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

# Agent Columns

Agent Columns let you enrich any segment or list with the exact tech-GTM signals you care about, right inside your Accounts view. Instead of running a separate agent and jumping between screens, you describe the signal you want in plain language, and Reo adds it as a new column against every account in your segment or list.

Here's a complete guide on how to add, manage, and filter Agent Columns.

### What you can add as a column

An Agent Column can answer almost any question you'd ask about your accounts. A few common types:

* **Enrichment signals** like "add the number of DevOps engineers for my list"
* **Qualification signals** like "which companies are doing cloud migration from my list"

Each column is created by an agent, and one agent creates exactly one column. Supporting details, reasoning, and evidence live inside that column and open up when you expand a value. (more on that below)

{% hint style="info" %}
The **Agent Column** feature works on any segment or list, including segments that have been shared with you. It is not currently available on the “**All Accounts”** list or in any segment or list with more than 10,000 accounts.
{% endhint %}

### Adding a column

**Step 1:** Open the segment or list you want to enrich.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FaT0H4MSBoRhIScR3dbUs%2FScreenshot%202026-10-05%20at%204.04.47%E2%80%AFPM.png?alt=media&amp;token=827cdf1d-1ebd-4f85-8374-b3033c69ad46" alt=""><figcaption></figcaption></figure>

**Step 2:** Click **Enrich with Agent** to get started.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FPuTpSUjMaRWH6vEeYITF%2FScreenshot%202026-10-05%20at%204.05.54%E2%80%AFPM.png?alt=media&amp;token=c3677e5b-99ab-40fa-a5ff-977b30c666af" alt=""><figcaption></figcaption></figure>

This opens the **Enrich with an Agent** modal.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FZZLG6wz9j2l0F0Z9scQg%2FScreenshot%202026-10-05%20at%204.07.10%E2%80%AFPM.png?alt=media&amp;token=6587f5fb-2971-4ed8-88c7-101ccd8e0080" alt=""><figcaption></figcaption></figure>

From here, you have a few ways to build your column:

* **Write a prompt:** Describe the signal you want as a column.
* **Try our agent library**: Pick a prompt from one of our multiple use-case-specific prompt library options. [Here's](https://docs.reo.dev/agents/agent-columns/agent-library) a detailed guide on how to use our agent library.
* **Choose from an existing prompt:** Select from the three prompts personalized to your workspace if you'd rather start from an example.
* **Add an existing agent column:** Reuse an agent column you already created on another segment or list.
* **Chat with an agent:** Open a conversation to refine exactly what the column should capture.

{% hint style="info" %}
Choose between Reo data and Public data. Reo data draws on Reo's proprietary account signals and is selected by default. Public data searches news, filings, and blogs, so it is the better choice for signals like SOC 2 certifications or SEC filings.
{% endhint %}

#### 1) Prompt to Column

**Step 1:** Type your prompt, pick your data source, and click **Add agent column**.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FNjgCE3Zc8SLyRXNO08ef%2FScreenshot%202026-10-06%20at%2010.35.57%E2%80%AFAM.png?alt=media&amp;token=4f3c2ae7-f17c-4acd-b8bb-5d5ef9df5048" alt=""><figcaption></figcaption></figure>

**Step 2:** A loading screen walks you through the steps, so you can see how it's reasoning through your request.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2F4CougyzhOyKYnEnMVsfr%2FScreenshot%202026-10-06%20at%2010.36.39%E2%80%AFAM.png?alt=media&amp;token=f8997978-a64b-49cc-8f2d-9f45e262f5a5" alt=""><figcaption></figcaption></figure>

**Step 3:** Review the **Preview & Save** screen. This is where you confirm what's about to be added before any credits are used.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2Fk2Yb00wzDHe4Wqe9yJrp%2FScreenshot%202026-10-06%20at%2010.38.21%E2%80%AFAM.png?alt=media&amp;token=3c022979-ada9-4bd8-bd53-bd0297480ab1" alt=""><figcaption></figcaption></figure>

