# An agent space with a place for the next step. Reviewed: 2026-10-20 Canonical: https://clankercloud.ai/learn/ai-agent-space Clanker Cloud is an agent space where people and authorized assistants can work from the same Project files and instructions. Keep briefs, evidence, deliverables, and handoffs in Workspace while ChatGPT, Claude, Hermes, or OpenClaw remains the client you use. Each client needs a compatible connection and its own approved access. ## What you are working toward A Project another authorized assistant can understand without inheriting your entire chat. ## Start with - A Project with a named owner and a specific outcome - Approved source files and clear review criteria - A connected assistant or a native Workspace Agent ## An agent space starts with the work, not the conversation A chat is useful for deciding what to do next. A Project gives the work a durable home: source files, instructions, Sessions, and saved results. Put the current brief and accepted deliverables there so a later task can read the evidence instead of relying on a remembered conversation. For a fictional client engagement, keep brief.md, the approved requirements, a draft report, and handoff.md together. State which file is authoritative, who reviews the result, and what is still a proposal. A shared space helps only when the next participant can distinguish current decisions from unfinished suggestions. ## Give each assistant a clear role | Assistant | Example responsibility | What stays with the Project | | --- | --- | --- | | ChatGPT | Prepare a weekly report from approved notes | The saved report, source references, and open questions | | Claude | Review a draft against the current requirements | Review findings and the revised deliverable | | Hermes | Run a repeatable research or file-processing task | Checked outputs and a concise handoff | | OpenClaw | Turn an authorized request into a bounded Workspace task | The task record and saved result | ## Connect each client before asking it to work Use the hosted MCP endpoint https://workspace.clankercloud.ai/mcp and the client’s supported OAuth flow. Start with a read-only workspace_status check. Then name the Project, allowed inputs, required output, and actions the user has authorized. Read, Edit, and Configure and run are separate permissions. A Project name in a prompt selects task context; it does not narrow the OAuth grant to that Project. The grant follows the connected user’s existing Workspace role. Another assistant does not acquire access merely because its name appears in a file. Hermes and OpenClaw setup follows their current client documentation; verify your installed version and connection before relying on it. Sources: - [Clanker: connect an external agent and review permissions](https://clankercloud.ai/workspace-agents) ## Hand off an artifact and a decision Ask the first assistant to save what changed, the exact output filenames, unresolved questions, and the next permitted step. The next authorized assistant reads that packet in a fresh task. For example, ChatGPT can save a proposal summary and Claude can review it against the same approved criteria. Saved Session messages are records. Through the external MCP connection, sending a message to another Session saves a prompt; it does not by itself start an autonomous Agent or run a second model. Decide explicitly who should act next and verify that the requested work actually ran. Keep private reasoning and credentials out of handoff files. ## Make the shared space useful to its owner Open the actual saved output in Workspace. Check important statements against the source, confirm revisions, and keep missing information visible. Use a reusable Agent when the method should repeat; use a new task when the brief changes. An agent space is valuable when a person can inspect what happened and continue the work. Projects are saved context, not a promise of a continuously running computer. Choose cloud compute only when a task needs execution, and configure recurring work separately. Review sharing deliberately before inviting people or publishing an App. ## Try this prompt Paste this prompt into the external assistant connected to your Workspace. The connection guide does not launch or send a task automatically. ```text Use my connected Clanker Cloud Workspace to prepare a handoff for one Project I select. First verify the connection and ask which approved source files to use. After I authorize saving, start a managed Session and create handoff.md with current outputs, source filenames, decisions, open questions, and the next permitted step. Read the saved file back and complete the Session. Do not contact anyone, publish, run compute, or start another Agent. ``` ## Common questions ### What is an agent space? An agent space is the shared context and saved work around a task. In Clanker Cloud, Projects hold files and instructions, Sessions record tasks, and authorized people or assistants can inspect the results. ### Does Clanker copy ChatGPT or Claude conversations automatically? No. The external client keeps its own conversation. Save the relevant task summary, source references, and results explicitly; a connected Workspace does not automatically import a client’s full chat history. ## Sources - [Clanker: connect an external agent and review permissions](https://clankercloud.ai/workspace-agents) - [Clanker: current agent instructions and access contracts](https://workspace.clankercloud.ai/for-agents.md) - [Clanker: artifact-based handoffs between assistants](https://clankercloud.ai/learn/project-handoffs-between-ai-agents) ## Related - [Give your agents a place to do lasting work.](https://clankercloud.ai/learn/ai-agent-workspace) - [A cloud for agents, with the work kept together.](https://clankercloud.ai/learn/agent-cloud) - [Let the next agent continue from checked work.](https://clankercloud.ai/learn/project-handoffs-between-ai-agents) - [/workspace-agents](https://clankercloud.ai/workspace-agents) [Open Workspace](https://workspace.clankercloud.ai) [Current pricing and usage](https://clankercloud.ai/pricing)