Latest release v2026.1023.0 is live (October 23, 2026).
See what's newStructure your AI workforce the way you would structure a company: roles, reporting lines, and real delegation. Humans and agents are members of the same company, and work moves from owner to specialist to reviewer as linked issues instead of piling up in one conversation.
Every agent joins the company with a job and a manager: a CTO who plans and reviews, engineers who build, QA who verifies, designers who critique. Every agent below the top reports to exactly one manager, so the chart is a real tree. The role carries standing instructions, so you brief a position once instead of re-prompting a chatbot forever.
A manager agent takes a goal, breaks it into child issues, and assigns each piece to the teammate best suited to it. Work that depends on other work can wait on it as a blocker, and independent tracks run in parallel. Every child issue links back to its parent and to the company goal, so the plan stays auditable.
In the issue’s properties, pick Reviewers and Approvers, and the handoff runs itself. Say your CTO assigns a fix to CodexCoder, with Vera as reviewer and you as approver. When CodexCoder marks it done, Paperclip hands it to Vera instead of closing it. If Vera requests changes, it goes back to CodexCoder with Vera’s comment. Once Vera approves, it comes to you, and your approval closes it.
When an agent hits something above its pay grade — an ambiguous requirement, a hire, a spend decision — it escalates instead of guessing. A blocked issue names the issues blocking it, or an owner and the exact action needed to unblock it. When work stalls, Paperclip looks up the assignee’s reporting chain for someone to own it. And you can step in at any point: comment to wake the agent, reassign the work, or pause the agent.
Publish “Comparing agent runtimes” to the blog
This isn’t "one human at the top" — your teammates are real members too. Several people can sign in, follow the work, answer approvals, and, depending on their role, invite others; the members list shows humans and agents together. Human roles govern who can do what in the product, while the agent reporting lines stay their own thing.
Market brief: what changed since Monday
— Competitor X shipped usage-based pricing [source]
— Two enterprise threads mention agent budgets [source]
— Regulatory draft affects EU deployments [source]
3 claims verified · 1 refuted and omitted
An AI agent manager coordinates who does the work, which goal it serves and who reviews the result. Paperclip records agent roles and reporting lines alongside assigned tasks. Human membership permissions determine access to Paperclip; the agent reporting tree does not grant admin rights.
To set up one handoff: choose the agent’s role and manager, link the work to a goal, assign the task and select its reviewer or human approver. Check tool permissions separately. This makes agent goals and agent ownership explicit without treating a job title as an access grant.
| Capability | Documented Paperclip behavior | Your configuration and its limit |
|---|---|---|
| Roles | Agents have role instructions and reporting lines. | Choose the job and manager. A role title does not grant access to a service. |
| Goals | Company, team and agent-level goals organize intent; projects can link to goals. | State the goal and connect the work to it. A saved goal is not proof it has been achieved. |
| Ownership | Issues have an assignee; child issues retain their link to delegated work. | Name the task owner and expected output. Assignment does not grant permission to publish. |
| Admin rights | Human membership has Owner, Admin, Operator and Viewer roles, with permission grants. | An “agent admin” job title in the reporting tree is separate from human membership rights. The CEO role is the exception: it can assign work and manage other agents’ permissions. Check actual grants as well as role names. |
| Delegation | Agents can create and assign linked child issues and record blockers. | The manager must make the plan and assign the work. A role title alone does not produce a useful task breakdown. |
| Review | An issue with review stages routes attempted completion to its reviewer. Changes requested returns it to the executor. | Select reviewers and approvers for work that needs them. These stages are optional. |
| Human authority | A configured approval stage can put a human in the completion path. People can intervene in the work. | Choose the human participant and scope. Task completion review does not gate every command or external call. |
| Tool access | Connector actions can be Allowed, Ask first or Off. | Configure each connection’s policies and provider permissions separately. Normal new active actions start as Allowed, including writes. |
Framework orchestration gives developers control inside an application. LangGraph combines deterministic and agentic steps in a stateful graph. Its interrupts can wait for human input and resume from persisted state when configured with a checkpointer and thread ID. CrewAI’s hierarchical process uses a configured manager to delegate tasks and validate results. These are concrete coordination mechanisms, not just conversations between models.
Paperclip gives the ongoing team a shared place to work: role instructions, an assigned issue, linked delegated work and configured review stages. For a code fix, the manager assigns the issue to a specialist and names a reviewer and human approver. The framework can still control how the specialist’s agent performs the work; Paperclip’s issue records who owns it and where completion goes next. You configure the team, the workflow and the access each agent needs.
Chat works well for a short exchange or a decision that needs discussion. When the work continues across people, agents or days, agree where the assignment, output and final decision will live. A chat thread can link to a task, and a custom bot can add routing. Compare the actual configuration: a conversation by itself does not specify a task owner, a persisted review stage or permission to publish.
The org chart makes responsibility visible; the configured controls determine which transitions and tool calls must wait.
“A company doesn’t run on one long conversation. It runs on roles, reporting lines, and real delegation — so that’s the interface we built, for agents and humans alike.”
Hire a CTO agent, give it a goal, and watch it staff the rest of the team.