**a. The column:** The agent identifies the single column your prompt is asking for and names it. Column names are set by the agent and are not editable. Any supporting columns, reasoning, and evidence are rolled into this one column and can be opened later from the Accounts list.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2Fd60B0i9IlDnD7SHVtVno%2FScreenshot%202026-10-06%20at%2010.39.02%E2%80%AFAM.png?alt=media&amp;token=02fa7384-4c12-4a6f-8460-eeea2408bbd2" alt=""><figcaption></figcaption></figure>

**b. Preview and reasoning:** You'll see a sample of up to 5 accounts with the value the agent found for each. Click **View Reasoning** on any row to expand it and read the full reasoning. If the agent can't find data for the signal, you'll see a clear message saying so.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FA0W0TWMr2APr5kddaqBj%2FScreenshot%202026-10-06%20at%2010.40.09%E2%80%AFAM.png?alt=media&amp;token=58191d28-047c-4a5f-ae04-17d37a9475da" alt=""><figcaption></figcaption></figure>

**c. Automations:** Decide how the column stays current:

* **Auto Enrich New Accounts:** Any new account that enters this segment or list gets enriched with this column automatically.
* **Re-enrich All Accounts:** Refreshes the column across all accounts on a schedule. Choose weekly, monthly, quarterly, or do not re-enrich.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FWtZZbIip032a9xMTlNHT%2FScreenshot%202026-10-06%20at%2010.44.36%E2%80%AFAM.png?alt=media&amp;token=fc9646df-05bf-404e-bc6d-cdacc8d54e76" alt=""><figcaption></figcaption></figure>

**d. Credits estimation.** Reo shows the credits this column will use before you commit.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2Fvi9MaIyyF7ULOhCtmdQe%2FScreenshot%202026-10-06%20at%2010.45.22%E2%80%AFAM.png?alt=media&amp;token=10b4e1af-5e20-4d50-9b32-6cd15261fc7a" alt=""><figcaption></figcaption></figure>

**Step 4:** Click **Add agent column**. You're taken back to the Accounts Listing page, and the new column is added as the second column. You'll watch each account enrich in real time.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FXyyi99eU4VoIHkatQ0Hc%2FScreenshot%202026-10-06%20at%2010.46.16%E2%80%AFAM.png?alt=media&amp;token=e2e9195e-b2fb-4d0e-bf94-ba29eda32f5d" alt=""><figcaption></figcaption></figure>

The column is added to this segment or list only. It won't appear on your other segments automatically, but you can add the same column elsewhere whenever you want (see Add an existing agent column below).

#### 2) Chat with an agent

If you want to shape the column through conversation, click **Chat with agent** in the Add agent column modal.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FQyMMvmxntouXkAIR6Zmf%2FScreenshot%202026-10-06%20at%2010.47.33%E2%80%AFAM.png?alt=media&amp;token=eb50128f-fdae-4c25-bda3-89efec16400d" alt=""><figcaption></figcaption></figure>

This opens the same chat view used across Reo's Agents flows, pre-filled with your current session so you can pick up right where you left off. Keep chatting until the agent understands exactly what you want, then click **Enrich & Add Column**.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FpIgPc79qsg2EUTRuIUrl%2FScreenshot%202026-10-06%20at%2010.52.03%E2%80%AFAM.png?alt=media&amp;token=8ef2181f-d0d6-4ee9-a2cf-2de969f5f723" alt=""><figcaption></figcaption></figure>

You'll land on a **Preview & Save** screen with the column name, the automation settings, the credits estimation, and a preview of up to 5 accounts showing account name, agent tags, and the pre-filled column values. Here you can also edit the agent name and tag. Click **Enrich & Add Column,** and you'll be returned to the segment or list.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FuL5jCGDF6UD2VjlPPc8y%2FScreenshot%202026-10-06%20at%2010.53.04%E2%80%AFAM.png?alt=media&amp;token=88c93e46-c79d-46c8-b488-e8ae2eafb162" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
If you close the chat modal without saving, you'll land back on the previous Preview screen. Nothing is lost.
{% endhint %}

#### 3) Add an existing agent column

If you've already built a column somewhere else, you don't need to recreate it.

