Skip to main content

​
General

Jinba App Neo is the next-generation platform that succeeds Jinba App. What’s new includes an agent-centric design (Skills, Connectors, and Knowledge attach directly to agents), AI execution in isolated session environments, continuous learning through Memory, and Skill management in the SKILL.md format.
Data from the Beta period is expected to carry over as a rule, but if there is a major change in the product, we may provide migration guidance. For important data, we recommend keeping the original files — such as knowledge sources — on your side as well.
Anthropic’s Claude family (Claude Opus 5.5 / Claude Sonnet 5.5 / Claude Haiku 5.5). You can choose a model per agent or as the workspace default. The model is fixed per chat and never changes mid-conversation. An agent or workspace that was set to an older generation (Opus 5 / Sonnet 5 / Haiku 4.5, or Opus 4.8 / Sonnet 4.6 before them) is not left behind: new chats run on the newest generation of the same line, its settings show that model, and the first time the composer’s model badge names a model you have not seen on that device, a one-time callout says which model it moved from and to.

​
Chat

By default Enter sends and Shift + Enter inserts a newline. You can switch to the ⌘ / Ctrl + Enter style under “Sending messages” in “Settings > Personalize” — the choice is saved per device. Either way, ⌘ / Ctrl + Enter always sends, the Enter that confirms Japanese IME conversion never sends, and on phones and tablets Return inserts a line break (send with the send button).
No. The model and agent are fixed when the chat is created. To use a different model or agent, start a new chat. The one exception: when the model behind an open chat has changed (the agent’s model, or the workspace default), a banner above the composer offers to switch that chat to the new model (Chat overview).
Yes. Click the “Stop” button shown during a run to halt at any time. After stopping, you can keep sending follow-up instructions in the same chat.
Read the message to see which of two limits was reached. The monthly credit allotment is shared across your whole organization: wait for the reset date shown on screen, or contact your organization admin about raising the limit. If your organization has additional credit packs (top-ups beyond the plan), they are consumed automatically once the monthly allotment runs out — packs with an expiry first — so the monthly-limit message appears only after those are used up too. In a personal organization the monthly allowance is $3.00 of usage, and the usage screens show amounts in US dollars (Workspace settings).A chat-specific 24-hour limit affects only the current chat. Wait for the rolling window to clear, or continue in a new chat; other chats remain available. Either limit can also stop a response part-way through. Whatever had already been written stays in the chat.

​
Agents and Skills

No. Chats that were attached to the agent are not deleted — they remain in your history as standalone chats. However, the agent’s version history and audit log are deleted.
There is a limit on the number of Skills that can be attached to a single agent (this comes from the underlying Anthropic Managed Agents platform). Consider consolidating or cleaning up existing Skills, or deleting ones you no longer need.
Use “Copy for this agent and edit” (fork) in the Skill editor. The original shared Skill is untouched, and you get a dedicated copy to edit.

​
Connections and Knowledge

Check that the flow is published on the jinba-flow side. Connections re-sync automatically when you open the Flow page or the composer’s connector picker, and you can force a refresh with “Refresh” in the workspace’s index on the Flow page. If the workspace has disappeared from the “Connected” list — or shows “Unavailable” once you turn on “Show inaccessible workspaces” in the ”…” menu beside the heading — its flows are hidden because the Flow workspace may have been deleted, changed to Private, or stopped allowing your access. If it still exists, ask the owner to switch its visibility to Unlisted, invite you as a member, or add an external access rule as appropriate, then refresh the connection.
No. MCP servers need a public URL reachable from Anthropic’s cloud. localhost and internal-network-only addresses cannot be used, and only the http-stream type is supported.
URL sources keep a snapshot taken at registration time. Run “Re-fetch” on the source to update it to the latest content.
There is a limit on how many items are loaded automatically when a chat starts; anything beyond it gets a “Not auto-loaded” badge. That said, the AI can still retrieve those items via search when needed, so they’re worth registering.

​
Memory and privacy

Turn off “Learn from your chats” under “Settings > Memory” to stop new writes. Content already remembered stays and is still recalled until you remove it — edit or delete individual entries from the list, or erase everything with “Delete all.”
No. Your personal memory is yours alone. However, a shared agent’s “agent memory” is shared among everyone who uses that agent.
No. API keys and tokens are stored encrypted and are designed so the AI cannot access them.

​
Other

Send Beta feedback to contact@carnot.ai. Including a screenshot and the steps to reproduce makes investigation much smoother.