Install and configure

The page provides the instructions for the AMM skill's installation and configuration. For IA compatibility data, refer to the AMM release notes.

Requirements

Hardware

The AMM skill runs on the standard Work.AI hardware configuration, as documented in System requirements.

Server	Recommended OS	CPU (cores)	RAM (GB)	HDD (GB)
Master	RHEL 8.5	8	32	750
BEP Agent	RHEL 8.5	4	16	150
Analytics	Windows Server 2016	16	32	150
MS SQL	Windows Server 2016	2/4	8/16	500

• RPA bots are not required for Adverse Media Monitoring.
• High-availability environments require a Proxy server.

For the architecture deployment, refer to Install AI Agents | View architecture deployment.

Software

Before installing AMM, make sure that your environment meets the requirements:

• You have installed Work.AI v10.2.8+ and have Control Tower and Analytics components enabled. For Work.AI, ODF 2 is installed automatically along with the system.
• You have the bundle with AMM Business Process and ML models.
• You have received the credentials for the required watchlists or licenses for the external screening software to be integrated with AMM.
• You have the Advanced Package Import and Import/Export permissions in Control Tower.

To check that ODF is installed:

1. Log in to Control Tower, and click Advanced > Data Stores in the menu.

2. In the list, find the Data Stores with the_odf_transactions and _odf_transactions_status names. ODF is installed on your instance if they are on the list.

   

If the Data Stores are missing, download ODF and save odf-install-package-yourversion.zip to your local workstation. To find the proper ODF installation package for your Work.AI version, refer to the Compatibility matrix documentation.

Performance

Adverse Media Monitoring leverages BEP servers that can be horizontally scaled for higher volumes.

Below is a sample of the volumes that can be expected when using the provided version and configuration. The system shows stable performance and resource consumption during the test without unexpected spikes or critical errors and warnings in logs.

The Search provider used is Google API. Note that throughputs can vary slightly based on the provider.

Configuration:

Skill version	Environment topology	Tested platform version	AutoML Worker configuration	Control Tower Worker configuration
3.6.1	standard-6 topology (6/1 BEP Agents)	10.2.8	1 CPU / 8 GB memory	0.4 CPU / 2 GB memory

Results:

Number of Agents	Execution time	Articles/hour
1	304 min	1,100
2	119 min	2,820
3	80 min	4,200
5	53 min	6,340

Install skill

See the Install AI Agents guide.

Configure skill

Once Adverse Media Monitoring is installed, configure the skill before running it for the first time.

You can configure multiple variations, or sets of parameters, for AMM. For example, a different data provider or a set of keywords per variation.

API credentials for providers

Before setting the news providers, ensure you have obtained the corresponding license with credentials.

The following search providers are supported:

• Google API
• Dow Jones Factiva Headlines
• LexisNexis L&P Media
• World-Check One
• Thomson Reuters CLEAR Adverse Media

You must acquire licenses and credentials for all providers, except for Google API. WorkFusion’s AMM solution includes access to Google API at no additional cost.

If you are using Google API, your first step is to provide credentials. To do that on a GCP-hosted environment, see the instruction under the expand:

Provide new credentials for Google API

The Google API used for Adverse Media Monitoring is the Custom Search JSON API.

You must provide credentials from WorkFusion’s Developer account owned by the Cloud Ops team.

GCP requires unique credentials to be used in each customer environment (for example, pre-production and production).

If you are not using Google Cloud, notify the WorkFusion Engineering and Product teams so that they can perform an audit to ensure there are no gaps for enablement.

To generate new credentials, do the following:

1. Log in to https://cloud.console.google.com.

2. Ensure that the Custom Search JSON API is enabled.

   

3. Navigate to the environment where you will use the API, for example, companyname-preprod.

4. Select Create Credentials.

   

5. Enter a Name for the API Key, then in the Application restrictions group, select HTTP referrers, and click Save.

   

6. Navigate to the OAuth consent screen, in the User Type group, select Internal and click Create.

   

7. Navigate to Enabled APIs & services to view the key and copy the credentials.

   You must add the key value to the Secrets Vault's key field. The Value field is static.

