Skip to content

Customizing IBM Bob to work with the Building Blocks

IBM Bob custom modes allow developers to tailor Bob's behavior by combining reusable Building Blocks. Numerous modes are available to support work in these areas to address specific operational needs and development workflows.

  • Building agents
  • MCP creation and integration
  • Vector Search & Document Processing
  • Data Engineering & Knowledge Pipelines
  • Application Observability & Monitoring
  • Security, Risk & Trust Intelligence

This composable approach enables teams to design highly contextual assistants optimized for specialized tasks and domain-specific scenarios.

Getting started with Building Block modes

Instructions and related files for these custom modes can be found in their respective repository.

Building Blocks Explorer

  • Building Blocks Explorer: A generic Bob mode that connects to an MCP server to detect all available Building Blocks. Use it to discover capabilities across the catalog and find the right assets for your use case.

AI

Agents

  • Agent Builder: Foundation mode for agent building workflows, Bob uses wxo's ADK and documentation MCP servers to build custom agents.
  • Domain Agent Builder: Bob builds a tool-augmented RAG agent for partner's custom business domain.
  • Voice Agent Builder: Build voice-enabled agents (TTS & STT) with multi-channel support (phone, WhatsApp, SMS, Slack)
  • MCP Builder: Expands on the Agent Builder mode to build and deploy MCP servers on wxo.
  • Agent-model-gateway-bob-mode: Comprehensive mode for integrating third-party LLM models (OpenAI, Anthropic, Google, Azure, AWS Bedrock, and more) into watsonx Orchestrate
  • Agent-Integrate Mode: Comprehensive custom mode for integrating IBM watsonx Orchestrate agents into applications via REST API. Provides end-to-end support from agent creation to production-ready code deployment, handling authentication, connection testing, and code generation across all deployment platforms (IBM Cloud, AWS, AWS GovCloud, and On-premises).

AI Trust

  • Agent Ops: Foundation Mode for pre-deployment evaluation of WXO agents. Using WXO ADK, Bob automates benchmark generation and provides a structured workflow for assessing agent behavior across key dimensions, including agent-specific metrics, cost and latency characteristics, and adversarial robustness through red-teaming.
  • Model Evaluation: Bob helps you evaluate GenAI apps (RAG pipelines, LLM outputs, chatbot safety) using IBM watsonx governance SDK and custom watsonx governance MCP server.

Data

Data Integration

  • Data Ingestion: Comprehensive data ingestion mode for both structured and unstructured data sources. Bob assists in building data pipelines, configuring connectors, and implementing data transformation logic for batch and streaming ingestion.

Data Intelligence

  • Text-to-SQL: Natural language to SQL query conversion mode with metadata enrichment. Bob helps build and optimize Text2SQL systems, configure schema understanding, and implement query validation for business intelligence applications.

Data Retrieval

  • Vector Search: Complete vector search mode with document processing and semantic search capabilities. Bob assists in building vector search systems, configuring embedding models, and optimizing retrieval strategies for question-answering applications.

Automation

Build and Deploy

  • Ansible Ops: Ansible Operations with Ansible playbook to deploy the Retail Application on RedHat OpenShift Cluster.

Optimize

Secure

Other