Install and configure

The page provides instructions on installing and configuring the Kayla AI Agent for coordinating the perpetual Know-Your-Customer (pKYC) process.

Check requirements

WorkFusion offers the following options to install and run Kayla:

• On your premise
• In your cloud
• In a private cloud hosted by WorkFusion

System requirements

The server requirements for Kayla, the pKYC Coordinator, are the same as for Work.AI (IA Cloud Enterprise) platform. For details, refer to the Hardware and OS article.

Hardware

• RPA bots are required if you use a connector or a data provider that uses them.

• High-availability environments require PROXY.

Software

• IA Cloud Enterprise v10.2.9 or higher

• No machine learning (ML) component used

• Superset Analytics available but not required

Performance and scaling

• BEP servers can be scaled horizontally for higher volumes.

Install Kayla

To install Kayla, obtain an Asset Bundle (zip archive) with the required release version from the appropriate S3 bucket. Then, upload it manually in the Control Tower interface in accordance with the guide.

Once the installation is complete, you can proceed to configure Kayla's settings.

note

You can configure multiple variations, or sets of parameters, for a single AI Agent. For example, different departments can set up and manage different requirements or input methods per variation. For details, refer to Manage AI Agent variations.

Configure Kayla

There are two possible ways to start the configuration flow for Kayla:

• If you install Kayla without a preset configuration, wait for the installation to complete. Once you are redirected to the AI Agent version details page, open the Actions menu and click Settings.

  

• If you install Kayla as an Asset Bundle with a preset configuration, wait for the installation to complete and click Show digital worker. Then, find the installed variation in the Digital Workers list and click Prepare.

  

After you complete any of the flows described above, proceed to the configuration:

1. In Advanced > Data Stores, do the following:

   • Set up a proxy server.

   • Configure the address service domain.

2. Install the Chrome driver for RPA sources (if needed).

3. In the AI Agent configuration wizard, perform the following steps:

   1. Configure the input settings.

   2. Set the review process rules.

   3. Configure a human-in-the-loop step (optional).

   4. Define where Kayla is to deliver and store its output.

   note

   When you configure your AI Agent variation for the first time, you must complete the above wizard steps one by one. Once you are in the last step, you can go back and make changes to any previous steps. If, for some reason, you cannot finish the configuration, click Save & continue later. This way, the entries you made are saved, and you can go back and complete the process later.

Proxy server

warning

If the proxy requires authentication, set up an alias containing the proxy credentials in Secrets Vault. The key is the username address, and the value is the password. For detailed instructions, read Set up secret entries in Secrets Vault.

To configure a proxy server, do as follows:

1. In Control Tower, go to Advanced > Data Stores.

2. Select the uc_DW_KAYLA_KYC_technical_configuration Data Store.

   

3. In the Data Store, set up the following fields:

   Name	Sample value	Instruction
   proxy.host	proxy.customerdomain.com	Enter your proxy host.
   proxy.port	1234	Enter your proxy port.
   proxy.credentialsAlias	kayla_proxy_credentials	Create an alias for the proxy credentials in Secrets Vault. Configure only if the proxy server requires authentication.

   note

   If you use the CSSF, AMF, or SEC Mutual Fund profile connectors, update the ZooKeeper settings to limit the worker pool.

   In ZooKeeper, create /config/worker-management-service/bep.worker.pool.com.workfusion.dw:dw-kayla-kyc-jnw:3.4.0-dev.max-worker-count-pool-limit 1.

Chrome driver for RPA sources

Install the Chrome driver on the auto-scaling agent servers in your environment if the following data providers are used:

• AMF

• CSSF

• SEC Mutual Fund profiles

Address service domain

The address verification service is required to use the Verify Address ML model method for setting the input processing requirements. To access the address verification service, configure an environment: Development, UAT, and production.

To configure the environment, do as follows:

1. Navigate to Advanced > Data Stores.

2. Select the uc_DW_KAYLA_KYC_technical_configuration Data Store.

3. In the Data Store, set up the following field:

   Name	Sample value	Description
   address_service_environment	https://address-service-uat.workfusion.io/	Specify the environment name.

Input

In the Input step, you choose and configure the following:

• Input method Kayla uses to fetch reviewed entity data

• Data providers from where Kayla sources enrichment data

Input method

As the input method for Kayla, you can choose one of the two alternatives:

• API: Kayla fetches data from the dedicated Application Programming Interface.

  For detailed API endpoints, see the Swagger specification.

  

• File ingestion: Kayla fetches data from CVS files that correspond to specific requirements and are stored in a S3 (MinIO) location.

To enable Kayla to work with file ingestion, configure the following:

1. Specify the input file bucket and location in S3 (MinIO) from where Kayla is to retrieve input files.

2. Define the monitoring settings:

   • Specify how frequently, in hours or minutes, Kayla should poll the input file location for new files.

