> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ones1ght.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Analytics / Actions

> Analyze store data in natural language and turn the answers into actionable policies.

## Analytics / Actions

**Analytics / Actions** is a conversational screen where you ask questions about your store data in natural language, and the AI returns root-cause analysis together with recommended, actionable policies.
A **"Recommendation L2 · Execute after approval"** badge appears at the top: the AI only proposes policies, and actual execution happens after a member approves.

> [!NOTE]
>
> This page is visible to every member of your organization (Owner, Manager, and Member).

## Analysis flow

**1. Select a Skill**

Choose the OneS1ght Skill used for analysis. The default is **"Sales Equation Analysis"**,
and the **＋ Store** button opens the [Skill Store](/en/console/agent/skill-store) to install a new Skill.

**2. Select an AI platform (BYOK)**

Choose the AI platform that runs the analysis — Claude, GPT, or Gemini. Each shows a key-status
badge (**Key connected / Server key / No key**). Platforms with no key are disabled; manage keys
in [Settings](/en/console/agent/llm-models).

**3. Enter your question**

Type your question in natural language. You can attach **up to 5 files**; text files have their
contents included in the analysis, while other files contribute their filename only.

**4. Register a policy**

Register a policy from the answer (see below).

> [!NOTE]
>
> Responses received without a connected BYOK key are marked with a **"Sample response"** badge.

## From answer to policy

You can register two types of policy directly from an AI answer.

| Type | Target | Action |
| - | - | - |
| 🏢 B2B store-manager policy | Store operations improvement | Register with an Action Agent → confirm the rule |
| 📱 B2C customer-app policy | Persona-based personalization | Delivered via the customer app (SDK) → register as "Provide to smartphone" |

Example personas: teens / women 20s–30s / returning / new.

## Recommendation → Execution (right panel)

Handle recommended policies in the **"Recommendation → Execution"** panel on the right.

> **Approve and execute**
>
> Approving a recommendation moves the policy into execution.

> **Edit**
>
> Edit the recommendation before registering it.

Policy status: **proposed / approved / dismissed**.

## Running a policy on an event zone

> Console menus: **Natural Language Query** → **Initiatives** → **Spaces**

In the **suggestion card** shown beside the answer, press **\[Add to action management]** to register it in your policy list.
When you **run (activate)** that policy, the target **event zone is created and automatically mapped into [Space Management](/en/console/areas)**.

**1. Ask and review the suggestion**

In the **Natural Language Query** menu, ask in natural language — the answer appears with a suggestion card (target, expected impact) on the right.

**2. Add to action management**

Press **\[Add to action management]** and it appears in the **Initiatives** menu. ([details](/en/console/agent/action-agents))

**3. Run → applied to the space**

Activating the policy in **Initiatives** creates the event zone and maps it onto the floor plan in the **Spaces** menu —
no manual drawing required.

> [!TIP]
>
> Zones created this way are also **detected within seconds** by any app with the SDK integrated.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.