**Step 1:** In the Add agent column modal, choose **Add an existing agent column**. Reo lists every column created across your other segments and lists, showing the column name, the data type of its values, and the agent that created it.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FbmnUGPmamXlSo7v3Plja%2FScreenshot%202026-10-06%20at%2011.26.54%E2%80%AFAM.png?alt=media&amp;token=321f8cd2-cfae-4776-b39b-3b3d0d4d29dc" alt=""><figcaption></figcaption></figure>

**Step 2:** Pick a column. Reo opens the same Preview & Save screen used in the prompt flow, this time with 5 sample accounts from your current segment so you can see how the column fills here.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FKfnt1CWqk3Bd4TZ3XYXM%2FScreenshot%202026-10-06%20at%2011.27.45%E2%80%AFAM.png?alt=media&amp;token=ddfa60ac-cf41-4c56-b4f2-e6419ab9c86a" alt=""><figcaption></figcaption></figure>

**Step 3:** Set your automations (Auto Enrich New Accounts and Re-enrich All Accounts), review the credits estimation, and click **Add agent column**. You're redirected back to the segment or list, same as the prompt flow.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FVs6WpURt9OhqT8HoOKV9%2FScreenshot%202026-10-06%20at%2011.30.20%E2%80%AFAM.png?alt=media&amp;token=4bbdf4c1-e00d-4a07-b9d5-2c855fbe188e" alt=""><figcaption></figcaption></figure>

### Credits

You're only charged for accounts where Reo is able to fill in the data. Accounts the agent can't enrich don't cost you credits.

If you add an existing column to a new segment or list, the overlapping accounts are charged again for that new placement.

Reo shows a credits estimate on the Preview & Save screen before you confirm, so there are no surprises.

Building a segment from agent columns doesn't cost credits. The agent charges as usual when it runs on new accounts.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FtmsqP7tSR6yDJv5UDSu3%2FScreenshot%202026-10-06%20at%2011.31.24%E2%80%AFAM.png?alt=media&amp;token=da552dbb-7bcd-4b74-a298-f4efb1b5eb52" alt=""><figcaption></figcaption></figure>

## Working with Agent Columns&#x20;

{% hint style="info" %}
This section assumes you already have agent columns on a segment. \
*New to them?* Start by adding [Agent Columns](https://docs.reo.dev/agents/agent-columns#adding-a-column)
{% endhint %}

### **Build a segment from Agent Columns**

Agent columns tell you which accounts in a segment show a signal. Once you know that, you can turn the accounts that pass into their own segment and run buyer audiences, CRM sync, and workflows on that set instead of the whole segment. Your credits go to accounts that already qualify.

{% hint style="info" %}
Want to run workflows only on the accounts that pass? Follow these steps to build a segment from agent columns.
{% endhint %}

#### **Method 1: From an existing segment**

Use this when you want a tighter version of a segment you already have:&#x20;

1. Open the segment that has the agent column

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FlVSoohmbQDKmqdOZgOtd%2FScreenshot%202026-11-06%20at%2012.13.53%E2%80%AFPM.png?alt=media&amp;token=9a023fe2-dc67-44e5-acac-19478a79c668" alt=""><figcaption></figcaption></figure>

2. Click **Add Filter** and open the **Agent columns** group

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2Fdqh5qVyo1byHxYI69e6r%2FScreenshot%202026-11-06%20at%2012.14.36%E2%80%AFPM.png?alt=media&amp;token=e9691661-6243-4644-89f3-be51d28edb89" alt=""><figcaption></figcaption></figure>

3. Pick a column > set the condition, for example *Runs Kubernetes is Yes*&#x20;

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FfLuwjnFODMABge85F4XH%2FScreenshot%202026-11-06%20at%2012.16.27%E2%80%AFPM.png?alt=media&amp;token=2af64dda-c4d1-416f-b1dd-573c9f1795d1" alt=""><figcaption></figcaption></figure>

