Implementation

Tools need to be tied to an actual implementation that backs it up. E.g. GetCustomerProfile needs to make a REST API call from a system that provides customer profiles; GetCustomerOrders need to make a query to a MongoDB operational database to get orders of a customer. When we create a tool, we create it in the context of a specific system.

Dataworkz supports a broad range of implementations:

• Datasets

  • for quick tabular queries

  • for table writes

• RAG Applications for document retrieval with metadata filters.

• Relational Databases like MySQL, Oracle, or Postgres.

• MongoDB for JSON-based collections.

• Snowflake for enterprise-scale analytics.

• REST or GraphQL APIs.

• LLM-based tools with system/user prompts.

• Composite/Workflow tools that combine multiple calls.

• Call Agent tools that delegate to other Agents.

By mixing implementations, you can give an Agent both breadth (access to many systems) and depth (specialized problem-solving).

Example: A Compliance Assistant might combine a RAG Application for policies, a REST API for employee records, and Snowflake for transaction history.

Each tool implementation has its own specific configuration that helps it to connect and to retrieve data from the system it describes.