# Tips for getting the most out of ScaleFlows

<details>

<summary><strong>Start with approval mode.</strong></summary>

Let the AI draft replies but review them for the first week. This builds your confidence and helps you refine policies.

<div align="left"><figure><img src="/files/le1BVoykWwFmbZxp1t8z" alt=""><figcaption></figcaption></figure></div>

</details>

<details>

<summary><strong>Use the "Try the AI" panel often.</strong></summary>

After changing any setting or policy, test it immediately.

<div align="left"><figure><img src="/files/OGP7HPL9v3Ci9KdIdEF8" alt=""><figcaption></figcaption></figure></div>

</details>

<details>

<summary><strong>Add AI context to your top products.</strong> </summary>

The more the AI knows about your products, the better its answers.

<div align="left"><figure><img src="/files/Zt46RO2cb02rf8xPORJT" alt=""><figcaption></figcaption></figure></div>

</details>

<details>

<summary><strong>Check Analytics regularly.</strong></summary>

&#x20;Look at auto-send rate and escalation rate to see where you can improve.

<div align="left"><figure><img src="/files/4iv0xuTanS3iJHQqXXzB" alt=""><figcaption></figcaption></figure></div>

</details>

<details>

<summary><strong>Set up Slack or Discord notifications.</strong> </summary>

So you know immediately when something needs your attention.

<div align="left"><figure><img src="/files/SeIDJyp8a5CbjuRMNtOw" alt=""><figcaption></figcaption></figure></div>

</details>

<details>

<summary>Use <strong>templates for complex replies.</strong> </summary>

<div align="left"><figure><img src="/files/jmBbfUKGxBGhUDpCHkge" alt=""><figcaption></figcaption></figure></div>

Even when writing manually, templates with placeholders save time.

</details>

<details>

<summary><strong>Keep your knowledge base updated.</strong> </summary>

When policies change, update the AI's knowledge so it stays accurate.

<div align="left"><figure><img src="/files/kd8dX7RbI7b6mCL733Xs" alt=""><figcaption></figcaption></figure></div>

</details>


---

# 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.scaleflows.net/documentation/documentation-v1.1/resources/tips-for-getting-the-most-out-of-scaleflows.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.