# How AI Marketing Agents Work: Goals and Controls

Canonical page: https://2bcome.ai/how-it-works/
Content updated: 2026-09-15

THE OPERATING MODEL

# Give it a goal. Keep it accountable.

A useful agent should observe, plan, act within its permissions, and review the outcome. Here is how we are designing that loop.

[Run the sample workflow](https://2bcome.ai/how-it-works/#demo) [Read the design notes](https://2bcome.ai/docs/)

THE CONTINUOUS LOOP

## The task ends. The goal remains.

The next action should follow from the current state and the evidence. When the data is insufficient or the action is outside the allowed scope, the agent should ask or stop.

INTERACTIVE PRODUCT DEMO

### From signal to reviewed change.

SAMPLE DATA

Run a simulated content-refresh workflow. No website, account, or AI service is connected.

- 01 Observe
- 02 Plan
- 03 Review
- 04 Validate

ACTIVITY LOG

Ready. Start the example to see the workflow.

PROPOSED DIFF

/guides/agent-workflows

- A generic opening paragraph

+ A precise explanation of the workflow

+ An example with approval checkpoints

+ A link to the permissions guide

The scope excludes pricing, legal pages, credentials, and deployment settings.

Run sample workflow Reset Waiting to start

THE RULES OF THE LOOP

## A system needs more than a prompt.

01

### A defined workspace

Give each agent the files, data, and actions its job requires. Keep everything else outside the boundary.

02

### A checkable output

The output needs to be a draft, a diff, a brief, or a report that someone can inspect.

03

### A stop condition

Pause after repeated failures, uncertain facts, exhausted budgets, or missing approval.

COMMON QUESTIONS

## Less mystery. More control.

**Will the agent publish without asking?**

The proposed starting mode is review before publishing. Broader autonomy should only be enabled for explicitly allowed actions after the workflow is tested.

**Is this the live product?**

No. The page describes the operating model we are building. The interactive workflow uses sample data and does not call a model or change a website.

**What happens when a check fails?**

The workflow should stop, record the failure, and either try a bounded repair or ask for help. The exact retry and spending limits belong in its configuration.

**Can I inspect what changed?**

The planned Git-first workflow is designed to preserve a diff, a test result, an approval record, and a deploy revision. These are product requirements, not a claim that the backend is already built.

START SMALL. BUILD FROM THERE.

## A useful first job. Not a giant transformation.

Tell us what needs doing. We will start with a goal, a boundary, and a way to judge the result.

[Explore early access](https://2bcome.ai/request-access/)

CONNECTED WORK

## The next useful connection.

GUIDE

### [Plan Your First AI Agent Workflow](https://2bcome.ai/docs/getting-started/)

A guide to framing the first pilot: choose the job, define the permissions, and agree how the result will be reviewed.

[Explore](https://2bcome.ai/docs/getting-started/)

GUIDE

### [AI Agent Approvals and Permission Boundaries](https://2bcome.ai/docs/approvals-and-permissions/)

The proposed rules for what an agent may read, prepare, change, and publish, with defaults that keep sensitive actions out of scope.

[Explore](https://2bcome.ai/docs/approvals-and-permissions/)

GUIDE

### [AI Agent Audit Trails and Website Rollback](https://2bcome.ai/docs/audit-and-rollback/)

The proposed audit record connecting a goal, evidence, draft, approval, tests, and deployed revision.

[Explore](https://2bcome.ai/docs/audit-and-rollback/)