To use providers other than Google API, you must first set up the above credentials in Secrets Vault. For step-by-step instructions, refer to the Set up secret entries in Secrets Vault guide.

Configure SMTP credentials

Adverse Media Monitoring emails analysts when results are ready, and the final report is available. To enable notification, configure the SMTP credentials. You must provide your own SMTP to ensure the respective security protocols are followed.

The sub-sections below describe the steps to configure the credentials and enable email notifications.

Update configuration in Data Store

To update the configuration in the Data Store, do the following:

1. Log in to Control Tower.
2. On the main menu, navigate to Advanced and select Data Stores.
3. Select the uc_amm_configuration_v1 configuration and specify the following:

Name	Value	Example	Notes
smtp.protocol	SMTP_OVER_TLS/SMTP_OVER_SSL/SMTP	SMTP_OVER_TLS	To be confirmed with WorkFusion.
smtp.host		smtp.office365.com	Set your host.
smtp.port		123
smtp.replyTo		replyTo@domain.com	Set the email address to be shown as the sender.
smtp.authEnabled	true/false	true	Set to true if the SMTP server requires authentication. Otherwise, set to false.
smtp.credentialsAlias		amm_smtp_credentials	Configure only if smtp.authEnabled is set to true. Specify the name of the SMTP credentials in Secrets Vault. The value must match the alias in Secrets Vault that contains the access credentials to the SMTP server.

Set up entry for SMTP credentials in Secrets Vault

info

The step is needed only if smtp.authEnabled is set to true.

The key is the email address, and the value is the password. For detailed instructions, see Set up secret entries in Secrets Vault.

tip

Use a descriptive name, such as amm_smtp_credentials.

Configure proxy

To configure a proxy, do the following:

1. Log in to Control Tower.

2. On the main menu, navigate to Advanced and select Data Stores.

3. Select the uc_amm_configuration_v1 configuration and specify the following:

   Name	Example	Notes
   proxy.host	proxy.customerdomain.com	Use your proxy host.
   proxy.port	9473	Use your proxy port.
   proxy.credentialsAlias	amm_proxy_credentials	Specify the name of the proxy credentials in Secrets Vault. Configure only if the proxy requires authentication.

4. If the proxy requires authentication, set up proxy credentials in Secrets Vault.

   The key is the username address, and the value is the password. For detailed instructions, refer to Set up secret entries in Secrets Vault.

Input

To set up the installed skill, do the following:

1. Log in to Control Tower, navigate to Digital Workers, find your newly installed AMM skill, and click the Prepare button.

   The Prepare your digital worker window appears, containing a configuration flow.

2. In the window, on the Input step, indicate how you want to get news articles. Answer the Do you want the digital worker to automatically source the information to be reviewed? question by selecting one of the options:

   • Yes for input data to be loaded automatically from a news provider. For further instructions, read Source input data automatically.

   • No for input data to be uploaded with a CSV file. For further instructions, refer to Provide input data with CSV file.

Source input data automatically

To configure the skill to source information automatically, in the Search provider field, select one or more providers for searching news about a required entity or individual. You can configure the AI Agent to return results from up to four providers at a time.

The following news providers are supported out of the box:

• Google API
• Dow Jones Factiva Headlines
• LexisNexis L&P Media v1
• World-Check One
• Thomson Reuters CLEAR Adverse Media

If you select more than one provider, each appears as a distinct collapsible section below the Search provider field.

Review each section carefully to ensure all required parameters are configured correctly. Available parameters vary by provider. For detailed instructions, read the sections below.

Google API

• Google API Key alias: specify the corresponding Secrets Vault alias for the Google API system. Enter an existing alias or click Create new secret vault entry to set up one.

