> ## Documentation Index > Fetch the complete documentation index at: https://docs.jinba.io/llms.txt > Use this file to discover all available pages before exploring further. # AI Activity and the Workspace Panel > How to read the AI run status, review outputs and the console log in the workspace panel, use the preview toolbar, and save deliverables to Knowledge or Notion In Jinba App Neo, the AI works inside an isolated session environment for each message, performing file operations, code execution, web search, and more. This page explains how to follow what it is doing. ## Run status The AI's status is shown in the message area in real time. | Indicator | Meaning | | -------------------------- | ----------------------------------------------------- | | Connecting... | Starting the session | | Thinking... / Reasoning... | The AI is working out its answer or plan of action | | Running tool | Executing a Connector tool, code, or similar | | AI running | Work is in progress (changes to "Done" when finished) | Each step in the activity timeline is named in plain language rather than by its tool name. A step whose label is still being prepared shows "**preparing**" beside the name; a tool that offers no readable name at all reads "**Working…**" while it runs and "**Ran a step**" once it is done. Raw tool names and commands stay in the Console log. ## Interrupting a run While the AI is running, an "**Interrupt**" button is shown. Click it to stop processing at any time. An interrupted chat records "AI run was interrupted", and you can send follow-up instructions from there. ## The workspace panel Use the "Workspace" toggle in the chat screen to open a side panel showing what the AI has been working on. The panel shows **one thing at a time**. The preview takes a pane of its own beside the chat, and the tab rail on the right edge opens one list at a time next to it. | Pane | Contents | | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Preview** | The item you picked, rendered in place — Office documents (.docx / .xlsx / .pptx), PDFs, images, HTML, diagrams, code, and text | | **Files** | Everything this chat produced or read. Search it by name, narrow it with "**All**" / "**Deliverables**" / "**Sources**" / "**Code**", and take the lot with "**Download all (ZIP)**." Selecting a row previews that file | | **Console log** | The commands the AI ran and their output | | **Configuration** | In a chat bound to an agent, that agent's configuration panel — the same one its own page shows | * Drag a pane's edge to resize it. "**Expand to full width**" gives the preview the whole chat width and "**Restore size**" hands it back — if there is no room to bring the chat back, the control tells you to widen the window or close a pane instead of leaving you stuck * The rail remembers which list you had open, so reopening the panel returns you to it * On a narrow window (roughly 970 px and below) the panel keeps its earlier form: a single drawer with **Results**, **Files**, **Code**, **Terminal**, **Plan**, **Preview**, and **Console log** tabs, which can also be switched to full screen Browser view (a live view of the AI's browser operations) is coming soon. ### The agent's configuration, from the chat A chat bound to an agent carries a "**Configuration**" tab in the rail, alongside Files and the Console log. It opens the same configuration panel as the agent's own page — model, skills, knowledge, connectors — so you can check or adjust a setting without leaving the conversation. * The rail keeps one pane open at a time: opening Configuration closes Files or the Console log, and the other way round * Clicking a skill or knowledge chip inside the panel drills into that item's details in place * A note sits at the top of the panel: "**Config changes take effect in new chats, not this conversation (knowledge is picked up immediately).**" * An ad-hoc chat has no agent to configure, so it does not get the tab ### The preview toolbar Everything that opens in the preview — a deliverable, a knowledge file, a flow's output file — carries the same toolbar. Each format contributes only the controls its viewer supports, so a plain text file shows far fewer of them than a PDF. | Control | What it does | | ------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Zoom out / Zoom in** | Steps through the zoom presets. The zoom level beside them opens "**Fit width**" and "**Whole page**"; "**Reset zoom**" returns to the fit the viewer started from | | **Previous page / Next page / Go to page** | Paging, for formats that have pages | | **Search in document** | Finds text inside the file, with previous / next match and a "No matches" state | | **Download** | Saves the file. A rendered format also offers "**Download source file**," and a diagram offers "**Export**" (SVG / PNG / source) | | **Save…** | Keeps the file in Knowledge or Notion — see below | | **File details** (i) | Type, size, folder, when it was