4. Click **Save as new segment**&#x20;

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2F59ulIbnyqyFxJDlMrI32%2FScreenshot%202026-11-06%20at%2012.16.53%E2%80%AFPM.png?alt=media&amp;token=33ae9480-f025-4477-8c6f-6c1a6388985e" alt=""><figcaption></figcaption></figure>

5. When you provide a name for the segment, you will notice that **the new segment keeps all of this segment's conditions and adds the agent column filter on top.**

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FrBafq84El3Ur0nVdbMmY%2FScreenshot%202026-11-06%20at%2012.18.21%E2%80%AFPM.png?alt=media&amp;token=50489939-08c0-40bc-83e5-86f79f739f9b" alt=""><figcaption></figcaption></figure>

#### **Method 2: From a new segment**

Use this when you want to combine agent columns with standard filters, or use columns from more than one segment:&#x20;

1. Go to **Segments** and click **Create segment**

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2F4iYpOHaJomIAhm4f7un2%2FScreenshot%202026-11-06%20at%2012.22.54%E2%80%AFPM.png?alt=media&amp;token=d70f6835-cc61-45e4-a17c-732ebd7dcf5b" alt=""><figcaption></figcaption></figure>

2. In **Segment filters**, open **Activity** and choose **Agent Columns**

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FnybSmTe5PT2NxzF50PAy%2FScreenshot%202026-11-06%20at%2012.24.06%E2%80%AFPM.png?alt=media&amp;token=8e1b8904-9767-4279-8eb4-7ea23848c227" alt=""><figcaption></figcaption></figure>

3. Pick a column and set the condition

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FgJvbeLqJHAARnzbxBn4A%2FScreenshot%202026-11-06%20at%2012.24.42%E2%80%AFPM.png?alt=media&amp;token=e37c4759-dfa7-4c84-8082-10a75e0194bf" alt=""><figcaption></figcaption></figure>

4. Add any standard filters you need, then save

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FZeIdigEHsJvVDFrWTdUP%2FScreenshot%202026-11-06%20at%2012.25.04%E2%80%AFPM.png?alt=media&amp;token=38cc88b0-35be-4167-a930-7091006932ff" alt=""><figcaption></figcaption></figure>

You can mix agent columns from different segments in one new segment. Columns from segments shared with you work too, and you don't need to clone them first.

#### **Conditions you can set**

The operators depend on the column type:&#x20;

<table data-header-hidden><thead><tr><th width="183.22265625"></th><th width="297.18359375"></th></tr></thead><tbody><tr><td><strong>Column type</strong></td><td><strong>Operators</strong></td></tr><tr><td>Number</td><td>is, greater than, less than, between</td></tr><tr><td>Date</td><td>is, before, after, between</td></tr><tr><td>Picklist</td><td>any of</td></tr><tr><td>Yes/No</td><td>is Yes, is No</td></tr><tr><td>Text</td><td>contains</td></tr><tr><td>All types</td><td>is empty, is not empty</td></tr></tbody></table>

{% hint style="info" %}
**Note:** <br>

* An account with no value in a column only matches **is empty.** It does not match **is No**.&#x20;
* An account has no value when the agent hasn't run on it yet, or ran and found nothing. So if your count looks low, those accounts are usually the reason.
  {% endhint %}

#### **How the segment stays up to date**

You don't need to refresh anything. New accounts join once the agent has run on them and they meet the condition. Accounts that stop meeting it leave.

This depends on the agent actually running on new accounts. If **Auto Enrich New Accounts** is turned off for the column, new accounts in the original segment never get a value and never join. Turn it on in the column's automation settings if you want the segment to grow on its own.

