Edges
Edges
Edges connect nodes within a agentic workflow. Every agentic workflow must begin with a Start Node and end with one or more End Node.
Node types
Node types
The system supports the following node type right now and more will be added over time:
- Flow Node: A node that represents a agentic workflow or a nested agentic workflow.
- Start Node: The entry point of a agentic workflow. Each agentic workflow must have exactly one Start Node.
- End Node: The exit point of a agentic workflow. A agentic workflow must have at least one End Node.
- Tool Node: Call an imported tool and returns its result.
- Agent Node: Call an imported agent to perform a certain task.
- Decisions Node: (Public Preview) Specify a decision table to determine actions based on provided conditions.
- Prompt Node: (Public Preview) Make a LLM call to extract/classify/generate information based on provided input.
- Doc Processing Node: (Public Preview) Extract text from a provided document.
- Branch Node: A conditional branch. Currently, only binary branches are supported.
- Foreach Node: A nested agentic workflow that iterates over a list of items until it is done.
- Loop Node: A nested agentic workflow that iterates over a condition as long as it is true.
Node specification
Node specification
Each node includes a specification that defines its behavior and properties:
- kind: The type of node. For example:
tool,user,agent. - name: The internal name of the node.
- display_name (optional): A user-friendly name for display purposes.
- description (optional): A brief description of the node’s purpose.
- input_schema (optional): The input schema of the node. By default there are no input schemas.
- output_schema (optional): The output schema of the node. By default there are no output schemas.
Data mapping
Data mapping
Currently, agentic workflows supports automatic runtime data mapping only.
Scheduling
Scheduling
(Public Preview) It is also possible to schedule a agentic workflow or an Agent to run at a later today. See the section on
Scheduler for details.Examples
Examples
The
examples/flow_builder directory includes sample agentic workflow that demonstrate key agentic workflow features:- agent_scheduler: Demonstrates agent scheduling.
- collaborator_agents: Shows how to sequence multiple agents.
- extract_support_request: Uses an LLM to extract information from support requests.
- foreach_email: Applies the
Foreachcontrol to iterate over a set of items. - get_facts_numbers: Uses the
Loopcontrol to repeat work until a condition is met. - get_insurance_rate: Uses a
Decisionsnode to determine insurance rates based on credit rating and loan amount. - get_pet_facts: Demonstrates branching to route requests.
- get_tuition_reimbursed: Uses multiple branches to support complex logic routing.
- hello_message_flow: Sequences two Python tools together.
- ibm_knowledge_to_emails: Combines an agent and a tool in a single agentic workflow.
- schedule_helpdesk_alert: Creates a schedulable agentic workflow to check helpdesk availability.
- text_extract: Uses the
DocProcnode to extract text from a document.
When to use agentic workflow
When to use agentic workflow
Use agentic workflow in the following scenarios:
- Repeatable, predictable sequencing of agents, tools, and human tasks is required.
- Long-running processes are involved. Agentic workflow supports extended task chains that can take minutes, hours, or even days to complete.
- Human-in-the-loop interaction is needed for approvals or decision-making.
- Scheduling is necessary to trigger tasks at specific times or intervals.
Note:
- When a agentic workflow tool is invoked, the system returns an instance ID and waits for the response.
- To check the progress, use the Get agentic workflow status tool in a new chat session. Provide the instance ID to retrieve the current status of the agentic workflow.