last updated and by whom, and how many agents use it. Sync status sits just before it as a chip | | **Expand preview** | Reopens the same preview as a modal over the whole screen | PDFs open in the app's own viewer, with zoom, paging, in-document search, and text selection. Mermaid files (`.mmd` / `.mermaid`) render as diagrams rather than as their source — the same viewer chat messages use for diagrams, so zoom, pan, and export work on them too. PowerPoint (.pptx) and Word (.docx) previews also zoom with a trackpad pinch or `Ctrl` (`⌘` on Mac) + scroll, from 10% to 400% — plain scrolling keeps behaving as before (in a pptx, it moves through the slides). ## Receiving generated files When the AI creates files, they appear in the message as cards under a "**Deliverables**" heading — each card shows a format icon, the file name, and its format and size. Click a card to preview it, or use the download button on the card to save it. Word (.docx), Excel (.xlsx), PowerPoint (.pptx), and PDF files render as previews (legacy binary `.doc` is download-only); other non-previewable formats open in the Files pane, where you can still read their contents or download them. An HTML file the AI creates runs live in the preview — buttons, page navigation, and other scripts work as they would in a browser. HTML you upload yourself, or that lives in Knowledge, is still shown as a static page. ## Files the AI reads from Google Drive When the AI reads a file from Google Drive during a chat, a copy is kept with the chat so you can see exactly what it read. These files appear in the message as cards under a "**Sources**" heading — separate from Deliverables — and in the Files pane under the "**Sources**" filter, and they open in the preview like any other file. * Google-native formats are converted for preview: Docs open as Word (.docx), Sheets as Excel (.xlsx), Slides as PowerPoint (.pptx), and Drawings as PDF. Regular files such as PDFs, images, and Office documents are kept as they are. Files on shared drives are covered too * The copy is made with **your own Google Drive access**, and files over 25 MB are not copied — the AI's answer itself is unaffected either way * A source can be saved to Knowledge from its card, just like a deliverable. Reading a file never opens the workspace panel on its own, and sources are not offered as file inputs to flow runs ## Knowledge files the AI points you at When the AI refers to a file in the agent's knowledge, it renders it in the reply as a clickable card labelled "**Knowledge**," carrying the item's title and type icon. Click the card to open the original in the preview; items with no file behind them, such as a URL or a Notion page, open their knowledge details instead. Ask for something explicitly — "open the price list" — and the preview opens on its own. Only knowledge the agent is allowed to read becomes a card, so a card never points at material you cannot open. ## Pages the AI links to When the AI points you at a screen — the Connectors page, an agent, a skill — it writes a clickable link to that page **in this workspace**, so following it lands you in the right place. Screens your workspace cannot open are never linked. ## Saving generated files to Knowledge or Notion Deliverables can be saved to a permanent home without downloading and re-uploading. Click the **bookmark icon** on a deliverable card (or "**Save…**" in the preview toolbar — use this for images, which have no card bookmark) and choose a destination: * **Knowledge** — save the file as a knowledge source, under "**Workspace knowledge**" or "**Agent knowledge**." The agent option carries its own picker offering every agent you can edit — the chat's own agent is preselected, but you can target any of them, and the option appears in agent-less chats too. For workspace knowledge, pick the destination with the built-in folder browser (the folder you are currently viewing is where the file is saved) * **Notion** — export the file to a Notion page you search for and select (requires the [Notion personal connector](/en/pages/jinba_app_neo/connectors/personal-connectors); if it is not connected, the menu shows a Connect link) The name field is pre-filled with the file name. If a knowledge item with the same name already exists, nothing is overwritten silently — rename the file, or explicitly choose "**Overwrite and save**." After a save completes, the bookmark stays lit as "Saved" for the rest of the session. The AI may also offer to save a deliverable for you via a "**Save to knowledge proposed**" card — see [In-Chat Forms and Suggestions](/en/pages/jinba_app_neo/chat/interactive-cards). ## When a run takes a long time If a tool run through a Connector is slow to respond, a hint message is shown. If a jinba-flow integration leaves no run history on the jinba-flow side, check that the MCP URL is reachable from outside (Anthropic's cloud) — `localhost` and internal-only hostnames cannot be reached.