Build

An agent is a saved AI configuration in your Mobius organization. It has a name, instructions, a model, and optional access to actions, skills, and memory.

Your organization owns the agent, its sessions, and the related data. If Build > Agents is not available, ask an organization administrator for access to create agents.

Saving the agent means you can use the same configuration again. You can chat with it in the app, connect it to a messaging channel, or give it a routine.

Create your first agent

In the app:

1. Open Build > Agents.
2. Click Create agent.
3. Name it Support ticket reviewer.
4. Add the optional description Summarizes a pasted ticket and drafts a reply.
5. Paste the instructions below into the instructions field.
6. Leave the model and Advanced options at their defaults.
7. Click Create agent.

Mobius opens the new agent and shows a message that the agent is ready.

Use these instructions for the first test:

Review support-ticket text pasted into chat. Return three headings: Problem, Missing information, and Draft reply. Do not invent missing details. Do not call actions, send the reply, or change a ticket.

This tells the agent what input it will receive, the required format, and what it must not do.

What controls an agent

An agent's page brings its settings and connections together.

An action performs one named operation. An agent's tools are the actions it may call, selected one at a time or a family at a time. Granting an action does not bypass the access rules for the organization or the connected service. The caller's permissions and the access granted by the connected service still apply.

See Tools and skills for the full distinction.

New agents are for everyone in the organization. Narrow that when the agent's accumulated knowledge should stay with one team or one person: see who an agent is for.

Keep each agent focused

Give an agent one responsibility that you can describe in a sentence. A support triage agent might summarize a ticket and draft a reply. A reporting agent might read monitoring results and prepare a daily summary.

Split the work into separate agents when:

• the tasks need different instructions;
• the tasks need access to different external systems; or
• keeping the access boundaries separate makes them easier to review.

This makes each agent easier to test. It also makes its access easier to review.

Three ways to use an agent

All three produce the same record: a session holding turns. A routine does not open a separate one; its occurrences land in the conversation where you asked for it.

Test before connecting other systems

The new agent page opens in Configure mode. To test it:

1. Open Sessions and click New chat session.

2. Paste this message:

   Ticket 4182: Pat cannot open the monthly report. The page says “Access denied.” The ticket does not say which report or when the problem began.

3. Send the message and wait for the reply to finish.

4. Confirm that the reply has Problem, Missing information, and Draft reply headings.

5. Confirm that the draft asks for the missing report and timing details. It should not claim that the issue was fixed or that a reply was sent.

6. Return to Sessions and open the most recent row. The transcript should show your message and the reply, with no action call between them.

This is a useful first test because the ticket text is supplied in the message. The agent does not need any tools or a connection to a ticket system.

Connect messaging or ask for a routine after this direct test behaves as expected. Both are covered in Agent messaging and Routines.

Change an existing agent

Open the agent in Configure mode and click Edit to change its name, description, instructions, model, skills, or tools. Click Save when you are done.

The edit keeps the same agent ID. It does not rewrite earlier session transcripts or completed turns. Future turns use the agent's current saved configuration. An open session can use the new configuration on its next turn, but its older messages remain in the transcript. For a clean comparison, use New chat session after each instruction change and send the same test message again.

Edit the existing agent when you are improving the same responsibility, including an intentional change to its tools. Create a different agent when a new responsibility or access boundary should remain separate.

Choose where information belongs

For example, a note about how one customer prefers reports may belong in agent memory. The current list of that customer's servers belongs in a table or the system that owns the list.

Pause or remove an agent

Open the Agent actions menu on the agent page and choose Disable agent to stop it from receiving new work or appearing as an available routing choice. You can enable it again later. Existing sessions remain records; check turns that are still running separately, because disabling an agent is not a recovery control for work already in progress.

Choose Delete agent from the same menu only when you want to remove it from the organization. Its routines stop with it. Mobius retains past message history for attribution, but the deleted agent is no longer available for new work.

Exact API fields are in the interactive API reference. Terminal commands are in the CLI command reference.

Next

• Decide who can use it in who an agent is for.
• Write more detailed instructions with agent definitions.
• Learn how conversations are stored in agent sessions.
• Add controlled capabilities with tools and skills.
• Put the agent's work on a schedule with routines.