> For the complete documentation index, see [llms.txt](https://docs.phocassoftware.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.phocassoftware.com/workspaces/workspaces.md).

# Workspaces

Learn about Workspaces, a new AI-powered way to explore, understand and act on your business data.

{% hint style="info" %}
This feature is currently under active development. Functionality and user interface elements are subject to change.

See [Limitations and FAQs](/workspaces/workspaces/limitations-and-faqs.md) for current limitations and answers to common questions.
{% endhint %}

Workspaces is an AI-powered conversational experience for exploring and investigating your business data, powered by Phocas PACE. Ask questions in everyday language and get answers, summaries, and supporting data based on the same data you already use in Phocas.

<details>

<summary>What is PACE?</summary>

PACE is Phocas's AI capability. It combines generative AI with your business data and context to help you ask questions, investigate results, and understand what's happening in your business.

Workspaces is powered by PACE, which is designed to support other AI-powered experiences across Phocas over time.

</details>

Start with a broad question, then ask follow-up questions to investigate the result. Workspaces uses the context of the conversation, so you can progressively narrow your questions, explore what's changed, investigate an anomaly, or investigate the customers, products, or regions behind a result.

For example, start by asking *Summarize my top-performing products this quarter*. You can then ask which customers or regions contributed to the result, why a particular product changed, or what else stands out.

Workspaces combines AI-generated responses with Analytics grids. You can review the data supporting a response, then continue your analysis in Analytics when you want to explore it in more detail.

You can also edit an earlier question to take the conversation in a different direction. This creates an alternative path while keeping your existing questions and results, making it easier to compare different approaches to an investigation.

### Open Workspaces

Click **Workspaces** in your Phocas navigation menu. This is available in the new experience.

<figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2FiqtMJLda5YzyLQdK1zfi%2Fimage.png?alt=media&#x26;token=6531e013-b0aa-49a0-becd-f37d18ab1c9a" alt=""><figcaption></figcaption></figure>

The chat page opens, displaying a message box for entering questions and some suggested prompts to help you get started.

The panel on the right contains:

* A list of recent chats. When available, click a chat to revisit the response or ask follow-up questions.
* A **New** button you can click to start another chat on a different topic.

You can close this panel until you need to use it.

<div align="left"><figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2FBZBtLp7I5o0ISV1ANYcc%2Fimage.png?alt=media&#x26;token=2bd0a9a7-70e0-40b7-9161-8d4585e62902" alt="" width="375"><figcaption></figcaption></figure></div>

### Ask questions

Use one of the system prompts or enter a question in the chat box and press **Enter** or click **Send**.

As the response is generated, you can see the steps Phocas takes to answer your question, including how it gathers and analyzes information.

When data is retrieved, the response includes one or more grids containing the underlying data. The response also includes a confidence status and information about where the data comes from.

You can continue a conversation by asking follow-up questions. Either continue in the chat that's open, or open a previous chat from your Recent chats panel. You don't need to repeat all the details in each question. Phocas uses the previous conversation as context, allowing you to progressively refine your analysis.

{% tabs %}
{% tab title="Example: Analyse sales performance" %}

#### Use a prompt

Click the prompt under the chat box: *Summarize my top performing products this quarter*.

PACE analyses the relevant sales data, provides a summary, and displays a supporting grid.

<figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2FOpxj4NjYabMaKaEyvkK5%2Fimage.png?alt=media&#x26;token=b2e71630-7077-4bea-8665-223fb3432cd8" alt=""><figcaption></figcaption></figure>

#### Ask follow-up questions

After reviewing the product summary, continue with the chat to drill into the product data.

Ask:

* *Which products are growing fastest?*

<div align="left"><figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2FOxQZcAqwNOejNacYcM57%2Fimage.png?alt=media&#x26;token=66c5e428-8ea9-482b-a216-681239f9fbb2" alt=""><figcaption></figcaption></figure></div>

* *Compare those products against last quarter.*

<div align="left"><figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2Fm5Xc38dAJ7aYFmQ7RSeg%2Fimage.png?alt=media&#x26;token=2d74c36c-836b-45b6-9815-859be065eb2a" alt=""><figcaption></figcaption></figure></div>
{% endtab %}

{% tab title="Example: Investigate a sales rep" %}

#### Ask your own question

Ask: *Tell me about \[insert sales rep name]*.

