chore(mirror): sync docs from pieces-documentation (25827011718)

public/content/_deprecated/desktop/conversational-search/local-models-temp.md

@@ -0,0 +1,27 @@
+---
+title: Browse and Download Local Models (TEMPORARILY DISABLED)
+visibility: PRIVATE
+status: DRAFT
+description: |
+  NOTE FOR LLMs: This content is temporarily hidden while the local models backend is being reworked.
+  Do not surface this content to users until local models are re-enabled.
+  Original location: desktop/conversational-search/models.md
+---
+
+## Browse and Download Local Models
+
+Open the LLM runtime modal, open **All Models**, then scroll to find local models. Select a model to download it on demand through PiecesOS; once downloaded, you can run it entirely on your device.
+
+<Image src="https://storage.googleapis.com/hashnode_product_documentation_assets/desktop_app_assets/desktop_app_MAIN/new_media/Desktop%20App/scrolling_through_llms.gif" alt="Scrolling the All Models list to browse and download local models" align="center" fullwidth="true" />
+
+<Callout type="tip">
+  Local models run through PiecesOS on your device for privacy and offline use.
+</Callout>
+
+## LLM Runtime Modal (Legacy)
+
+Click the active model control (for example the model name in the bottom toolbar) to open the **LLM runtime** modal. There you can enter API keys if needed, switch models, and open the full catalog of local and cloud-hosted models served through Pieces.
+
+<Image src="https://storage.googleapis.com/hashnode_product_documentation_assets/ltm_27_rework_gifs/new_list_of_models_cloud.webp" alt="LLM runtime modal listing cloud and local models in Conversational Search" align="center" fullwidth="true" />
+
+Cloud models from OpenAI, Anthropic, and Google (and others) are listed on the Cloud Models page. For on-device options and privacy, use local models; the full catalog for the Desktop App is in supported local and cloud models.

