> For the complete documentation index, see [llms.txt](https://help.usejimo.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.usejimo.com/docs/build/actions/automated-actions-no-code.md).

# Automated Actions (No-Code) (outdated)

Outdated: Automated Actions and the Run Action option were removed on October 16, 2026. This page is kept for reference, with what replaces them.

{% hint style="danger" %}
**Outdated: Automated Actions were removed on October 16, 2026.** The Actions page, the no-code action builder and the **Run Action** option are gone from every project, and saved Automated Actions no longer run. The content below is kept for reference only.
{% endhint %}

## What replaces them

| You used an Automated Action to                                       | Use instead                                                                                                                                                                                                                                               |
| --------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Let the Agent do a task for the user in a conversation                | An [Execute Skill](https://help.usejimo.com/docs/experiences/agent/skills.md#the-three-types-of-skills): the Agent clicks and fills on the user's behalf. See [Create a skill](https://help.usejimo.com/docs/experiences/agent/skills/create-a-skill.md). |
| Run a flow from a button, a checklist task or a Resource Center block | **Launch experience**, to start a tour that walks the user through the flow, or **Navigate to**, to send the user to the right page. See [Available Actions](https://help.usejimo.com/docs/build/actions/available-actions.md).                           |

To convert what you had, see [Migrating to Skills](https://help.usejimo.com/docs/experiences/agent/skills/migrating-to-skills.md).

***

## Previous content (outdated)

## Overview

The Actions dashboard is organized into two tabs:

* **No-code**: All your recorded Automated Actions. Each card shows step thumbnails, a name, description, and run count.
* **MCP** *(Moved)*: The Jimo MCP is live and now lives in Settings → Integrations → Model Context Protocol. It lets an AI assistant work on your project from a chat. See [Jimo MCP](https://help.usejimo.com/docs/integrations/mcp.md).

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2F7DzKpJ0BAHGOvLe2furF%2Fimage.png?alt=media&amp;token=da0b611b-ab87-4b8f-90d2-f4ca8feadfc7" alt=""><figcaption></figcaption></figure>

**Dashboard path:** [Actions > No-Code](https://i.usejimo.com/actions/no-code)

***

### What Are Automated Actions?

Automated Actions let you record a sequence of interactions on your product (clicking buttons, typing into fields, navigating between pages) and turn them into replayable workflows. Once saved, these actions can be triggered by [the Agent](https://help.usejimo.com/docs/experiences/agent.md) via [Custom answers](https://help.usejimo.com/docs/experiences/agent/knowledge/custom-answers.md), connected to [experience CTAs](https://help.usejimo.com/docs/build/actions.md#where-actions-are-used), or run on demand using the [Run Action](https://help.usejimo.com/docs/build/actions/available-actions.md#run-action-outdated) action type.

Think of them as macros for your UI: instead of writing step-by-step instructions, you record the steps once and Jimo executes them for your users.

***

## Creating an Action

{% hint style="warning" %}
Automated Actions can no longer be created in any project. For any new automation, create an [Execute a flow Skill](https://help.usejimo.com/docs/experiences/agent/skills/create-a-skill.md) instead.
{% endhint %}

#### Step 1: Set the starting page

Click **+ New Action** (top-right). A modal asks where the flow begins.

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2Fuj9MnQ0Sod6nRAqPm7Cn%2Fimage.png?alt=media&amp;token=3ec67ffd-53b6-4538-b605-a33e7888d09b" alt=""><figcaption></figcaption></figure>

Enter the URL of the page where the workflow starts (e.g. `https://yourapp.com/settings`), then click **Open Page**. Jimo opens the page in a new window and prepares for recording.

#### Step 2: Record the workflow

Once on the target page, a floating prompt appears at the bottom of the screen.

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2FBBOQu2c5Dq2DRqApkMb2%2Fimage.png?alt=media&amp;token=8778578f-48b3-4d78-9102-577673d71010" alt=""><figcaption></figcaption></figure>

Click **Start recording**, then perform the exact steps you want to automate: click buttons, type into fields, press keyboard shortcuts, navigate between pages. Jimo captures every interaction.

#### Recording toolbar

While recording, a toolbar at the bottom of the screen shows your progress.