• Article language: select the language of articles to search in. Any language is used by default. You can also choose Keyword language and its following options:

  • Shared creates a single input field for keywords.
  • Defined by keyword language.

• Keywords: specify keywords to be used for the search. You can add a maximum of 28 words.

  The following keywords are added by default based on the article languages you select:

  • English:

    ACCUSE, ARREST, BRIBE, CONVICT, CORRUPT, COUNTERFEIT, CRIME, EMBEZZLEMENT, FRAUD, GUILT, ILLEGAL, INDICTMENT, INVESTIGATION, KICKBACK, MONEY LAUNDERING, NARCOTIC, PENALTY, SANCTION, SENTENCED, EVASION, TERRORIST, THEFT, TRAFFICKING, VIOLATION

  • Spanish:

    ACUSAR, ARRESTAR, SOBORNO, CORRUPTO, FALSIFICACIÓN, CRIMEN, MALVERSACIÓN, FRAUDE, CULPA, ILEGAL, ACUSACIÓN, INVESTIGACIÓN, CONTRAGOLPE, LAVADO DE DINERO, NARCÓTICO, MULTA, SANCIÓN, SENTENCIADO, EVASIÓN, TERRORISTA, ROBO, TRÁFICO, VIOLACIÓN

• Enable keywords thesaurus: activate to look not only for exact keywords but also for their synonyms. By default, the feature is turned on. Disable it if your organization requires only exact matches on all keywords.

• Number of articles to extract: specify the maximum number of reports to fetch from 1 to 20. By default, up to 20 articles are retrieved.

• Search time period: select an option to find information published during a specific time frame.

• File types to exclude from results: select the file types that you want to exclude from Google results:

  • HTML is included by default.
  • Non-HTML file types do not have the same meta data and tagging. Excluding them reduces the number of articles to review and false hits by 50% without increasing the risk of missing a true hit.

• Partial name search: select to include partial names of entities or person in the search.

• Dynamic location search: select to dynamically broaden the search location for an entity if no results are found.

• High-risk countries: select countries from the dropdown or enter their names in the search field. The high-risk countries configured here are highlighted in articles returned from each investigation.

Factiva

• Factiva Headlines API URL: select the address of the Factiva API. Available options:

  • https://api.beta.dowjones.com
  • https://djrc.api.dowjones.com

• Factiva Headlines API Key alias: specify the corresponding Secrets Vault alias for the Factiva system. Enter an existing alias or click Create new secret vault entry to set up one.

• Article language: select the language of articles to search in. The English language is used by default.

• Keywords: specify keywords to be used for the search. You can add a maximum of 28 words.

  The following keywords are added by default based on the article languages you select:

  • English:

    ACCUSE, ARREST, BRIBE, CONVICT, CORRUPT, COUNTERFEIT, CRIME, EMBEZZLEMENT, FRAUD, GUILT, ILLEGAL, INDICTMENT, INVESTIGATION, KICKBACK, MONEY LAUNDERING, NARCOTIC, PENALTY, SANCTION, SENTENCED, EVASION, TERRORIST, THEFT, TRAFFICKING, VIOLATION

  • Spanish:

    ACUSAR, ARRESTAR, SOBORNO, CORRUPTO, FALSIFICACIÓN, CRIMEN, MALVERSACIÓN, FRAUDE, CULPA, ILEGAL, ACUSACIÓN, INVESTIGACIÓN, CONTRAGOLPE, LAVADO DE DINERO, NARCÓTICO, MULTA, SANCIÓN, SENTENCIADO, EVASIÓN, TERRORISTA, ROBO, TRÁFICO, VIOLACIÓN

• Number of articles to extract: specify the maximum number of reports to fetch from 1 to 20. By default, up to 20 articles are retrieved.

• Search time period: select an option to find information published during a specific time frame.

• High-risk countries: select countries from the dropdown or enter their names in the search field. The high-risk countries configured here are highlighted in articles returned from each investigation.

