# Integration with AWS Bedrock

### Overview

AWS Bedrock provides a platform for building and deploying AI models. By integrating AWS Bedrock Agents into MangoApps AI Studio as Assistants, you can enhance automation and intelligence within your intranet environment. 

<figure><img src="https://3253353518-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fler8efF6dRPhC6skcFIU%2Fuploads%2FJGDNWPqvkIVJxEXNomgM%2Ftyjkrtyu.png?alt=media&#x26;token=507732df-3c69-4b00-9913-93ca71ceee91" alt="" width="375"><figcaption></figcaption></figure>

If your company already has a configured and licensed AI Assistant from AWS Bedrock, you can integrate it into your MangoApps domain.

***

### Prerequisites

* An active AWS account with access to Amazon Bedrock.
* Administrator access to MangoApps AI Studio.
* AWS IAM permissions to create and manage Bedrock Agents.

***

### Setup in AWS Bedrock

#### Create an AWS Bedrock Agent

1. **Log into AWS Management Console** and navigate to **Amazon Bedrock**.

<figure><img src="https://3253353518-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fler8efF6dRPhC6skcFIU%2Fuploads%2FLY4M5SyaqufHnG1fGgAB%2Feartghethw.png?alt=media&#x26;token=5ff7b5f3-16d2-4c3d-aad5-2296c0fa8669" alt="" width="563"><figcaption></figcaption></figure>

2. Click on **Agents** and select the **Create Agent** button if you do not already have an active Agent.&#x20;

<figure><img src="https://3253353518-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fler8efF6dRPhC6skcFIU%2Fuploads%2FW1iBTBmPD9LJyTPpVPjJ%2Ffykmukt.png?alt=media&#x26;token=1cf6a483-8e24-47ea-b4a4-15d3af2ab55b" alt="" width="563"><figcaption></figcaption></figure>

3. Continue through the steps to create an agent:
   1. Choose a **Foundation Model** from the Model Catalog.
   2. Configure your Agent with **Action Groups** and define its response flows.
   3. Deploy the Agent by associating an **Alias** with a specific version.
4. Test the Agent in real-time before deployment.

***

#### Configure IAM Permissions for Integration

1. From the search bar, navigate to the **AWS IAM**.

<figure><img src="https://3253353518-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fler8efF6dRPhC6skcFIU%2Fuploads%2FVSY1nfFnU2dzl303uT6R%2Frewteq.png?alt=media&#x26;token=de8b25c2-cd8b-43e0-90be-2ce1d035a1fc" alt="" width="563"><figcaption></figcaption></figure>

2. From the **IAM dashboard**, click the **My security credentials** from the right hand **Quick Links** menu.

<figure><img src="https://3253353518-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fler8efF6dRPhC6skcFIU%2Fuploads%2FebqIz26KhirlNKVcWqRn%2Frsrghwrth.png?alt=media&#x26;token=b065cef4-6dee-4f97-b7b1-f9d742e6de4a" alt="" width="563"><figcaption></figcaption></figure>

3. Create an **Access Key** with policies granting access to **Amazon Bedrock** services. Attaching all the necessary **Bedrock-related permissions**.

<figure><img src="https://3253353518-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fler8efF6dRPhC6skcFIU%2Fuploads%2FKYXYFNqp7MarKE2P1pdw%2Frtjyty.png?alt=media&#x26;token=81fe5eb7-1e8c-4424-adf5-51a89091f022" alt="" width="563"><figcaption></figcaption></figure>

4. Generate an **Access Key** and **Secret Key**. These will be used on the MangoApps side.

***

### Set Up In MangoApps

Once added, you will be able to select **Amazon Bedrock Agents** from the **AI Service Provider** dropdown menu.

#### Connect an AI Service Provider

Navigate to the **AI Service Providers** tab within the **AI Studio** module. Click the **Connect an AI Service Provider** button in the upper right hand corner.

