# Turn Amazon Marketing Cloud Workflows into Skills

Canonical page: https://www.kuudo.com/guides/amc-agent-workflows/

Package Amazon Marketing Cloud workflows as agent Skills with query inputs, privacy checks, interpretation, approval policy, and repeatable run logs.

Author: Thomas Spicer
Updated: Oct 19, 2026

## Summary

Repeatable Amazon Marketing Cloud (AMC) workflows should be packaged as Skills only after the agent can run a 6-step contract: retrieve, resolve, check, produce, review, and log. The reusable unit is not a prompt; it is a reviewed workflow contract with 2 boundaries, read-only analysis and approval-gated writes.

Automating Amazon Marketing Cloud (AMC) workflows means packaging the query, input checks, privacy constraints, interpretation, and approval policy as a versioned agent Skill. Kuudo retrieves the relevant operator playbook, verifies that the request is sufficiently specified, runs the approved tools, and preserves a run log so the same analysis can be reviewed and repeated.

The operator question was practical: *"We keep asking for the same AMC analyses. Can the agent remember the workflow instead of improvising every time?"*

Yes, but the reusable unit should be a Skill, not a prompt snippet. A prompt remembers wording. A Skill remembers the steps: retrieve the right [Amazon Marketing Cloud](/features/amc/) (AMC) playbook, choose the table, run the privacy or size check, produce the artifact, route the decision, and log what happened.

## Why prompt-only AMC workflow automation breaks

> **Four ways an un-grounded workflow turns brittle**
> 1. It stores a generic "run AMC analysis" prompt with no table-selection rule.
> 2. It forgets that measurement and audience activation can require different table variants.
> 3. It treats every output as read-only, even when the next step changes a DSP audience or budget.
> 4. It has no run log, so the team cannot reproduce which parameters or rules produced the result.

That is how a helpful demo becomes an unreviewable production process.

## What an AMC workflow must retrieve before it runs

The agent starts by pulling the relevant Amazon Marketing Cloud playbooks from [Amazon Agent Atlas](/features/agent-atlas/). For an audience workflow, it retrieves:

- The audience-source rule that decides whether the Skill can use an audience-safe table.
- The sizing pattern that tells the operator whether the seed can activate.
- The activation timing and companion measurement guidance that belong beside the output.
- The **AMC synthetic data** playbook context when the Skill needs a safe test surface before it touches production workflows.

For a measurement workflow, it retrieves the attribution table, lookback rule, and caveats that belong in the output.

The [Amazon Ads MCP](/features/amazon-ads-mcp/) gives the Skill live access to the Ads and AMC surfaces. Atlas tells it what the current playbook says before it acts.

## Package the AMC workflow as a versioned agent Skill

The useful output is a workflow contract:

```json
{
  "skill": "amc_audience_workflow",
  "mode": "read_then_approve",
  "steps": [
    "retrieve_atlas_playbook",
    "resolve_table_window_filters",
    "run_privacy_and_seed_checks",
    "produce_sql_or_payload",
    "request_approval_for_writes",
    "write_run_log"
  ],
  "writeBoundary": "approval_required_before_dsp_activation"
}
```

That contract is deliberately more boring than an open-ended chat. Boring is what makes it repeatable.

## Which checks belong in every automated AMC workflow

> **The Skill should preserve these details every time it runs**
> - Which Atlas chunks grounded the workflow.
> - Which MCP tools were called and with which parameters.
> - Whether the output was read-only or write-capable.
> - Which approval policy applied.
> - Which user approved or rejected the action.

Those details are the difference between "the agent said so" and "we can audit the workflow."

## What happens next

The full workflow runs through the [Amazon Agent Data layer](/features/amazon-agent-flow/): Amazon Ads MCP brings AMC and demand-side platform (DSP) campaign signals, the [Selling Partner MCP](/features/amazon-selling-partner-mcp/) can add catalog context, Atlas grounds the operating procedure, and [Skills](/features/skills/) turn the workflow into a reviewed recurring automation.

Once the Skill exists, the same workflow can run from chat, code, or an automation tool. The interface changes; the source rules and approval gates do not.

## Why repeatability matters more than one successful query

A Skill is how an agent stops improvising an operating procedure.

*Next: put a [human approval gate](/guides/human-approval-for-amc-activation/) in front of activation, so a Skill that builds an audience never ships it to DSP unreviewed.*


## Frequently asked questions

### What makes an AMC workflow a Skill instead of a prompt?

A Skill fixes the retrieval step, table-selection rule, checks, approval policy, output shape, and run log. A prompt only preserves wording.

### Should every AMC Skill be allowed to write?

No. Measurement Skills can stay read-only. Skills that create audiences, alter budgets, or change targeting should require approval before the write step.

### What should the Skill log every time it runs?

Log the Skill version, retrieved Atlas chunks, MCP tool parameters, generated artifact hash, checks, approval state, and final result.

### How does the Selling Partner MCP fit an AMC Skill?

It adds catalog and Amazon Standard Identification Number context when the AMC workflow depends on product eligibility, listing state, or promoted-item scope.

### Why does a Skill need Atlas retrieval if the SQL is already saved?

The saved SQL is only one artifact. Atlas retrieval keeps the table rules, privacy notes, and workflow constraints visible when the Skill reruns.


## Sources

- [Amazon Marketing Cloud product overview](https://advertising.amazon.com/solutions/products/amazon-marketing-cloud/)

- [Amazon Marketing Cloud APIs are now part of the Amazon Ads API](https://advertising.amazon.com/resources/whats-new/amc-api-available-on-amazon-ads-api/)

- [Amazon Marketing Cloud custom audience creation and activation](https://advertising.amazon.com/en-gb/resources/whats-new/amc-custom-audience-creation-and-activation)