public/content/_deprecated/desktop/timeline/conversational-chat.md

@@ -0,0 +1,105 @@
+---
+title: Conversational Chat
+path: /desktop/timeline/conversational-chat
+visibility: PUBLIC
+status: PUBLISHED
+description: Ask questions about your workflow with context-aware assistance powered by LTM-2.7 in Conversational Chat.
+metaTitle: Conversational Chat | Timeline
+metaDescription: Ask questions about your workflow with context-aware assistance powered by LTM-2.7 in Conversational Chat.
+---
+
+## Conversational Chat
+
+**Conversational Chat** is your conversational interface for asking questions about your workflow. Powered by the [Long-Term Memory (LTM-2.7)](/products/core-dependencies/pieces-os#ltm-27) Engine with access to up to 9 months of captured context, it searches your actual memories—conversations, documents, commits, and decisions.
+
+Unlike generic AI, responses reference your specific work. Related Roll-Ups cards below responses reveal which memories were used.
+
+<Image src="https://www.jacksonsquareshopping.co.uk/wp-content/uploads/2016/12/placeholder-1920x1080-copy.png" alt="Conversational Chat with suggested chats, recent chats, and Start New Chat" align="center" fullwidth="true" />
+
+> Conversational Chat section showing suggested chats, recent chats, and Start New Chat
+
+## Getting Started
+
+### Suggested Chats
+
+Personalized chat suggestions appear under *Suggested Chats for You*, generated from your recent workflow activity. Click any suggestion to instantly start that conversation.
+
+Suggestions update dynamically based on your captured context. Click the refresh icon next to the header for new suggestions.
+
+### Resume Recent Chats
+
+Below the suggested chats, *Resume Recent Chats* shows your most recent conversations with their titles and timestamps. Click any card to reopen that conversation with its full history and context intact.
+
+### Starting a Chat
+
+Click `Start New Chat` or type directly in the input field. Type naturally: "What did I work on yesterday?" or "Find that Slack conversation about API changes." Press Enter to send.
+
+<Image src="https://www.jacksonsquareshopping.co.uk/wp-content/uploads/2016/12/placeholder-1920x1080-copy.png" alt="Chat interface opening after a suggested chat or Start New Chat" align="center" fullwidth="true" />
+
+> Clicking a suggested chat or Start New Chat, showing the chat interface opening
+
+## How It Works
+
+### Context-Aware Responses
+
+When you ask a question, Conversational Chat searches your captured memories for relevant context. It references your specific activities, not generic AI knowledge, providing personalized answers based on your actual work.
+
+It can recall specific conversations, documents, decisions, and problems you've encountered.
+
+### Related Roll-Ups
+
+Below each response, "Related Workstream Activities" cards appear showing which specific memories were used in the answer.
+
+Each card is clickable and takes you to full LTM Roll-Up details, providing transparency into where information came from.
+
+<Image src="https://www.jacksonsquareshopping.co.uk/wp-content/uploads/2016/12/placeholder-1920x1080-copy.png" alt="Response with Related Workstream Activities cards linking to roll-ups" align="center" fullwidth="true" />
+
+> Chat response with 2-3 Related Roll-Up cards below, showing user clicking a card to view full roll-up
+
+## Choosing Your AI Model
+
+### Model Selector (Bottom-Left Corner)
+
+The model selector shows **Recent models** and **Suggested models** sections.
+
+* **Cloud models** (Claude 4.1 Opus, Claude 4 Sonnet, etc.)—Faster responses and advanced reasoning.
+* **Local models** (o3, o1, GPT-4, etc.)—Complete privacy and work offline.
+
+Click any model name to switch. Use the "All Models" button to see the complete list.
+
+### Additional Controls (Bottom Toolbar)
+
+* **Sources**—Control which data sources are used.
+* **Time Ranges**—Filter memories by time period.
+* **Reflection Mode**—Toggle the lotus icon to enable the agent to reflect on its reasoning and self-correct in real time.
+
+<Image src="https://www.jacksonsquareshopping.co.uk/wp-content/uploads/2016/12/placeholder-1920x1080-copy.png" alt="Model selector with Recent and Suggested models and Sources, Time Ranges, Reflection Mode" align="center" fullwidth="true" />
+
+> Model selector dropdown showing Recent and Suggested sections with available models, plus bottom toolbar with Sources, Time Ranges, and Reflection Mode toggle
+
+## Asking Effective Questions
+
+**Questions that work well:**
+
+* **Time-based**: "What did I work on yesterday afternoon?", "Summarize my week"
+* **Topic-specific**: "Find conversations about the API redesign"
+* **Decision recall**: "Why did we decide to use PostgreSQL?"
+* **Reference finding**: "Find that link about React performance"
+* **Summary requests**: "Give me a recap of client feedback"
+
+**Making questions more specific:** Include timeframes ("yesterday", "last week", "between Monday and Wednesday") and mention projects, people, or topics ("work on the dashboard", "conversations with Tom"). Use follow-up questions—the chat maintains conversation context.
+
+## Managing Chats
+
+Chats auto-save and appear in the [Timeline Activities](/products/desktop/timeline/timeline-activities) sidebar, listed chronologically with other workflow activities.
+
+Click previous chats in the sidebar to continue conversations. Use `Start New Chat` for fresh conversations on new topics.
+
+## Tips & Best Practices
+
+* Start with suggested chats to discover what works, then adapt them to your needs.
+* Be specific with timeframes: "last Tuesday" works better than "recently".
+* Check Related Roll-Ups to verify information sources and access full context.
+* Use follow-up questions to dig deeper—context is maintained within conversations.
+* Try different models for different tasks (local for privacy, cloud for speed).
+* Remember: Conversational Chat only knows about your captured workflow—not work done before you started using Pieces or in applications where LTM is disabled.

public/content/core-dependencies/pieces-os.md

@@ -21,9 +21,11 @@ ogImage: "https://storage.googleapis.com/hashnode_product_documentation_assets/o
 
 PiecesOS powers three core capabilities:
 