<figure><img src="https://3253353518-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fler8efF6dRPhC6skcFIU%2Fuploads%2FPTQx52PprNrzP37HwZ7T%2Fmdtyh.png?alt=media&#x26;token=be66ded0-380e-4b55-90ea-1f92bb2bb38a" alt="" width="563"><figcaption></figcaption></figure>

Select **AWS Bedrock** from the **AI Service** dropdown menu, then create a **Name** and **Icon**. This name and icon will appear in the **AI Service Providers** list. Once AWS Bedrock is added to the list, it will no longer be available in the dropdown menu. To add a new AWS Bedrock instance, you must first remove the existing one within MangoApps.

Enter in the **AWS key** and **Secret token** generated in the AWS setup steps above. For security purposes, the key and token will **not** be displayed in MangoApps.

***

#### Connect Your Assistant&#x20;

1. Click the **Create an Assistant** button and choose **Connect Your Assistant** from the dropdown menu. This will take you to the assistant configuration screen.&#x20;

<figure><img src="https://3253353518-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fler8efF6dRPhC6skcFIU%2Fuploads%2F22HViEUqHXgGbpBCIaRT%2F06-02-2025-12-13-17.png?alt=media&#x26;token=4e60a819-3ff0-4ffc-a5f1-2d1b988b801a" alt="" width="563"><figcaption></figcaption></figure>

2. The **Configure Assistant** menu will be very similar to the [**Create an Assistant**](https://guides.mangoapps.com/ai-guide/admin-portal/ai-studio-module/ai-assistants/create-an-assistant) menu. Complete the required fields and confirm that your provider has been successfully listed under the **AI Service Provider** tab.&#x20;
3. Within the **Customize Assistant** section, select AWS Bedrock from the **AI Service Provider** dropdown. Once selected, choose the AWS Bedrock Agent you would like to connect as a MangoApps AI Assistant from the dropdown menu.&#x20;

<figure><img src="https://3253353518-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fler8efF6dRPhC6skcFIU%2Fuploads%2FEKs63eZW2YLXCIoiLXCV%2F10-02-2025-01-38-40.png?alt=media&#x26;token=8d6a576d-55c3-471d-8d20-30a6ccee89d6" alt="" width="563"><figcaption></figcaption></figure>

4. Finally, complete the remaining menu configurations. Since the AI service provider supplies the LLM, no additional configuration is required in this menu.
5. Your Assistant is now connected. By default, it will remain disabled until enabled from the **Admin Menu**.

<figure><img src="https://3253353518-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fler8efF6dRPhC6skcFIU%2Fuploads%2FeX5lwFiTl3JqyWllpmTc%2Fehsetr.png?alt=media&#x26;token=1ec35463-9c81-410e-a2aa-7325c3bf3b9f" alt="" width="563"><figcaption></figcaption></figure>

***

### Security Considerations

* **Access Control**: Use **IAM roles and policies** to restrict access to AWS Bedrock agents.
* **Logging & Monitoring**: Enable **AWS CloudTrail** and **MangoApps Audit Logs** to track AI interactions.
* **Compliance**: Validate AI outputs against **organizational policies** to prevent misinformation.

***

### Rollout Recommendations

* **Pilot Testing**: Start with a small user group to validate AI responses and improve accuracy.
* **User Training**: Educate employees on AI functionalities and best practices.
* **Feedback Loop**: Continuously refine the AI model based on user feedback.
* **Gradual Expansion**: Scale up deployment based on adoption rates and performance analysis.

***

### Disconnect LLM

To disconnect the AWS Bedrock LLM from MangoApps, navigate to **Modules > AI Studio > AI Service Providers** within the **Admin Portal**. Click the **3-Dot** action menu next to AWS Bedrock and click **Remove LLM** from the action options.

<figure><img src="https://3253353518-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fler8efF6dRPhC6skcFIU%2Fuploads%2F8HgmpOS1pBEkRW7wUbEm%2F13-02-2025-10-51-42.png?alt=media&#x26;token=b4b19faa-77df-49ca-be3d-9d5add270387" alt=""><figcaption></figcaption></figure>