LexisNexis

• LexisNexis L&P Media API URL: select the address of the LexisNexis API. By default, https://services-api.lexisnexis.com.
• LexisNexis L&P Media auth URL: specify the Authentication URL for the LexisNexis News. By default, https://auth-api.lexisnexis.com.
• LexisNexis L&P Media API Key alias: specify the corresponding Secrets Vault alias for the LexisNexis News system. Enter an existing alias or click Create new secret vault entry to set up one.
• Article language: select the language of articles to search in. The English language is used by default.
• Keywords: specify keywords to be used for the search. You can add a maximum of 28 words.
• Number of articles to extract: specify the maximum number of reports to fetch from 1 to 20. By default, up to 20 articles are retrieved.
• Search time period: select an option to find information published during a specific time frame.
• High-risk countries: select countries from the dropdown or enter their names in the search field. The high-risk countries configured here are highlighted in articles returned from each investigation.

World-Check One

• World-Check One API URL: select the address of the World-Check One API. The default one is https://api-worldcheck.refinitiv.com.
• World-Check One Group: specify the Group Id for the World-Check One system.
• World-Check One API Key alias: specify the corresponding Secrets Vault alias for the World-Check One system. Enter an existing alias or click Create new secret vault entry to set up one.
• Article language: select the language of articles to search in. The English language is used by default.
• Keywords: specify keywords to be used for the search. You can add a maximum of 28 words.
• Number of articles to extract: specify the maximum number of reports to fetch from 1 to 20. By default, up to 20 articles are retrieved.
• Search time period: select an option to find information published during a specific time frame.
• High-risk countries: select countries from the dropdown or enter their names in the search field. The high-risk countries configured here are highlighted in articles returned from each investigation.

info

For the World-Check One provider, the keywords highlight important sections within each article returned by the search, but not for the API call. You must configure keywords to be used in a search at the World-Check One's website.

Thomson Reuters CLEAR Adverse Media

• Thomson Reuters CLEAR Adverse Media API URL. Select the address of the Thomson Reuters CLEAR Adverse Media API. By default, it is https://api-worldcheck.refinitiv.com.

• Thomson Reuters CLEAR Adverse Media API Key alias: specify the corresponding Secrets Vault alias for the Thomson Reuters CLEAR Adverse Media system. Enter an existing alias or click Create new secret vault entry to set up one.

• Gramm-Leach-Bliley Act permissible purpose: to comply with the privacy provisions of the Federal Gramm-Leach-Bliley Act and the subsequent regulations adopted by the Federal Trade Commission (GLB), select only a single purpose from the presented list. Misrepresenting your access purpose is a violation of our subscriber agreement and certain federal and state laws. Any use of information maintained by West, a Thomson Reuters business, other than for the selected permissible purpose, is a ground for account termination and can be referred to the appropriate governmental agency.

• Driver’s Privacy Protection Act permissible purpose: the Driver's Privacy Protection Act (DPPA) was enacted to prevent any Department of Motor Vehicles (DMV) officer, employee, or contractor from knowingly disclosing or making available to any person or entity the personal information associated or contained within a motor vehicle record. This act does not include or affect accident reports, violations (MVRs), and driver status.

• Voter permissible purpose: due to data privacy restrictions imposed by state laws, users accessing voter registration records are required to acknowledge compliance with the law and to indicate the intended permissible use for the data. Information obtained from each search, including the indicated permissible use, date of search, and search details, are stored for at least five years to comply with states' statutory requirements. Not all permissible uses are applicable to each state.

• Article language: select the language of articles to search in. The English language is used by default.

• Number of articles to extract: specify the maximum number of articles to fetch within the range from 1 to 100. By default, up to 20 articles are retrieved.

• Search time period: select an option to find information published during a specific time frame.

• Minimum risk score: articles that do not meet the minimum risk score are excluded from the results. The default value is 80.

