Skip to main content
Jinba App Neo integrates with jinba-flow in two ways: workspace connections and AI operation. Choose based on what you need (using both is fine).

​
Connecting a workspace

Connect a jinba-flow workspace so its published flows can be called as tools for the AI. Connecting takes one click — there are no API keys to issue or paste.
1

Open the Jinba Flow page

The “Not connected” group lists the jinba-flow workspaces you belong to whose published flows are reachable externally.
2

Press Connect

Press “Connect” on a workspace. It moves to the “Connected” group, and its published flows become callable as tools. Workspace connections are call-only — the AI cannot create or edit flows through them.
3

Attach it to an agent

Add this connection from the Flow connectors section of the agent’s configuration panel. The AI can then run the flows as tools.
  • You can also connect straight from the agent detail page: its Flow connectors section lists your connectable workspaces too, and one click sets up a connection dedicated to that agent (Attach resources)
  • See connected workspaces and their published flows on the “Jinba Flow” page
  • Connections stay in sync automatically: opening the Flow console or the composer’s connector picker checks the jinba-flow side for changes, and new or updated flows are marked with “NEW” / “Updated” chips. Manual “Re-sync” on the connection is still there when you want to force a refresh
  • When a flow runs, a flow input form may appear in the chat

​
Flow runs in chat

When the AI runs a flow, a “Flow run” card appears in the chat with the flow’s name and live status — “Running…” with the latest progress message and elapsed time, then “Completed” or “Failed” with the reason (if you have lost access to the Flow workspace, the card says so). Files the flow produces appear as download chips just below the card, with their real filenames, and are collected with the chat’s other deliverables. Files generated earlier in the chat — by a flow or by the AI itself — can be passed as file inputs to follow-up flow runs, so multi-step pipelines work without downloading and re-uploading anything.

​
Approval steps (human-in-the-loop)

When a running flow reaches a WAIT_FOR_APPROVAL step, the run pauses until someone decides.
  • In chat, the flow-run card switches to “Awaiting approval…” and shows an approval form: the message the flow author configured, any data to review, a comment box, and one button per configured action (typically Approve / Reject). An “Open approval page” link and the request’s expiry are shown as well
  • Whether a comment is required is up to the flow author — always, only when rejecting, or not at all. If a required comment is missing, the card says so and you can try again
  • The same approval form appears in the Flow run console for runs started from a form there
  • A request that has expired, or was already decided by someone else, is reported on the card

​
Flow run console

“Flow” in the sidebar is a run console for executing published flows directly from a form, without going through chat.
  • Flows are listed per workspace and organized by their jinba-flow folder structure — drill into folders, or search across them by name. Newly published flows carry a “NEW” chip and updated ones an “Updated” chip
  • Selecting a flow opens its input form; run it and check the results on the spot. If the flow has an approval step, the approval form appears right in the console
  • A link to the list of connected workspaces (the Jinba Flow page) is also here

​
AI operation

Turn on “AI operation” and the AI can operate Jinba on your behalf — listing, creating, and running flows: anything you can do.
  • Turn it on with the toggle on the card at the top of the “Jinba Flow” page. A confirmation dialog explains the scope; press “Allow”
  • It is a one-time, account-wide setting: it covers every Jinba Flow workspace you belong to (including ones you join later). There are no per-workspace grants
  • If the AI needs it mid-conversation, a “Let the AI operate your Jinba?” card appears in the chat — press “Enable”, confirm the same “Allow the AI to operate your Jinba?” dialog with “Allow”, and the AI picks up right where it left off
  • You can turn it off anytime from the same card
  • The AI acts with your own permissions, and every action is logged
  • Credentials are never passed to the AI
  • If your organization’s settings disable AI code execution, this setting is unavailable — the in-chat card shows “Unavailable — your organization’s settings disable AI code execution.” instead of the Enable button

​
Troubleshooting

  • “No access” is shown — you have lost access to that Flow workspace on the jinba-flow side. Ask the owner to invite you as a member or add an external access rule
  • Flow runs never respond — if no run appears in the jinba-flow run history, the MCP URL may not be reachable from Anthropic’s cloud. jinba-flow instances on localhost or internal-only hosts cannot be integrated
  • Connected but tools are missing — check that the flow is published. Connections re-sync automatically when you open the Flow console or the composer’s connector picker; “Re-sync” on the connection forces a refresh