Can I schedule an agent to run automatically?

You can schedule an agent to run automatically on a recurring schedule so it runs at the times you set. Open the agent and select the run from its Runs list on the left-hand side of the page to review the completed scheduled run.

Do I need to add a prompt every time I run an agent?

No. Adding a prompt is optional. If you don't add one, the agent runs using its configured instructions.

Where do I see the results after a run?

Each agent keeps your past runs as reports in the Agents tab. Open the agent and select any run from its Runs list on the left-hand side of the page to see the findings and the steps the agent took to reach them.

Does the agent make changes to my data?

Whether the agent makes changes to your data depends on how it's configured. Pre-built agents from the template library are view-only by default, so they surface findings and recommendations without modifying anything. If you've edited the agent to include tools that write data, it can take action on your behalf.

What happens if I don't have access to all the data my agent needs?

Agents can only access data and perform tasks within the permissions and access assigned to you. If certain data is outside your access, the agent may return fewer results than expected without showing an error. If the agent tries to perform a task that requires higher permissions or access, it will tell you what it can't perform or access. Contact your organization admin to request the permissions and access levels you need.

Can I run multiple agents at the same time?

You can run up to 5 agents at the same time. This limit is shared with AI Assistant , so agents and AI Assistant chats running at once can't add up to more than 5 total. For example, you could run 5 agents and 0 AI Assistant chats, or run 2 agents while 3 AI Assistant chats are open.

AI in Mitti

Run agents

Learn how to run agents via the web app in Mitti (by SafetyCulture) to analyze your organization's data without repeating the same prompts for recurring tasks.

Last updated: July 28, 2026

This feature is currently in Preview. As we continue developing this feature, its functionality and availability may change before its full release.

What are Agents in Mitti?

Agents in Mitti do the checking and analysis for you. Think of an agent as a team member who specializes in a specific task. You define what to look for, and it runs whenever you need it. The agent works through your organization's data and surfaces what matters, along with suggested next steps.

For example, instead of manually checking hundreds of inspection reports to find the three that need action, an agent scans them and tells you exactly what needs fixing.

What you'll need

Premium Plan or Enterprise Plan

Web app

"AI Assistant: Access" permission

Full seat

Your ag ents can only access data and perform tasks within the permissions and access assigned to you.

Run an agent

Log in to the web app (opens in new tab).
Click Agents in the sidebar.
Click the agent and select Run now.
Depending on the agent's instructions, it reviews your data and surfaces relevant findings or recurring patterns.

Click 'Run now' on the Agents page to run an agent.

Frequently asked questions

Need more help?

Was this page helpful?

Relevant articles

What are Agents in Mitti?

Learn more about Agents in Mitti (by SafetyCulture) and how they help teams surface recommendations from their data and act on findings without manually prompting each time.