   • If needed, select the Stop monitoring after some iterations checkbox. In the displayed Max loop field, specify the number of iterations.

   • Optionally, select the Stop monitoring after some duration checkbox. In the displayed Max monitoring duration and Time unit fields, set the period duration.

3. Map the fields to the respective headers in the input CSV file.

Data providers

Select one or more data providers you want to use to enrich Kayla's input data from third-party sources and click Apply. For the complete list of supported data providers, see the F.A.Q topic.

Some providers (such as Sayari and twelveData) require additional licenses. You will need to select an alias from the Secrets Vault containing the credentials to access the data or create one if it is the first time you are setting up the AI Agent in that environment. For detailed instructions, read Set up secret entries in Secrets Vault.

Sayari Graph also requires you to set the parameters for searching and retrieving records.

Requirements

To configure a requirement, follow the steps below:

1. Click Add Another.

   

2. Specify the rules Kayla should follow when reviewing KYC data for an entity. For more details, see the table below.

   

   Field	Description	Values	Required
   Rules	The name-value pairs that determine to which entities to apply a specific requirement.	Use the name-value pairs from the input file. You can set more than one pair per requirement by clicking the Add Another button in the Rules section.	Yes
   Source	The external data provider from where input data is retrieved.	As configured on the Input step	Yes
   Requirement Reference ID (optional)	A key or reference to the KYC requirement matrix.	Free-text field	No
   Review Method	The method used to complete the review	Exact Match: the Field Name value should be a direct match against a value in the API response from the configured source. Information Extraction Model: the Field Name value is validated using an information extraction model. Manual Review: the Field Name value is not reviewed. Used if an information extraction model or API is unavailable or a data point requires additional scrutiny. Name Match: works similarly to Exact Match, except that it does not consider punctuation, extra spaces, or other special characters that are inadvertently present in a name. This ensures that minor discrepancies (- vs. : or extra spaces) do not get flagged for manual review. Verify Status: used to verify the Field Name status. For example, whether the entity is regulated and found in a regulator's database and whether the status is a specific value. Verify Address ML model: used to verify two addresses. Each address is either normalized (unstructured) or structured. To use the review method, set the address service domain.	Yes
   Model	The ML model to be used	Available pre-trained models	Yes, if Review method is set to Information Extraction Model.
   Field Name	The name in the input file that must be reviewed.	Depends on the input file	Yes
   Source Field Name	The field from the specified source to be compared to the Field Name from the input file	Varies, depending on the source	Yes, if Review method is set to Exact Match, Name Match, Verify Address ML Model, or Information Extraction Model.
   UUID	Identifier that is unique for each requirement and used for audit and reporting purposes.	Automatically generated	-

3. Click Save to save the rules for the entity.

4. Repeat steps 1 to 3 to add as many rules as you need.

   

5. Click Next to move on to the Human-in-the-Loop step.

Human-in-the-Loop

The step is optional. It allows analysts and quality assurance specialists to review Kayla's results in Workspace and address any exceptions prior to the generation of the final periodic review report.

To configure the step, follow the instructions below:

1. Choose an option to define when manual review should be enabled:

   • Enable in all Cases creates an assignment in Workspace for every entity, regardless of whether Kayla completed requirements or not.

   • Disable in all Cases disables manual reviews completely. In this case, the Automatically route users to the next task in the queue? setting is unavailable.

   • Conditionally disable conditionally creates an assignment based on rules. Select one of the options or both:

     • All requirements are successfully completed creates an assignment when a requirement needs manual review.
     • EvA is not required creates an assignment when an entity requires expected versus actual activity (EvA) review.

     

2. Specify the task routing mechanism. Select True for Automatically route users to the next task in the queue? to route users to the next task in the queue that is not actively being worked on, regardless of who it is assigned to.

Output

In the Output step, you set how Kayla should deliver its output:

• Entity level reports
• Batch summary reports

For details about the reports, see Input and output data.

To configure the output settings for Kayla, do as follows:

1. Specify the S3 bucket where the reports are to be saved.

   

2. If you selected the File ingestion option when configuring the input method, choose whether you want Kayla to email the reports. If you don't want Kayla to email the reports, skip the step and go straight to step 4. Otherwise, in the Output Email section, configure the following:

   1. Specify the email address where batch summary reports are to be sent.

   2. Choose a Secrets Vault alias from the drop-down list. If you don't have an alias configured, click the Create New Secret Vault Entry, set the alias up, and save it. For detailed instructions, refer to Set up secret entries in Secrets Vault.

   3. Make sure to add the following:

      • SMTP host and port

      • Required email addresses

      • Authorization

3. Click the Finish button to save the configuration.

Update configuration

To update Kayla's configuration, follow the steps below:

1. Go to the Digital Workers page.

2. Click the Kayla's version you are working with.

3. On the version details page, open the Actions menu and select Settings.

   

4. On the displayed configuration screen, make changes in each step as required and click Finish to save the updated configuration.