How-to Guides

Within this section, you will find answers to “How do I…” types of questions. The proposed guides are goal-oriented and concrete, as they are meant to help you complete a specific task. Each code example in these how-to guides is self-contained and can be executed with WayFlow.

For comprehensive, end-to-end walkthroughs, refer to the Tutorials. For detailed descriptions of every class and function, see the API Reference.

Building Assistants

WayFlow offers a wide range of features for building Agents, Flows as well as multi-agent patterns such as hierarchical multi-agent and Swarm. These how-to guides demonstrate how to use the main features to create and customize your assistants.

• Change Input and Output Descriptors of Components
• Use Asynchronous APIs

Agents

• Create a ReAct Agent
• How to Send Images to LLMs and Agents
• Use OCI Generative AI Agents
• Use Templates for Advanced Prompting Techniques

Flows

• Ask for User Input in Flows
• Create Conditional Transitions in Flows
• Do Structured LLM Generation in Flows
• Add User Confirmation to a Tool Call Request
• Catch Exceptions in Flows
• Do Map and Reduce Operations in Flows

Multi-Agent Patterns

• Use Agents in Flows
• Build a Hierarchical Multi-Agent System
• Build a Swarm of Agents
• Build a ManagerWorkers of Agents

Tools in Assistants

Equipping AI assistants with tools unlock key capabilities such as being able to fetch data, take action, and connect to external data and systems. These guides cover how to leverage the several tools features available in WayFlow, such as server-side tools, client-side tools, tools to perform remote API calls, and support for Model Context Protocol (MCP) tools.

• Build Assistants with Tools
• Create Tools with Multiple Outputs
• Convert Flows to Tools
• Connect MCP tools to Assistants
• Do Remote API Calls with Tokens

Configuration and State Management

These guides demonstrate how to configure the components of assistants built with WayFlow.

• Load and Execute an Agent Spec Configuration
• Serialize and Deserialize Flows and Agents
• Serialize and Deserialize Conversations
• Specify the Generation Configuration when Using LLMs
• Use LLM from Different LLM Sources and Providers
• Install and Use Ollama
• Enable Tracing

Data in Assistants

• Connect Assistants to Your Data
• Use Embedding Models from Different Providers
• How to Evaluate WayFlow Assistants
• How to Evaluate Assistant Conversations
• Use Variables for Shared State in Flows