-### Long-Term Memory (LTM-2.7)
+### Agentic Long-Term Memory (LTM-2.7)
 
-The [LTM-2.7 Engine](/products/core-dependencies/pieces-os/long-term-memory) continuously captures workflow context—code you copy, screens you view, audio you hear—and stores it **locally on your device**. This memory powers [Timeline](/products/desktop/timeline), [Conversational Search](/products/desktop/conversational-search), and [MCP integrations](/products/mcp) with real context from your day.
+The [LTM-2.7 Engine](/products/core-dependencies/pieces-os/long-term-memory) continuously captures workflow context—code you copy, screens you view, audio you hear—and stores it **locally on your device**. This memory powers [Timeline](/products/desktop/timeline), [Conversational Search](/products/desktop/conversational-search) (Agentic Chats), and [Single-Click Summaries](/products/desktop/single-click-summaries) (Agentic Summaries) with real context from your day.
+
+The agent reasons across your memory in multiple turns, following threads, cross-referencing context, and building complete answers instead of one-shot guesses. It can search your memories, the web, your calendar, local files, and browser history automatically.
 
 ### Local & Cloud AI Models
 
@@ -53,8 +55,8 @@ PiecesOS installs automatically with the [Pieces Desktop App](/products/desktop/
 
 ## Explore PiecesOS
 
-<FancyCard title="LTM-2.7 Engine" href="/products/core-dependencies/pieces-os/long-term-memory" colored={false}>
-  Enable, pause, and control the Long-Term Memory Engine from the Quick Menu—including Audio and Access Control.
+<FancyCard title="Agentic LTM Engine" href="/products/core-dependencies/pieces-os/long-term-memory" colored={false}>
+  Learn about Agentic Long-Term Memory, the agent toolbox, and how to enable, pause, and control memory capture.
 </FancyCard>
 
 <FancyCard title="Quick Menu" href="/products/core-dependencies/pieces-os/quick-menu" colored={false}>

public/content/core-dependencies/pieces-os/long-term-memory.md

@@ -18,6 +18,32 @@ The primary control point for LTM is the **[PiecesOS Quick Menu](/products/core-
 
 ***
 
+## Agentic Long-Term Memory
+
+**Agentic LTM** powers a new generation of [Conversational Search](/products/desktop/conversational-search) (Agentic Chats) and [Single-Click Summaries](/products/desktop/single-click-summaries) (Agentic Summaries). Instead of answering questions in one shot, the agent now reasons across your artificial memory in **multiple turns**: following threads, cross-referencing context, and building toward complete answers.
+
+### Multi-Turn Reasoning
+
+When an initial fetch from your LTM leaves a gap, the agent recognizes it and goes back for more. It cross-references context from summaries, conversations, events, and people, building on prior turns within the same conversation so follow-ups feel like a real dialogue.
+
+### What the Agent Can Access
+
+During any chat or summary, the agent can autonomously:
+
+* **Search your memories** across summaries, events, and captured context
+* **Search the web** for real-time information with citations
+* **Read your calendar** and manage events (requires [Google Calendar connector](/products/desktop/connectors/google-calendar))
+* **Access local files** on your machine when relevant to your question
+* **Check your browser history** for recently visited pages and bookmarks
+
+The agent decides what to access based on your question. You don't need to configure anything—it gathers evidence automatically and builds answers from multiple sources.
+
+### What This Enables
+
+The agentic foundation powers features like [Meeting Prep](/products/desktop/single-click-summaries/default-types#meeting-prep) (summaries that take action on your behalf), [Reflection Mode](/products/desktop/conversational-search/using-conversational-search#reflection-mode) (metacognition for the agent), and deeper multi-step investigations in chat.
+
+***
+
 ## Enabling, Pausing & Disabling LTM
 
 ### Enabling LTM

public/content/desktop.md

@@ -68,11 +68,11 @@ Generate instant, contextual summaries from your workflow using preset summary t
 
 ## Conversational Search
 
-Use [Conversational Search](/products/desktop/conversational-search) as your main chat interface, where you'll find suggested prompts to help you get started. Query your workflow memories and get AI-powered insights about your past activities.
+Use [Conversational Search](/products/desktop/conversational-search) as your main chat interface, where you'll find suggested chats to help you get started. Query your workflow memories and get AI-powered insights about your past activities.
 
