The Model steps (previously, AutoML Bridge) enable integrating and executing a Machine Learning (ML) model or model-related operations in a Business Process (BP). In addition to the legacy Execute AutoML Model (AutoML Bridge) step, Work.AI offers the following no-code Model steps:
To customize the Answer style, perform the following actions:
You can use links to secure S3 buckets in the input data files for Manual Tasks and Business Processes.
The no-code Rate Limiter bot step enables you to control the number of records passing through the step within a specific time frame. This is particularly beneficial for implementing rate-limiting at a granular level, such as per AI Agent, reducing the impact on resources when two AI Agents are running in a single environment.
The Data Store module is a web interface for managing database (DB) tables in the Work.AI platform. A field scheme defines the Data Store table structure and column data format.
The article focuses on applying the FreeMarker Template Language to deliver a legacy Manual Task design via Code Editor.
A Business Process (BP) is an automation flow combining various code based and no-code elements, such as Manual Tasks, Bot Tasks, Model steps, decision or transformation rules, or nested processes. Work.AI allows you to implement two types of Business Processes (BP):
A crucial aspect of installation and further support is implementing an AI Agent (or AI Digital Worker) so that you can change any setting outside of the implementation code without recompiling, updating, or re-deploying your AI Digital Worker. Typically, this is achieved by making your configuration external to the source code.
Custom attributes are user-defined data fields that extend or customize task and process data. These attributes rely on Field Schemes to determine how data is stored and interpreted.
Work.AI offers the following OCR providers:
Connectors in the Work.AI platform enable Business Processes (BPs) and AI Agents to communicate with external systems. They provide standardized integration points for retrieving and enriching data, sending information to third-party services, triggering workflows based on external events, and orchestrating end-to-end automation across enterprise environments.
The Correlated Fields Answer Type allows you to repeat a block of answer fields, enabling workers to dynamically add answers. This feature is useful when the number of task answers is unknown, for example, "Find all members of the Board of Directors from an annual report".
Before reading this topic, see the detailed Operation description.
The instruction contains customization samples for legacy Manual Task designs in some of the most typical scenarios. There're two groups of samples described for the following groups of Manual Tasks:
When adding or editing an Answer, you must set an Answer Type. The parameter defines the type and format of the input field.
All stored procedures supporting the Data Management API functionality reside within the dp schema and are divided into the following subsets:
When two or more users are editing the same Business Process (BP) or different runs of the same BP, the WorkFusion engine detects the activity and performs the following actions:
Data flow
FIFO (First In, First Out) is a prioritization strategy in which the oldest (first) entry is processed first. The FIFO strategy helps improve adherence to the service-level agreement (SLA) for record processing time.
The qualification mechanism is no longer available for access control purposes and is replaced by a new user management approach. However, to support training before employees begin performing actual tasks, WorkFusion provides a special Qualification Business Process (BP), which you can deploy and configure as described below.
In an Asset Bundle, Business Process (BP) scheduler configurations are located in the bp-scheduler folder as shown below. For the complete Asset Bundle structure, refer to the guide.
The article details how to import database and S3 data management configurations as part of an Asset Bundle.
Information Extraction (IE) is a special answer type used for extracting structured content from raw unstructured text. It displays input data as non-editable text where a user can select text chunks and tag them.
The article lists operators supported for no-code Transformation and Decision rules steps.
Global variables store common values used in different Business Processes (BPs) without hard-coding them in Bot Tasks. In particular, global variables can store the following information:
The Answer Types tab allows creating and managing Answer Types in Control Tower. These Answer Types are used for the following actions:
The Work.AI platform lets users create the following types of data management configurations:
Templates allow you to reuse objects. Almost every object in the Work.AI platform, including Manual Tasks and Business Processes, is based on templates.
The guide explains how to add a Manual Task to a Business Process based on ODF 2. When working with Manual Tasks, consider the following aspects:
The System Preferences page contains all Control Tower parameters, but it is available only to users with Administrator privileges. To access it, go to System Settings > System preferences.
High-level description
The instruction describes running, stopping, and scheduling Business Processes based on the ODF 2 example project.
Besides running Business Processes (BPs) manually, you can set them to run on schedule.
Download the Scheduler Business Process package.
Control Tower allows multiple teams to work collaboratively in the same environment. For that, filters are used to give specific user groups access to certain Control Tower items while hiding others. As a result, several teams can use the same Control Tower instance to perform different tasks without interfering with each other's work. To set up filters, go to System Settings > Filters.
To manage the access to Superset dashboards and related components, use standard Control Tower roles and permissions. To view or change the Superset-related permissions in Control Tower, navigate to System setting > Role management.
To configure the settings for a specific Business Process (BP) run, navigate to the Run page of the BP instance you want to run.
Software development life cycle (SDLC) is a process for planning, creating, testing, and deploying an information system. The instruction focuses on a recommended SDLC approach for the Work.AI automation solution implementation.
Split and merge records
The information in the article relates to the low-code approach of creating AI Agents using Work.AI Developer.
If you have several Business Processes (BP) where one BP produces data for another, you can apply the event-based communication mechanism and configure the data transfer between them. You can set a sub-process to start from another BP based on a specific event or set transaction processing to be launched from another transaction in a different BP using no-code sub-process steps.
You can start a Business Process (BP) from a Manual Task. Below are some code samples of how you can perform various operations with it.
A Data Source is a mechanism providing input data and configuration for your Business Processes (BPs) and tasks. The input format is best suited for those use cases where the data resides on an external source, such as an SFTP Server or Amazon S3 Cloud.
While designing a Business Process (BP), it is helpful to use a synchronization design pattern.
Transaction tracking is applied at the Business Process (BP) level. It is possible to track only specific or multiple steps or exclude them from tracking. The feature enables collecting Service-Level Agreement (SLA) and Straight-Through Processing (STP) metrics and getting them displayed.
The guide is intended for IT Operations Support Engineers who own the Work.AI platform environment. Those engineers are expected to have access permissions to configure servers for the Open Development Framework (ODF).
The Split-Join rule is used to separate every single record (or document) from Input Data into a few records to let them pass through different steps (either Bot or Manual Tasks) of a Business Process (BP) in parallel (in the split point) and then combine the processed records back into a single record or a document (in the join point) to process the consolidated results from the previous steps further.