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2FamkqJCmOFaw80XkLEaPd%2Fimage.png?alt=media&amp;token=c27674cf-730e-4abd-bf90-79ba4628f723" alt=""><figcaption></figcaption></figure>

| Control              | What it does                                                                                                                            |
| -------------------- | --------------------------------------------------------------------------------------------------------------------------------------- |
| **Status indicator** | Shows "Ready to select!" when waiting for your next interaction, or "X selected" with the count of recorded steps.                      |
| **Restart**          | Clears all recorded steps and starts over. A confirmation dialog asks "You've recorded X elements. Restart capture?" before proceeding. |
| **Pause**            | Temporarily pause recording without losing your steps.                                                                                  |
| **Delete**           | Remove the last recorded step.                                                                                                          |
| **Finish Recording** | End the recording session and process the captured steps.                                                                               |

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2FghbD34sIJbD31ay4ssid%2Fimage.png?alt=media&amp;token=1e0cdf0d-4cdd-4478-96a4-750ba8684514" alt=""><figcaption></figcaption></figure>

#### Step 3: Processing

After clicking **Finish Recording**, Jimo processes your captured interactions and generates the automated action.

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2F5WKUYz1DjWzfae40nSvC%2Fimage.png?alt=media&amp;token=d8084057-b914-4f6e-83fe-617138fc9585" alt=""><figcaption></figcaption></figure>

This takes a few seconds. Once done, the Action editor opens with your recorded steps.

***

### Action editor

The Action editor displays your recorded workflow as a vertical step flow. Each step represents one interaction you performed during recording.

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2FL2n5CeETF0iSp5Svb4Qj%2Fimage.png?alt=media&amp;token=8f76bb15-e24b-4460-9013-ca6e96ce5897" alt=""><figcaption></figcaption></figure>

#### Step flow (left panel)

The left panel shows all recorded steps connected by flow lines. Each step card displays:

* **Step type icon**: Color-coded by type (green for clicks, purple for inputs, yellow for keyboard events).
* **Step title**: Auto-generated description (e.g. "Click on 'Sign In'", "Input", "Keyboard Event").
* **Screenshot preview**: A visual snapshot of the target element on the page.
* **Description**: Human-readable explanation of what the step does (e.g. "Click the Sign in button to log in.", "Type 'Example' in the input field.").

Click any step to open its detail panel on the right side.

#### Step detail (right panel)

When you click a step, the right panel shows its properties and lets you edit the element targeting.

**Input text step**

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2FveqfSxVy2BeRNAr6Gw8U%2Fimage.png?alt=media&amp;token=fac6c0ba-4617-4db5-afc2-2962e43e1144" alt=""><figcaption></figcaption></figure>

* **Description**: What this step does (e.g. "Type text into the input field.").
* **Target Element**: A visual preview of the element on the page, with the CSS selector path shown below (e.g. `.flex > .relative > .pl-8\.75`).
  * **Reselect element**: Re-record the target element by clicking it on the live page.
  * **Edit selector**: Manually edit the CSS selector for advanced targeting.
* **Input**: The text value to type into the field (e.g. "Example").

**Click element step**

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2FseeVO00VLLkz86yA3jI0%2Fimage.png?alt=media&amp;token=0fdec38f-5ed4-46e4-a543-eab6d3a32469" alt=""><figcaption></figcaption></figure>

* **Description**: What this step does (e.g. "Click on the target element.").
* **Target Element**: Two targeting methods:
  * **Element text**: Match the element by its visible text content (e.g. the button label).
  * **CSS selector**: Match the element by its CSS path (e.g. `form > .text-center > .inline-block`).
  * **Switch to auto selection**: Let Jimo automatically determine the best selector.

#### Action controls

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2FjTifjwAwsLXEbK6ubsbc%2Fimage.png?alt=media&amp;token=2afd4296-ad4b-440e-b2d4-2bc23d4acb86" alt=""><figcaption></figcaption></figure>

At the bottom of the editor:

* **Play**: Run the action on the target page to test it. The steps execute sequentially, and you can watch the UI respond in real-time.
* **Redo**: Re-record the entire action from scratch. Opens the recording flow again.
* **Save**: Save the current version. If steps have been edited, a banner appears at the top: "This walkthrough has unpublished updates" with **Discard updates** and **Publish updates** buttons.