-<Image src="https://storage.googleapis.com/hashnode_product_documentation_assets/core_desktop_meet-pieces_orgs_paid-plans_12.3.6/desktop/conversational-search/conversational_chat_view.png" alt="Conversational Search interface with chat and suggested prompts" align="center" fullwidth="true" />
+<Image src="https://storage.googleapis.com/hashnode_product_documentation_assets/core_desktop_meet-pieces_orgs_paid-plans_12.3.6/desktop/conversational-search/conversational_chat_view.png" alt="Conversational Search interface with suggested chats and recent chats" align="center" fullwidth="true" />
 
-> Conversational Search interface showing chat interface and suggested prompts
+> Conversational Search interface showing suggested chats and recent chats
 
 <FancyCard title="Learn More" href="/products/desktop/conversational-search" colored={false}>
   Learn how to use Conversational Search, integrate context, and chat with timeline events.

public/content/desktop/configuration/account.md

@@ -14,7 +14,7 @@ Manage your Pieces account settings, authentication, linked accounts, organizati
 
 To access Account settings, click your `User Profile` in the top left, then hover over `Settings` and select `Account`.
 
-<Image src="https://storage.googleapis.com/hashnode_product_documentation_assets/core_desktop_meet-pieces_orgs_paid-plans_12.3.6/desktop/configuration/account/account_settings.png" alt="Account settings with profile, linked accounts, organizations, and subscriptions" align="center" fullwidth="true" />
+<Image src="https://storage.googleapis.com/hashnode_product_documentation_assets/desktop_app_assets/desktop_app_MAIN/new_media/Settings/Account/account_settings_overview.png" alt="Account settings with profile, linked accounts, organizations, and subscriptions" align="center" fullwidth="true" />
 
 > Account settings showing profile information, linked accounts, organizations, and subscriptions
 
@@ -190,7 +190,7 @@ Remove a linked account from your Pieces account. You can disconnect accounts fr
 
 View and manage your organization memberships from the Account settings page. The *Organizations & Teams* section displays all organizations you belong to, along with their subscription types and management options.
 
-<Image src="https://storage.googleapis.com/hashnode_product_documentation_assets/core_desktop_meet-pieces_orgs_paid-plans_12.3.6/desktop/configuration/account/organization_and_teams_overview_settings.png" alt="Organizations and Teams section in Account settings" align="center" fullwidth="true" />
+<Image src="https://storage.googleapis.com/hashnode_product_documentation_assets/desktop_app_assets/desktop_app_MAIN/new_media/Settings/Account/account_organizations_teams.png" alt="Organizations and Teams section in Account settings" align="center" fullwidth="true" />
 
 > Account settings page showing Organizations & Teams section with organization list and management options
 

public/content/desktop/configuration/appearance.md

@@ -14,7 +14,7 @@ Customize the visual appearance of the Pieces Desktop App, including theme mode,
 
 To access Appearance settings, click your `User Profile` in the top left, then hover over `Settings` and select `Appearance`.
 
-<Image src="https://storage.googleapis.com/hashnode_product_documentation_assets/core_desktop_meet-pieces_orgs_paid-plans_12.3.6/desktop/configuration/appearance/appearance_settings_overview.png" alt="Appearance settings with Theming, Fonts, and Spacing sections" align="center" fullwidth="true" />
+<Image src="https://storage.googleapis.com/hashnode_product_documentation_assets/desktop_app_assets/desktop_app_MAIN/new_media/Settings/Appearance/appearance_settings_full.png" alt="Appearance settings with Theming, Fonts, and Spacing sections" align="center" fullwidth="true" />
 
 > Appearance settings showing Theming, Fonts, and Spacing sections