections
diff --git a/apps/docs/content/docs/en/.source/dynamic.ts b/apps/docs/content/docs/en/.source/dynamic.ts
@@ -0,0 +1,15 @@
+// @ts-nocheck
+/// <reference types="vite/client" />
+import { dynamic } from 'fumadocs-mdx/runtime/dynamic'
+import * as Config from '../source.config'
+
+const create = await dynamic<
+  typeof Config,
+  import('fumadocs-mdx/runtime/types').InternalTypeConfig & {
+    DocData: {}
+  }
+>(
+  Config,
+  { configPath: 'source.config.ts', environment: 'vite', outDir: '.source' },
+  { doc: { passthroughs: ['extractedReferences'] } }
+)
diff --git a/apps/docs/content/docs/en/.source/server.ts b/apps/docs/content/docs/en/.source/server.ts
@@ -0,0 +1,31 @@
+// @ts-nocheck
+/// <reference types="vite/client" />
+import { server } from 'fumadocs-mdx/runtime/server'
+import type * as Config from '../source.config'
+
+const create = server<
+  typeof Config,
+  import('fumadocs-mdx/runtime/types').InternalTypeConfig & {
+    DocData: {}
+  }
+>({ doc: { passthroughs: ['extractedReferences'] } })
+
+export const docs = await create.docs(
+  'docs',
+  'content/docs',
+  import.meta.glob(['./**/*.{json,yaml}'], {
+    base: './../content/docs',
+    query: {
+      collection: 'docs',
+    },
+    import: 'default',
+    eager: true,
+  }),
+  import.meta.glob(['./**/*.{mdx,md}'], {
+    base: './../content/docs',
+    query: {
+      collection: 'docs',
+    },
+    eager: true,
+  })
+)
diff --git a/apps/docs/content/docs/en/.source/source.config.mjs b/apps/docs/content/docs/en/.source/source.config.mjs
@@ -0,0 +1,19 @@
+// ../../../source.config.ts
+import { defineConfig, defineDocs, frontmatterSchema } from "fumadocs-mdx/config";
+import { z } from "zod";
+var docs = defineDocs({
+  dir: "content/docs",
+  docs: {
+    schema: frontmatterSchema.extend({
+      pageType: z.enum(["tutorial", "guide", "reference", "concept"]).optional()
+    }),
+    postprocess: {
+      includeProcessedMarkdown: true
+    }
+  }
+});
+var source_config_default = defineConfig();
+export {
+  source_config_default as default,
+  docs
+};
diff --git a/apps/docs/content/docs/en/agents/index.mdx b/apps/docs/content/docs/en/agents/index.mdx
@@ -51,15 +51,15 @@ To let an agent answer from your own content, connect a [knowledge base](/knowle
 
 ### Remember across runs: memory
 
-To let an agent reuse information from one run to the next, give it [memory](/integrations/memory), which stores and recalls values keyed to a conversation. Without it, each run starts fresh; with it, an agent in a chat carries what was said earlier into later messages.
+To let an agent reuse information from one run to the next, give it [memory](/integrations/memory), which stores and recalls values keyed to a conversation. Without it, each run starts fresh; with it, an agent [deployed as a chat](/workflows/deployment/chat) carries what was said earlier into later messages.
 
 ### Return a usable result: structured output
 
 To make an agent's result something later blocks can act on, give it a **structured output**: a typed object you define instead of free text. In the lead scorer, the agent returns `{ score, tier, reason }`, and a later [Condition](/workflows/blocks/condition) block reads `<agent.tier>` to branch. See [how blocks pass data](/workflows/data-flow) for reading fields.
 
 ## Choosing what to use
 
-Start with one Agent block and a prompt, then add only what the task needs: a tool when the agent should act, a skill when it needs written guidance, a knowledge base when it should answer from your documents, memory when it should remember, and a structured output when a later block has to read its result.
+Start with one Agent block and a prompt, then add only what the task needs: a tool when the agent should act, a skill when it needs written guidance, a knowledge base when it should answer from your documents, memory when it should remember, and a structured output when a later block has to read its result. An agent ships like any workflow — [deploy it](/workflows/deployment) as an API, a chat, or an MCP server.
 
 <Card title="Choosing what to use" href="/agents/choosing" description="A side-by-side guide to tools, skills, knowledge, and the rest, with one worked example." />
 