***

### Action detail panel

Click any action card from the dashboard to open its full detail view.

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2FYJdPVsqlofc3YZI2KOM7%2Fimage.png?alt=media&amp;token=f32e31bb-0917-4671-a5fc-caf4412148e3" alt=""><figcaption></figcaption></figure>

The right panel shows:

#### Allow Agent to run this action

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2F6plNb3EaXLovDiiMJhEk%2Fimage.png?alt=media&amp;token=c722d1ef-9a96-4ceb-8f0f-60d93413c19f" alt=""><figcaption></figcaption></figure>

~~A toggle that controls whether the~~ [~~Agent~~](https://help.usejimo.com/docs/experiences/agent.md) ~~can automatically run this action for your users. Click the chevron (>) to open the full~~ [~~Agent Trigger configuration~~](https://help.usejimo.com/docs/experiences/agent/knowledge/actions.md) ~~with Topics, Where rules, and Fallback URL.~~

{% hint style="warning" %}
The **Allow Agent to run this action** toggle was removed on September 17, 2026. To let the Agent run a flow in conversation, create a [Custom answer](https://help.usejimo.com/docs/experiences/agent/knowledge/custom-answers.md) or build an [Execute Skill](https://help.usejimo.com/docs/experiences/agent/skills.md#the-three-types-of-skills).
{% endhint %}

#### Statistics

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2FrfLaPzxQWZCB0G8jvbHX%2Fimage.png?alt=media&amp;token=65ba2bae-71f6-482e-a970-5d13c02b1859" alt=""><figcaption></figcaption></figure>

Three KPI cards tracking the action's performance:

| Metric         | Description                                                        |
| -------------- | ------------------------------------------------------------------ |
| **Runs**       | Total number of times this action has been executed.               |
| **Finished**   | Number of runs that completed all steps successfully.              |
| **Completion** | Percentage of runs that finished without errors (Finished / Runs). |

#### Metadata

* **Users Reached**: Number of unique users who have triggered this action.
* **Last run**: Timestamp of the most recent execution.
* **Last modified**: When the action was last edited.
* **Created by**: The team member who originally recorded the action.

***

## How Actions are triggered

Before October 16, 2026, a saved Automated Action ran whenever something in Jimo asked it to, through two trigger paths.

#### **Via the Agent**

Connect the Action to the Agent via [Custom answers](https://help.usejimo.com/docs/experiences/agent/knowledge/custom-answers.md) in [**Agent > Knowledge > Custom answers**](https://i.usejimo.com/agent/knowledge/custom-answers).

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2FQ5dFmbO04COLbpAGA43d%2Fimage.png?alt=media&amp;token=91baa5b7-be36-4897-aaf1-8bb09f0a240a" alt=""><figcaption></figcaption></figure>

#### **Via the Run Action action type**

Use the **Run Action** action type when configuring any standard action surface. Pick the saved Automated Action from your library, and the workflow runs when the user clicks the CTA or when the trigger condition fires.

**Available on:** [CTA buttons](https://help.usejimo.com/docs/experiences/tours-and-modals/components.md#primary-cta), [Progress triggers](https://help.usejimo.com/docs/build/triggers-and-conditions/steps-triggers.md), [Survey Conditions](https://help.usejimo.com/docs/build/triggers-and-conditions/conditions.md), [Changelog Post CTA](https://help.usejimo.com/docs/experiences/changelog/posts/post-components.md#call-to-action-cta-button-f), [Resource Center Action Blocks](https://help.usejimo.com/docs/experiences/resource-center/components.md#action-block), [Checklist Tasks](https://help.usejimo.com/docs/experiences/checklists/components.md#tasks), [Custom Answers](https://help.usejimo.com/docs/experiences/agent/knowledge/custom-answers.md)

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2F4c5bTuAbSrkl3ZTzAihF%2Fimage.png?alt=media&amp;token=f6eb2317-8a39-453f-8da7-8d3756b2ef4a" alt=""><figcaption></figcaption></figure>