#### **Spotting these segments**

On the **Segments** page, a sparkle before the name means the segment was built from agent columns. That's the only visual difference from other segments.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FEUCxqtAhk1YzH6KxQfTn%2FScreenshot%202026-11-06%20at%2012.29.37%E2%80%AFPM.png?alt=media&amp;token=c1070f2b-7cd6-4508-bcf4-a58af720eaf1" alt=""><figcaption></figcaption></figure>

#### **Limits**

* **One level only:** You can't build a segment on top of a segment that was built from agent columns. **Save as new segment** is disabled in that case.
* **The agent has to finish first:** Agent columns are disabled in filters while the agent is still running. Try again once the run completes.

#### **Deleting a segment or an agent**

Deleting a segment or an agent also deletes every segment built on its agent columns, and turns off their automations. Before you confirm, Reo shows you the list of segments that will go with it.

This can't be undone. Deleted segments aren't archived and can't be restored.

#### **Frequently asked questions**

<details>

<summary><strong>Why are there fewer accounts than I expected?</strong> </summary>

The agent hasn't run on some accounts yet, or ran and found nothing. Those accounts have no value, so they only match *is empty*, not *is No*. Check that the agent has finished running and that Auto Enrich New Accounts is on.

</details>

<details>

<summary><strong>Does this cost credits?</strong></summary>

Creating the segment doesn't. The agent charges as usual when it runs on new accounts, just like it does for the column on the original segment.

</details>

<details>

<summary><strong>Can I build a segment on top of one of these?</strong></summary>

No, segments built from agent columns only go one level deep.&#x20;

</details>

<details>

<summary><strong>Can I use a column from a segment someone shared with me?</strong></summary>

Yes, it shows up under Agent Columns like your own - no cloning needed.

</details>

<details>

<summary><strong>What happens if I delete the original segment or the agent?</strong></summary>

Every segment built on its columns is deleted too, and their automations are turned off. You'll see the full list before you confirm.

</details>

### **Spotting an Agent Column in your account list**&#x20;

Agent Columns are marked with an icon in the column header, so you can tell at a glance which columns were added by an agent and which are Reo's default columns.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FC8cgMNuxsbv6yIWK3Obr%2FScreenshot%202026-10-08%20at%209.07.08%E2%80%AFAM.png?alt=media&amp;token=c6e28b22-3b8e-430c-96d6-66a39c30388d" alt=""><figcaption></figcaption></figure>

### **Filtering an Agent Column**

Each Agent Column has a filter built into its column header. The filter options depend on the type of data the column holds:

| Data type | What it looks like                              | Filter options                                                     |
| --------- | ----------------------------------------------- | ------------------------------------------------------------------ |
| Number    | e.g. number of DevOps engineers                 | Greater than, less than, equals, or is between a min and max value |
| Boolean   | Yes / No                                        | Yes or No                                                          |
| Picklist  | A fixed set of values, e.g. High / Medium / Low | Select one or more values                                          |
| Text      | A sentence or paragraph                         | Keyword search across the column for all accounts                  |
| Date      | e.g. date of a funding round                    | Before, after, is, or is between a from and to date                |

### **Digging into the research behind an account**

Every positive value in an Agent Column is clickable. Hover over a cell to find an expand icon. Click the icon to see the agent's comprehensive research for that account.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2F6UiM3bVUZtEJZbdbiATB%2FScreenshot%202026-10-08%20at%208.55.59%E2%80%AFAM.png?alt=media&amp;token=e050de4f-7979-4a55-a3f7-f93f098f7cc1" alt=""><figcaption></figcaption></figure>

This opens up a modal containing the reasoning behind the answer, the evidence it found, the last date that it was updated, and any related data it collected along the way.\
\
You can also navigate between accounts at the click of a button.

<figure><img src="https://2705882080-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fx46P5sAHxDG7PqOdVLxI%2Fuploads%2FfX6IiMhXpiWK3ZaICYqp%2FScreenshot%202026-10-08%20at%208.54.01%E2%80%AFAM.png?alt=media&amp;token=3069985a-7a54-4707-9cbe-a478c13df833" alt=""><figcaption></figcaption></figure>


---

# 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://docs.reo.dev/agents/agent-columns.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.
