> For the complete documentation index, see [llms.txt](https://docs.smaq.io/documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.smaq.io/documentation/features/media-plans/intelligence.md).

# Media Plan Intelligence

Media Plan Intelligence is an AI automation that runs against a [media plan](/documentation/features/media-plans.md) on a schedule (usually weekly). It reads:

* The plan's flight, total budget, and KPI targets.
* Actual spend and performance per channel from your connections.
* Pacing and performance gaps.

Then it generates a recommendation — usually a specific reallocation between channels.

### Example output

> "Meta is underpacing at 62% of plan with ROAS at 4.5. Google Ads brand is overpacing at 118% with ROAS at 1.9. Recommend shifting $1,500/week from Google Ads brand to Meta prospecting. Net ROAS estimate: 2.8 → 3.2."

The recommendation is human-readable, references specific channels and dollar amounts, and shows the projected impact.

> **\[Screenshot needed]** Media Plan Intelligence email showing the structured recommendation: situation summary, specific actions, projected impact.

### Setup

Once you have a [media plan](/documentation/features/media-plans/create.md):

1. Open the plan detail page.
2. Click **Add automation → Media Plan Intelligence**.
3. Set recipients (the marketing operator, usually) and a weekly schedule.
4. Save.

The plan now has an attached MPI automation. It runs on the schedule, but you can also click **Run** to trigger immediately.

### What the agent considers

* **Pacing** — actual spend vs plan, week by week.
* **Performance** — actual KPIs vs targets.
* **Trend** — improving or deteriorating week-over-week.
* **Saturation signals** — borrows from [Audience Decay Monitor](/documentation/features/creative-intelligence/audience-decay-monitor.md) and [Ad Fatigue Detector](/documentation/features/creative-intelligence/ad-fatigue-detector.md) if those automations are running on the same connections.
* **Flight remaining** — time-weighted; recommendations get more aggressive as flight end approaches.

### What it doesn't do

* **Auto-execute changes.** All recommendations are advisory. SMAQ never spends your money on its own.
* **Override your strategic intent.** If you've notes saying "minimum 30% in Meta for brand," it respects that.
* **Account for off-platform context** SMAQ can't see — competitor launches, supply chain, news. Human judgment still required.

### Tips

* **Run weekly, not daily.** Daily recommendations are noisy because per-day variance dominates per-week trend.
* **Read the recommendation, then check it against your gut.** Most weeks, MPI is right. The 10% where it's wrong, your judgment catches it.
* **Document why you didn't take a recommendation.** Future-you will appreciate the breadcrumb.

### Tier availability

* **Scale & Agency** — fully available.
* **Starter, Growth** — not available.

### Related

* [Media Plans overview](/documentation/features/media-plans.md).
* [Budget Pacing Alert](/documentation/features/automations/reference.md#budget-pacing-alert) — pacing-only alerts (lighter than MPI).
* [Command Center](/documentation/features/command-center.md) — cross-plan view for agencies.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.smaq.io/documentation/features/media-plans/intelligence.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.