AI Activity and the Workspace Panel

How to read the AI run status, review outputs, code, terminal output, and plans, 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)

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. You can also switch it to full screen.

Tabs

Tab	Contents
Results	A summary of the run’s results
Files	Files the AI created (“Deliverables”). Select one to view its contents in place — text-based formats show their source, images / PDF / Office files show their rendered form. The “Open preview” (eye) action on a row opens it in the Preview tab, and “Download all (ZIP)” grabs everything at once
Code	Code files the AI created or edited
Terminal	Commands the AI ran and their output. Output can be shown or hidden
Plan	The work steps the AI laid out. The current step is highlighted
Preview	Rendered previews of HTML, Office documents (.docx / .xlsx / .pptx), PDFs, images, and similar formats
Console log	A record of what was executed

Browser view (a live view of the AI’s browser operations) is coming soon.

When the AI produces a file and the panel opens automatically, formats that cannot be rendered in Preview (data files such as JSON) open on the Files tab, where the contents are still readable.

The new preview layout (rolling out)

The panel is moving to a new layout that shows one item at a time: the preview gets its own pane next to the chat, and a separate “Files” pane — with search, filters (All / Deliverables / Sources / Code), and bulk download — opens from the tab on the right edge. Panes are resizable, and the preview can be expanded to the full chat width. The rollout is gradual, so your workspace may still show the tabbed panel described above.

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 tab, where you can still read their contents or download them.

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 tab’s toolbar — use this for images, which have no card bookmark) and choose a destination:

• Knowledge — save the file as a knowledge source. In an agent chat you can choose between workspace knowledge and that agent’s knowledge; 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; 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.

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.