AppsAutobots

You stay in control

Permissions and guardrails

Autessa Autobots work within the person’s permissions, are available to roles allowed to use agents, and build only what was explicitly asked for.

Autobots work within your permissions, only for roles allowed to use agents, build only what you asked for and draw on your company’s AI credit limits.

Guardrails · every AutobotSAMPLE
Who can use itPeople whose role can use agents
What it can reachOnly what the person chatting can reach
Which appsOnly the apps and MCP servers you picked
What it buildsOnly what you explicitly asked for
Before it actsAsks before sending, buying, deleting or posting
UsageDraws on your company’s AI credit allowances

The problem it solves

Why it matters

Rolling out AI at work raises the same questions every time: who can use it, what it can reach, and what stops it from doing too much.

How it works

How permissions and guardrails works, step by step

  1. 1

    Turn it on for roles

    Autobots are for people whose role can use agents.
  2. 2

    It acts as the person

    Within that person’s permissions.
  3. 3

    Narrow its reach

    Only the apps and MCP servers chosen for it.
  4. 4

    Keep a hand on it

    Approvals, secure forms and an editable memory.

Options and settings

Every option, in one place

OptionWhat it does
Role accessWho can use Autobots.
Own permissionsWhat it can reach.
Apps and MCP serversPer Autobot.
Only what you askedIt suggests and waits for your yes for anything you did not ask for.
AI creditsDraws on your company’s daily and weekly allowances.
Own browser onlyPeople see only their own browser.

Roles and permissions

Who can do what?

WhoWhat they can do
Company adminsDecide which roles can use agents and set usage limits.
Everyone elseUses Autobots within their own permissions.

AI assist

How the Autobot helps

Every Autobot is told to build only what was explicitly asked for, and to describe anything else it would make and wait.

Connected features

How it connects to the rest

Approvals before it acts →Asks before acting.Secure forms and private answers →Passwords never in chat.Autessa AI Agent Firewall →Company-wide AI agent security.

FAQ

Questions about permissions and guardrails

Who can use Autessa Autobots?

People whose role can use agents. Each Autobot works within the permissions of the person chatting.

Can an Autobot build things I did not ask for?

No. When building something would help but you did not ask, it says what it would make and waits for your yes.

How is AI usage controlled?

Autobots draw on your company’s AI credit allowances, which admins see in Usage and limits.

Try it with your own work.

Permissions and guardrails is part of every Autessa Autobot. Meet yours and hand it something real.

Included in every Autessa account · it asks before it sends, buys or deletes anything

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