# Agents

Agents are AI-powered processes that act on different parts of the platform to enhance your planning. Each agent is displayed as a card showing its description, run frequency, and next scheduled run. Some agents run automatically on a schedule (daily or weekly), while others are triggered manually.

### Available agents

#### Demand Anomaly Agent

Automatically identifies and replaces anomalies in your historical demand with more relevant, context-aware values — ensuring the accuracy of the data that feeds your forecasts. The agent runs **weekly** and provides a summary of all adjustments it has made, broken down by anomaly type:

* **Outliers** — Unusual demand peaks that don't reflect typical customer demand patterns.
* **Shortages** — Stockout periods where zero demand occurred due to product unavailability rather than lack of demand (e.g. "0 stock and 0 demand") or periods when inventory below lot size artificially suppressed sales ("stock < lot size").
* **Smooth past promotions** — Smooths out promotional spikes to give a cleaner baseline.

For each anomaly type, you can see the count of adjustments along with their acceptance status (Accepted, Rejected, Not treated, Modified).

#### Forecast Agent

Your AI-powered forecasting companion. The Forecast Agent runs **weekly** and powers Flowlity's probabilistic forecasting engine, continuously learning from your data to improve forecast accuracy over time.

#### Product Similarity Agent

Finds the top 5 most similar products for each item in your catalog. Runs **weekly** and is especially valuable for new or sparse products — when a product has little or no demand history, the similarity agent identifies analogous products to bootstrap a reliable forecast. You can configure whether similar products are included in or excluded from the agent's scope.

#### Planning Agent

Recommends the best quantities and dates for optimized supplies. The Planning Agent runs **daily**, taking into account your forecasts and risk assessment through buffers to generate the most optimized supply plan while respecting all your constraints and needs. It provides a summary of the order lines and total value it has generated.

#### Pricing Research Agent

Evaluates market conditions and demand elasticity, recommending strategic prices that maximize revenue. This agent runs **manually** — you select a product, provide its current price and description, and optionally focus on a specific competitor. The agent then performs a competitive intelligence analysis (e.g. via Google Shopping) and returns a detailed report including:

* **Executive Summary** — Product overview and key metrics at a glance (market position, your price vs market median, price range, number of competitors analyzed).
* **Strategic Insights & Recommendations** — AI-generated pricing recommendations based on competitive intelligence.

<figure><img src="/files/ARqN3A8dFyvmBajzvgRh" alt=""><figcaption></figcaption></figure>

### Agent detail view

Clicking on an agent card opens a panel with two tabs:

* **How it works** — Explains what the agent does and shows a summary of its latest results (e.g. total adjustments made, order lines created). Some agents also include a "See the agent in action" video.
* **Configuration** — Displays the agent's settings. For the Demand Anomaly Agent, this lets you activate or deactivate specific anomaly types and choose whether events are accepted **automatically** or **manually**. Configurations are currently read-only for most agents.

### When to use it

Most agents work in the background, so you don't need to interact with them daily. Use the Agents module to monitor their status, review their latest results, and understand the insights they surface. For the Pricing Research Agent, use it on demand whenever you need a competitive pricing analysis for a specific product.

### Learn more

* [Demand forecasting explained](/concepts/demand-forecasting.md) — How the Forecast and Similarity agents power the AI forecast.
* [Forecast events and demand adjustments](/concepts/forecast-events.md) — How the Demand Anomaly Agent interacts with events and corrections.
* [Investigate and fix demand anomalies](/how-tos/investigate-demand-anomalies.md) — Review and act on agent suggestions.


---

# Agent Instructions: 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:

```
GET https://docs.flowlity.com/modules/agents.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.