Security, permissions and data handling
An AI assistant you can trust with real work
Autessa Autobots work within each person’s permissions, use only the apps chosen for them, never take passwords in chat, and ask before they send, buy, delete or post. Every standing permission and every memory is visible and removable.
Controls
How Autobots handle access and data
| Area | How it works |
|---|---|
| Who can use Autobots | People whose role can use agents. The Autobot build chat follows its own builder permission. |
| What an Autobot can reach | What the person chatting can reach, through the apps and MCP servers chosen for that Autobot. |
| Passwords and codes | Secure forms post values straight to the browser; never shown in or saved to the chat. |
| Sensitive answers | Send privately: typed hidden and never shown back in the conversation. |
| Actions with consequences | Approval before sending, buying, deleting or posting: Allow once, Always allow or Deny. |
| Standing permissions | Always allowed rules are listed per Autobot and removable at any time. |
| Memory | Every memory is visible and editable in the Autobot’s settings. |
| Browser isolation | Each person sees only their own Autobot browser; it closes with the conversation. An optional fresh browser for each scheduled run. |
| Things it built | Temporary builds are kept for 30 days unless saved as a dashboard app. |
| Changing an Autobot | Only its owner can rename it, change its job, apps or settings, or delete it. |
| Usage limits | Autobots draw on your company’s daily and weekly AI credit allowances. |
| Scope of work | Builds only what was explicitly asked for; anything else is suggested and waits for a yes. |
Company-wide AI security
Add the AI Agent Firewall
Autobots are Autessa agents. Companies that want turn-by-turn inspection for prompt injection and data exfiltration across their agents can add the Autessa AI Agent Firewall.
FAQ
Security questions
Is it safe to let an AI assistant use my email and apps?
Autessa Autobots use only the apps chosen for each one, work within the permissions of the person chatting, and ask before sending, buying, deleting or posting. Every Always allow can be removed.
Does an Autobot see my passwords?
No. Passwords and codes go through a secure form straight to the Autobot’s browser and are never shown in the chat. Sensitive answers can be sent privately, typed hidden.
Can other people see my Autobot’s browser or chats?
No. The live browser view shows only your own browser, and each person keeps their own chats, even with a shared Autobot.
Where are Autessa’s certifications and security documents?
On the Autessa Trust Center at trust.autessa.com.
100% customizable, code and all
Make Autessa Autobots fully your own.
Use it out of the box, then change anything. Ask Autobot, Autessa’s AI builder, for a new field, screen, report, workflow or agent and it builds it into your copy of the app. Or open the code and edit it yourself. Nothing is locked: the app, its data and its code are yours.
Start free and make it yours