> For the complete documentation index, see [llms.txt](https://nationgraph.gitbook.io/nationgraph/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://nationgraph.gitbook.io/nationgraph/help-center/readme/workspaces/workspace-summary.md).

# Workspace Summary

Summarize smart columns into a new column for talking points, “asks”, and next steps.

Click here to watch [video](https://screen.studio/share/UEucFjp8).

{% embed url="<https://screen.studio/share/UEucFjp8>" %}
Workspace Summary Tutorial
{% endembed %}

### What Workspace Summary does

Workspace Summary creates a new column that summarizes other columns. You select up to **3 smart columns** as inputs. You write instructions in an input field. NationGraph writes the output into a new column.

Use it when you want consistent, repeatable “so what?” outputs.

### Create a Workspace Summary column

{% stepper %}
{% step %}

#### 1) Add the column

Click **Add column**. Select **Workspace Summary**.
{% endstep %}

{% step %}

#### 2) Pick your input columns

Select **3 smart columns** to summarize. Pick columns with complementary context.

Good combos:

* intent signals + account notes + contract intel
* stakeholders + current activity + objections
* RFP activity + contract intel + fit score
  {% endstep %}

{% step %}

#### 3) Write what you want generated

In the prompt input, describe the output format and purpose.

Example prompts:

* “Summarize these columns into 5 call prep talking points. Add 3 questions to ask.”
* “Generate a list of the top 5 asks for discovery. Keep each ask under 12 words.”
* “Write a one-paragraph brief. End with the likely renewal window.”
  {% endstep %}

{% step %}

#### 4) Generate into an output column

Choose the destination column. Generate the summary. Re-run after you update the input columns.
{% endstep %}
{% endstepper %}

{% hint style="info" %}
Keep inputs tight. More than 3 columns usually reduces quality.
{% endhint %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://nationgraph.gitbook.io/nationgraph/help-center/readme/workspaces/workspace-summary.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.