• File types to exclude from results: select the file types that you want to exclude from Google results:

  • HTML is included by default.
  • Non-HTML file types do not have the same meta data and tagging. Excluding them reduces the number of articles to review and false hits by 50% without increasing the risk of missing a true hit.

• High-risk countries: select countries from the drop-down list or type and search. The selected high-risk countries are highlighted in articles returned from each investigation.

warning

To start using Thomson Reuters Clear API, add all public IP addresses of agents to Thomson Reuters Whitelist. For that, contact Thomson Reuters' team. Additionally, Thomson Reuters keystore should be installed to /opt/workfusion/ssl at the Master node. Once it’s installed, create the tr.clear.api.keystore Secrets Vault entry, where the key is the path to the keystore file, and the value is the certificate password.

Provide input data with CSV file

To enable sourcing data from a CSV file, make sure the file has the correct format. To do that, download a CSV file template by clicking the Template link. Files that do not comply with the format requirements are not ingested.

Then, specify the following:

• Input file bucket: specify the S3 bucket name where you need to upload the CSV file.
• Input file location: specify the path to the directory where you need to upload the CSV file.
• Monitoring frequency and Time Unit: configure the interval of monitoring for CSV files.
• Stop monitoring after some iterations: select the checkbox if you want the AI Agent to stop monitoring for new CSV files at the specified location after a predefined number of loops.
• Max Loops: the setting shows after you selected the Stop monitoring after some iterations checkbox. In the field, define how many times the File Ingestion BP should be run to monitor for new CSV files.
• Stop monitoring after some duration: select the checkbox if you want the AI Agent to stop monitoring for new CSV files at the specified location after a predefined period.
• Max Monitoring Duration and Time Unit: the setting shows after you selected the Stop monitoring after some duration checkbox. In the field, define how long the File Ingestion BP should monitor for new CSV files.
• Do you want to ignore dead links?: select Yes if you want the links that don’t work to be excluded from the final result.
• Do you want to ignore articles that redirect?: select Yes if you want the links that return 30X statuses to be excluded from the final result.

Investigation

After setting the Input parameters, click Next to go to the following step of the wizard.

• Do you want the digital worker to identify and group duplicate content?: set to Yes for the AI Agent to identify and group articles by the similarity threshold that you choose. By default, the threshold is set to 50%. However, you can configure it in the field below.

• Do you want to use available meta data to adjudicate articles first?: applicable only for the CSV input file method. Set to Yes for the AMM skill to use the meta data from the input file and process it with the NSS model before running the investigation. To start using it, you also need to configure a signal_id from the Execute NSS step in the Adverse Media Monitoring File Ingestion BP.

  

• Remove legal endings: select Yes to remove legal endings from the company entities. Entities with common names or small businesses (LLCs, S corps) can receive more tailored results when the option is set to No.

• Number of submit investigation tasks: configure how many Submit Investigation Tasks you want to create when running the Ad hoc investigation BP. The recommended setting is one task is per 2-3 analysts.

• Article classification decision model: select the version of the model you want to use. The latest model is selected by default.

• Date of birth matching threshold: articles are marked as False Positive if the difference between the age of the screened entity and the age of the entity in the article is greater than the value configured here. The default setting is 2 years.

• Advanced article classification settings: configure custom investigation statuses and comments for various ML decisions.

Human in the Loop

Configure whether and how you want to enable the Manual Review step (also known as Human in the Loop) by selecting one of the following options:

• Enable in all cases: the AI Agent creates Manual Review steps for every search run.

• Disable when there are no new articles to review: the AI Agent skips the Manual Review step when all retrieved articles are evaluated as False Positive or have been previously reviewed with the False Positive status.

• Disable when all new articles are false positive: the AI Agent skips the Manual Review step when all retrieved articles are evaluated as False Positive or have been previously reviewed with any status.

• Disable in all cases: the AI Agent skips the Manual Review step in all cases, sticking to model decisions.