<details>

<summary><strong>Examples</strong></summary>

* **Checklist task**: "Set up your workspace" task triggers an Action that creates the default workspace structure when the user clicks the CTA
* **Survey condition**: User answers "Yes" to "Want me to enable advanced features?", Run Action turns them on
* **RC Action Block**: "Reset to defaults" block triggers an Action that restores default settings
* **Tour CTA**: "Let me do it for you" button on a tour step triggers an Action that walks through the setup automatically

</details>

{% hint style="warning" %}

#### **Run Action behaves like Launch Experience.**

When triggered mid-flow, it dismisses the current experience and the Automated Action takes over the UI. The original experience does not resume after the Action finishes.
{% endhint %}

{% hint style="info" %}

#### **You can only trigger Automated Actions that already exist.**

There is no inline on-the-fly action creation from a CTA or trigger.\
Build the Action in Actions > No-Code first, then reference it from anywhere.
{% endhint %}

→ See [Run Action in Available Actions](https://help.usejimo.com/docs/build/actions/available-actions.md#run-action-outdated) for full reference.

***

### Testing an Action

You can test an action in two ways: using the **Play** button in the action editor, or using the **Test** option from the card's three-dot menu on the dashboard.

When a test runs, a progress indicator appears at the bottom of the target page.

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2F3bUWQJlLeMNdyt47YkUc%2Fimage.png?alt=media&amp;token=4b85cb83-5dba-4b2c-b5c6-182262cd9891" alt=""><figcaption></figcaption></figure>

The indicator shows which step is currently executing (e.g. "1 of 5") and a **Stop** button to cancel mid-execution. Jimo takes control of the UI and performs each recorded step sequentially: navigating, clicking, typing, exactly as you recorded. Use this to verify the action works correctly before connecting it to the Agent.

***

### Managing Actions

#### Card actions

Each action card on the dashboard has a three-dot menu with four options.

<figure><img src="https://2794860263-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKzAcDWQbK1gKbpra7bkb%2Fuploads%2FARkK6TqZvj9un0IPMqLk%2Fimage.png?alt=media&amp;token=96689370-f994-4fad-8595-f4d2d3374b29" alt=""><figcaption></figcaption></figure>

| Action        | What it does                                                                                |
| ------------- | ------------------------------------------------------------------------------------------- |
| **Test**      | Run the action on the target page to verify it works correctly.                             |
| **Redo**      | Re-record the action from scratch. Opens the recording flow with a new starting URL prompt. |
| **Duplicate** | Create a copy of this action with all its steps and settings.                               |
| **Delete**    | Permanently remove this action.                                                             |

***

## Best practices

{% stepper %}
{% step %}

#### **Keep actions short and focused.**

Record one task per action (e.g. "Navigate to billing", "Invite a team member"). Long multi-page workflows are more likely to break when your UI changes.
{% endstep %}

{% step %}

#### **Use descriptive names.**

Name actions by what they accomplish ("Update Username in Settings") not by how they work ("Click Settings then Profile then Edit").
{% endstep %}

{% step %}

#### **Test after every UI update.**

If your product's layout, button labels, or page structure changes, actions may fail to find their target elements. Use **Test** to verify and **Redo** to re-record.
{% endstep %}

{% step %}

#### **Edit selectors for stability.**

Auto-generated CSS selectors can be fragile. If an action breaks frequently, open the step detail and use **Edit selector** to set a more stable selector (prefer IDs and data attributes over positional selectors).
{% endstep %}

{% step %}

#### **Use Element text targeting for buttons.**

For click steps on buttons with stable labels, the "Element text" matching mode is often more resilient than CSS selectors to layout changes.
{% endstep %}

{% step %}

#### **Monitor completion rates.**

Check the Statistics panel regularly. A low completion rate signals that steps are failing, usually due to UI changes or selector drift.
{% endstep %}

{% step %}

### **Pair with Tours when relevant.**

A short tour explaining what is about to happen, followed by a CTA with Run Action, gives users context before the workflow takes over.
{% endstep %}

{% step %}

### **Be intentional about flow continuity.**

Run Action interrupts the current flow. If you need the user to come back to where they were, use a Tour instead, or chain a follow-up experience after the Action completes.
{% endstep %}
{% endstepper %}
