# Set up an agent > Create an agent with New agent, answer its short setup interview and apply the card, then adjust its model, instructions, permissions, tools and limits in Agent settings. Source: https://orbitalaip.com/docs/agents/set-up-an-agent ## Before you start An agent belongs to a project, and anyone in the project except a viewer can create one. Your plan sets how many agents a workspace can hold. See [Members and roles](https://orbitalaip.com/docs/workspace-and-account/members-and-roles) and [Credits and billing](https://orbitalaip.com/docs/workspace-and-account/credits-and-billing). Open **Agents** in the sidebar, or go to [https://app.orbitalaip.com/agents](https://app.orbitalaip.com/agents). ## Create an agent 1. **Click New agent** Orbital creates the agent at once, names it **New Agent** and opens its conversation. If the project already holds an unfinished setup, **New agent** opens that draft instead. 2. **Say what its job is** The agent asks what its job should be, with a few suggested replies and room for your own (**Type your own answer…**). Say what it should do, with which data, and what it should report. 3. **Answer the second question, if it comes** When the job builds or tests strategies, the interview asks whether the agent should check with you first. Any other answer puts a permission on the card. See [Give a permission from Chat](https://orbitalaip.com/docs/agents/permissions-and-approvals#give-a-permission-from-chat). 4. **Apply the card** The agent proposes its name, type, model and instructions on one card, titled **Rename agent** and the new name. Review it, then click **Apply**, or **Discard** to drop the proposal. A schedule is not part of the card: add one under **Automations** once the card is applied. Until the card is applied, the agent cannot run. Anything that tries, such as **Run** under **Test input**, is refused with **Finish and apply this agent's guided setup before running it.** Setup configures the agent; it does not do the job, which the agent does in its own runs. Answers that give the interview enough to work with - "Screen mid-cap momentum names each morning and summarize the top 5 with entries and risks" - "Build and backtest a 20-day breakout strategy on my watchlist, then report what worked and what did not" ## Open Agent settings 1. **Open the agent's menu** In the **Agents** list, hover the agent and click **⋮** (**Actions for** its name). 2. **Choose Settings** The panel opens beside the conversation under the heading **Agent settings**. On a window narrower than a tablet it does not show; widen the window first. Changes save as you make them, and **✓ Saved** confirms each one. ## Name, model and instructions **Name** renames the agent. **Model** is the agent's own, and a draft starts on **GPT-5.6 Luna**; when the agent has tools, the list shows only models that support tools. See [AI models](https://orbitalaip.com/docs/workspace-and-account/ai-models#agents-use-their-own-model). **Instructions** tell the agent what it does, how it analyzes, what matters and what is noise. Leave out rules about approvals and limits: what the agent may do on its own is set by its permissions, not its instructions. ## Agent type, permissions, automations and knowledge **Agent type** shows the kind in words. A new agent is a **Job**: **Runs when you ask, or on a schedule.** **Manage** opens **Advanced settings**, where **Kind** also offers **Mission** and **Monitor**. **Permissions** says what the agent may do on its own, and only workspace owners and admins can change it. See [The four permissions](https://orbitalaip.com/docs/agents/permissions-and-approvals#the-four-permissions). **Automations** → **Manage** opens the schedules and wakes that run the agent when nobody is here; schedules created there start paused. See [Automations](https://orbitalaip.com/docs/agents/automations). **Knowledge** → **Manage** binds Library documents and artifacts the agent can read and cite, each with its own switch. See [Knowledge](https://orbitalaip.com/docs/agents/teams#knowledge). ## Advanced settings Open the **Advanced settings** line, which summarizes what sits behind it, for example **Focused · all tools · no output contract**. ### Creativity **Precise**, **Focused** or **Creative**. New agents are **Focused**. ### Reply length The most the agent may write in one reply, in tokens: 32,000 for a new agent, or its model's maximum where that is lower. You can set any number up to the model's maximum. An agent with no tools and JSON output is capped at 16,000 tokens outside a conversation. ### Memory and limits **Remembers** names the memory the agent keeps across runs; every run reads what the last one wrote. Leave it blank for no memory. **Spend cap** is how many [credits](https://orbitalaip.com/docs/glossary#credits) one run may spend. A run that reaches it stops before its next step and keeps its work. Outside a task, calls on your own provider keys do not count toward it. Blank, shown as **no cap**, means the workspace limit is the only ceiling. **Step limit** is how many times the agent may use a tool before it has to answer. Blank means 100, and the most you can set is 1,000. Reaching the limit is not a failure: the agent answers from what it gathered and says what it could not finish. The exception is a run started by a workflow's **Agent** node, which fails at the limit. The limit only applies to agents with tools. ### Tools **Use all available tools** is on for a new agent: every tool, including ones added later. Turn it off and the tools it covered stay ticked, grouped by category; untick the ones the agent should not use. **Hosted tools** are **Web search**, on by default, and **Code Interpreter**, off by default. Once **Make trading decisions** is set, in any mode, the agent's runs get neither, whatever these boxes show. See [Make trading decisions](https://orbitalaip.com/docs/agents/permissions-and-approvals#make-trading-decisions). ### Output **JSON** or **TEXT**; new agents answer in JSON. An **Output contract**, built with **Add output schema** or **Edit as JSON**, makes the answer's shape enforceable. **Required top-level keys**, such as **verdict, confidence**, are enforced even without a schema. With **TEXT** and a contract set, the final answer still has to be JSON. ### Test input **Test input** runs the agent on a sample payload, such as `{ "symbol": "AAPL" }`. **Run** starts it in the agent's conversation. **Save** keeps the payload under a name, up to 12 per agent. ### Lifecycle **Archive** stops the agent and keeps everything; it then sits under the **Archived** filter. **Unarchive** brings it back as a draft, with its schedules off until you turn them on again under **Automations**. **Delete** moves the agent to **Trash**, where you can restore it until it is permanently deleted after 30 days. See [Trash](https://orbitalaip.com/docs/workspace-and-account/workspace-settings#trash). Only project editors and above, and workspace owners and admins, can archive, unarchive, delete or restore an agent.