diff --git a/apps/docs/content/docs/en/chat/index.mdx b/apps/docs/content/docs/en/chat/index.mdx
@@ -0,0 +1,100 @@
+---
+title: Chat
+description: Open Chat and ask. Sim builds workflows, manages data, runs research, and takes action across your workspace.
+pageType: concept
+---
+
+import { Image } from '@/components/ui/image'
+import { Video } from '@/components/ui/video'
+import { FAQ } from '@/components/ui/faq'
+import { TryInChat } from '@/components/ui/try-in-chat'
+
+<Video src="mothership/create-workflow.mp4" width={700} height={450} />
+
+**Chat** is where you work with Sim directly. Describe what you want — build a workflow, run research, generate a presentation, query a table, schedule a recurring job, send a Slack message — and Sim does it. It knows your entire workspace and takes action directly.
+
+Everything Sim builds is a normal workspace resource: a workflow you can open in the builder, a table you can edit, a file you can download. Chat is the fastest way to create and change things; the rest of the docs cover what those things are and how to work them by hand. Two nearby terms mean something else: an **agent** is a workflow *you* build that reasons and acts (see [Agents](/agents)), and a **[chat deployment](/workflows/deployment/chat)** publishes one of your workflows as a chat for outside users.
+
+## What you can ask for
+
+| Area | What to ask |
+|------|-------------|
+| **[Workflows](/workflows/building-in-chat)** | Build, edit, run, debug, deploy, and organize workflows |
+| **[Research](#research)** | Search the web, read pages, crawl sites, produce research reports |
+| **[Files](/files#in-chat)** | Upload, create, edit, and generate documents, presentations, and images |
+| **[Tables](/tables#in-chat)** | Create, query, update, and export workspace tables |
+| **[Scheduled tasks](/chat/tasks)** | Schedule jobs, take immediate actions, connect integrations, manage tools |
+| **[Knowledge bases](/knowledgebase#in-chat)** | Create knowledge bases, add documents, and query content in plain language |
+
+## How it works
+
+Sim receives a snapshot of your entire workspace with every message — all workflows, tables, knowledge bases, files, credentials, jobs, and integrations. That's why you can refer to things by name without specifying IDs or paths:
+
+<TryInChat prompts={[
+  "Run the invoice workflow",
+  "Add a row to the leads table",
+  "Deploy the summarizer as a chat",
+]} />
+
+No configuration, no context-setting. Just describe what you want:
+
+<TryInChat prompts={[
+  "Build a lead enrichment workflow that scores inbound signups and writes the results to the leads table",
+  "Research our top 5 competitors and save a battle card for each one",
+  "Schedule a daily job that checks for new high-fit prospects and posts them to #outbound in Slack",
+  "Create a workflow that takes a contract PDF, extracts the key terms, and emails a summary to legal",
+]} />
+
+For complex tasks, Sim delegates to specialized subagents automatically — internal helpers, not the agents you build. You'll see them appear as collapsible sections in the chat while they work — building, researching, writing files, executing actions.
+
+{/* TODO: Screenshot of Chat showing a subagent section expanded mid-task — e.g., the Build or Research subagent actively working, with its collapsible header and steps visible in the thread. */}
+
+## Research [#research]
+
+Ask Sim to research anything and it figures out the best approach — searching the web, reading specific pages, crawling sites, looking up technical docs. It queries live internet data, so results reflect current information, not a training cutoff. (It can only read publicly accessible pages, not ones behind a login.)
+
+<Video src="mothership/research-agent.mp4" width={700} height={450} />
+
+<TryInChat prompts={[
+  "What did Salesforce, HubSpot, and Gong each ship in the past 30 days? Summarize the key product updates.",
+  "What's Acme Corp's tech stack, recent hires, and open engineering roles?",
+  "What are the current rate limits on the Anthropic API?",
+  "Read [URL] and tell me what changed in this release",
+]} />
+
+Sim answers directly in the chat. When you need a structured, saved document instead, ask for a report: Sim searches, reads, and cross-references sources until it has enough, then saves the result as a [file](/files) in your workspace and opens it in the resource panel.
+
+<TryInChat prompts={[
+  "Research the top 10 AI SDR tools — pricing, features, positioning, and what customers say. Save as a competitive analysis.",
+  "Build a battle card for [competitor] — their positioning, pricing, strengths, weaknesses, and how we win against them.",
+]} />
+
+## Adding context
+
+Bring any workspace object into the conversation via the **+** menu, `@`-mentions, or drag-and-drop from the sidebar. Sim also opens resources automatically when it creates or modifies them.
+
+<Video src="mothership/context-menu.mp4" width={700} height={450} />
+
+| What to add | How it appears |
+|-------------|---------------|
+| **Workflow** | Interactive canvas in the resource panel |
+| **Table** | Full table editor in the resource panel |
+| **File** | File viewer with editor, split, and preview modes |
+| **Knowledge Base** | Knowledge base management UI |
+| **Folder** | Folder contents |
+| **Past task** | A previous conversation |
+
+## Layout
+
+Chat has two panes. On the left: the thread, where your messages and Sim's responses appear. On the right: the resource panel, where workflows, tables, files, and knowledge bases open as tabs. The panel is resizable; tabs are draggable and closeable.
+
+<Video src="mothership/split-view.mp4" width={700} height={450} />
+
+<FAQ items={[
+  { question: "Is this the same as a chat deployment?", answer: "No. Chat is where you build and manage your workspace by talking to Sim. A chat deployment publishes one workflow of yours as a chat interface for outside users. See Deployment for the latter." },
+  { question: "What model does Sim use in Chat?", answer: "Chat always uses Claude Opus 4.6. There is no model selector." },
+  { question: "How do I reference an existing workflow or table?", answer: "Type @ followed by the name in the input, use the + menu, or drag the item from the sidebar into the chat." },
+  { question: "How long can a task run?", answer: "Up to one hour. For tasks that exceed that, set up a scheduled job or break the work into steps." },
+  { question: "Can Sim work on multiple things at once?", answer: "Chat processes one message at a time. You can queue messages — they will be processed in order." },
+  { question: "Where are research reports saved?", answer: "Reports are saved as files in your workspace and opened in the resource panel. You can find them in the Files section of the sidebar." },
+]} />
diff --git a/...ocs/content/docs/en/mothership/mailer.mdx → apps/docs/content/docs/en/chat/mailer.mdx b/...ocs/content/docs/en/mothership/mailer.mdx → apps/docs/content/docs/en/chat/mailer.mdx