Although the question is broad, PACE attempts to identify the person and gather relevant information, such as:

* Performance metrics
* Top products
* Related sales activity
* Comparative insights

The response might include multiple grids and a summary of findings.

<figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2Fu3mH0Z4InojPyCNR0SNL%2Fimage.png?alt=media&#x26;token=650974f0-818a-4c42-9839-8f34b6ae749f" alt=""><figcaption></figcaption></figure>

#### Ask a follow-up question

After reviewing the sales rep's performance, continue with the chat to better understand the context of their performance.

Ask: *Compare him against his colleagues*.

<figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2FRsL6wD2K3Bkz9V4QpBkk%2Fimage.png?alt=media&#x26;token=a622e4b7-80cc-4006-beb5-7874058e50a8" alt=""><figcaption></figcaption></figure>
{% endtab %}
{% endtabs %}

### Analyze or download the grid data

When a response includes a grid, you can download and analyze the data in contains.

<div align="left"><figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2F40LSKcBfk309abEXqbzm%2Fimage.png?alt=media&#x26;token=381632fc-4952-413b-ba48-848091b53fb4" alt=""><figcaption></figcaption></figure></div>

Click **Analyze** to open the underlying data in Flex Modes, where you can:

* Validate the AI-generated response.
* Explore the data further using the Flex Modes tools, for example you might want to apply additional filters. You can also save the [view as a favorite](/flex-modes/save-and-share-your-work/save-and-share-favorites.md) or add it as a widget on a dashboard.

<figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2FKt3YOlfSFKToGztAHbi0%2Fimage.png?alt=media&#x26;token=628ef77f-b0d4-475e-93b3-10b8d4a992cb" alt=""><figcaption></figcaption></figure>

Click the **Download** button to download the grid in SGV format, which opens in a new browser tab.

<div align="left"><figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2Ft17bNTJ0eNx5AC6Hcz8T%2Fimage.png?alt=media&#x26;token=ba04c0a3-4f6e-48e6-ac93-b6a232eb8392" alt="" width="563"><figcaption></figcaption></figure></div>

### Create a chart

When a response includes a grid, you can ask a follow-up question to convert the grid into a chart, so you can visualize the data instead.

For example, ask something like *Put it in a bar chart* or *Make me a pie chart*.

You can also ask for a chart in your initial question. If you're not sure what type of chart you want, ask for a generic chart to get started.

<div align="left"><figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2Fgit-blob-e61ee8c9f6f679ef41388d96a27b719dc00297a1%2Fimage%20(691).png?alt=media" alt="" width="563"><figcaption></figcaption></figure></div>

You can then edit your question (see below) to ask for a specific type of chart.

<div align="left"><figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2Fgit-blob-1cab8c63eb7a49bc0c1739e76d1e260eb6a273f0%2Fimage%20(694).png?alt=media" alt="" width="563"><figcaption></figcaption></figure></div>

Ask the chat for a list of chart types and try them all out.

<div align="left"><figure><img src="https://900295827-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F7pj8v25BOyqZTdG5mdD1%2Fuploads%2Fgit-blob-0d292d3dd9d495da7bc923c75661eeb52a8a2fac%2Fimage%20(695).png?alt=media" alt="" width="563"><figcaption></figcaption></figure></div>

### Personalize your chats

Personalize PACE so its responses better reflect your role and how you work. Your personalization applies across chats within Workspace.

1. Click **Settings** at the bottom of the **Recent chats** panel.
2. Select the option that best describes your work. For example, select **Sales** if you're a sales representative.
3. Enter any information you want Phocas to keep in mind when responding to your questions. For example, you might specify the type of data you typically analyze or how you prefer responses to be presented.
4. Close the **Personalization** page.

Update your personalization when your role or standing instructions change.


---

# 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.phocassoftware.com/workspaces/workspaces.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.