• Require users to disposition all articles?: set to Yes if you want users to disposition all articles prior to closing an investigation in Workspace.

• Automatically route users to the next task: choose whether you want users to be routed to the next task in the queue. If disabled, users are always taken back to the main queue list after closing or saving an assignment.

• Generate report if manual task expires: if the parameter is set to Yes, when a Manual Task expires, it is considered submitted. The transaction is processed as usual, and a report is generated.

Output

In the last step, specify the output parameters:

• Interface language: select the language of the final report and Manual Tasks.
• Report format: select the report file format for generating a screening request: HTML or PDF.

Review

Once you complete the required fields, review the configuration. You can return to any step to change previous settings before finalizing. If everything looks correct, click Finish. You are now ready to use the Adverse Media Monitoring skill.

Advanced settings

Configure Data Purge

The Data Purge Business Process is an additional part of the Adverse Media Monitoring skill that allows for cleaning up old data on the environment.

Configure Data Purge settings

To configure Data Purge settings, do the following:

1. Log in to Control Tower.

2. Click the Advanced tab and select Data Stores.

3. Select uc_amm_configuration_v1 and set the following parameters:

   Name	Value type	Example	Description
   dataPurge.storagePeriodInDays	Integer	30	Specify how many days should pass after the completion of the transaction to delete the data.
   dataPurge.deleteReports	true/false	false	Set to true to delete generated reports.
   dataPurge.deleteAnalyticsData	true/false	false	Set to true to delete analytics data.
   dataPurge.deleteArticleHistory	true/false	false	Set to true to delete the previous investigation for the same Entity ID.
   dataPurge.articleReviewStoragePeriodInDays	Integer	30	Specify how many days completed investigations should be stored in the database. The parameter works in combination with dataPurge.deleteArticleHistory.

Configure Data Purge scheduling

You can run the Data Purge BP manually or on a schedule.

To configure the schedule, do the following:

1. Log in to Control Tower.

2. Go to the Advanced tab and select Schedules.

3. Click Create.

4. In the Create Schedule window, select the following parameters:

   • In Task or Process Definition, select Adverse Media Monitoring Data Purge vX.X.X | AMM | X.X.X.
   • In Input Data, select Empty.
   • Specify Schedule Period to run Data Purge only for some period. Otherwise, leave it empty.
   • In Schedule Name, set the operation's name, for example, Adverse Media Monitoring Data Purge.
   • In Schedule Frequency, specify days and times when Data Purge must be started. It is recommended to set the time when the environment is least loaded, for example, nightly hours on weekends.

   

5. Click Save.

After that, the purge operation runs automatically on a specified day and time.

To learn more about data purging in Work.AI, see the following guides:

• Data management and purging
• Manage database and S3 data
• Data Management API

Configure REST API endpoints

To configure REST endpoints for Adverse Media Monitoring, perform the following steps:

1. In Control Tower, open the main BP definition Adverse Media Monitoring vX.X.X. On the Data tab, select Streaming Records from External Sources. Here, also specify a custom signal id:

   

2. On the Run tab, click Run This Process.

3. After the BP starts, return to the Run tab and click Show API to find all available generated endpoints:

   

For Adverse Media Monitoring, only asynchronous invocation is supported, in particular the following endpoints:

• /start-record-raw/ to start a BP

• /check-record-status/ to check the status of a running transaction

• /get-record-result/ to get the result data of a finished transaction

For detailed information on invoking transactions and getting access to a token, see Running AI Agents via REST API.

Configure ad-hoc search

To configure the ad-hoc search settings, follow the steps below:

1. Log in to Control Tower.

2. On the main menu, navigate to Advanced > Data Stores.

3. In the Data Store list, select uc_amm_configuration_v1 and enter the values for the following parameter:

Name	Value type	Example	Notes
adHoc.investigationBatchMaxSize	Integer	100	Defines how many entity names can be in one investigation batch.

Verify settings

To check that the Business Process is imported correctly, try running an investigation.