Use this file to discover all available pages before exploring further.
An agentic workflow is a collection of nodes and edges that define the logic of your workflow. To build an agentic workflow, follow these steps:
1
Import your agents and tools
Ensure that the agents and tools you want to connect in an agentic workflow are already imported.
2
Define a Python function with the @flow decorator
Use the @flow decorator to define your agentic workflow. In the decorator, specify the agentic workflow’s name, display_name, description, input_schema, output_schema, initiators, schedulable, llm_model, and agent_conversation_memory_turns_limit.
The function must take a single parameter of type Flow and return a Flow object.
Construct the agentic workflow using a combination of tool(), agent(), and edge-building functions like sequence() or edge().
For Branch and Loop nodes, use a Python expression in the evaluator to define the branching or looping condition. For more information, see Agentic workflow expressions.
When you use forms in user nodes, connect the form buttons to the next node in the flow using the edge() function with the button_label parameter. This connection enables users to trigger the transition to the next node when they click a button on the form.
The following tabs show some code snippet examples of agentic workflow:
Example 1
Example 2
Example 3
Example 4
Example 5
Example 1: Sequencing two tools
Python
@flow( name = "hello_message_flow", input_schema=Name, output_schema=str)def build_hello_message_flow(aflow: Flow = None) -> Flow: """ Based on the first and last name of a person, combine into a single name and create a simple hello world message. """ combine_names_node = aflow.tool(combine_names) get_hello_message_node = aflow.tool(get_hello_message) aflow.edge(START, combine_names_node).edge(combine_names_node, get_hello_message_node).edge(get_hello_message_node, END) return aflow
@flow( name="ibm_knowledge_to_emails", description="This flow will send a random fact about IBM to a group of people", input_schema=FlowInput, output_schema=FlowOutput)def build_ibm_knowledge_to_emails(aflow: Flow) -> Flow: """ Retrieve a random fact about IBM and send it out to an email list. """ ask_agent_for_ibm_knowledge = aflow.agent( name="ask_agent_for_ibm_knowledge", agent="ibm_agent", display_name="ask_agent_for_ibm_knowledge", message="Please retrieve a random fact about IBM on a topic.", description="Get a random fact about IBM.", input_schema=IBMAgentInput, output_schema=IBMAgentOutput, ) ask_agent_to_send_email_node = aflow.agent( name="ask_agent_to_send_email", agent="email_agent", display_name="ask_agent_to_send_email", message="Please send email based on the following email addresses and based on a fact about IBM.'", description="This agent will send email content to a list of email addresses", input_schema=EmailAgentInput, output_schema=EmailAgentOutput, ) aflow.sequence(START, ask_agent_for_ibm_knowledge, ask_agent_to_send_email_node, END) return aflow
@flow( name = "get_pet_facts", input_schema = Pet, output_schema = PetFacts)def build_get_pet_facts_flow(aflow: Flow) -> Flow: """ Based on the request, we will return the list of facts about the pet. A pet can be either a cat or a dog. """ dog_fact_node = aflow.tool("getDogFact") cat_fact_node = aflow.tool("getCatFact") # create a branch check_pet_type_branch: Branch = aflow.branch(evaluator="flow.input.kind.strip().lower() == 'dog'") aflow.edge(START, check_pet_type_branch) # edges are automatically added when cases are added check_pet_type_branch.case(True, dog_fact_node).case(False, cat_fact_node) aflow.edge(dog_fact_node, END) aflow.edge(cat_fact_node, END) return aflow
For the full example and complete code, see get_pet_facts.
Example 4: Foreach
Python
@flow( name="send_invitation_to_customer", input_schema=CustomerName, output_schema=None)def build_send_invitation_to_customer_flow(aflow: Flow) -> Flow: """ Given a list of customers, we will iterate through the list and send email to each """ get_customer_list_node = aflow.tool(get_emails_from_customer) # calling add_foreach will create a subflow, and we can add more node to the subflow foreach_flow: Flow = aflow.foreach(item_schema = CustomerRecord) node2 = foreach_flow.tool(send_invitation_email) foreach_flow.sequence(START, node2, END) # add the foreach flow to the main flow aflow.edge(START, get_customer_list_node) aflow.edge(get_customer_list_node, foreach_flow) aflow.edge(foreach_flow, END) return aflow
For the full example and complete code, see foreach_email.
Example 5: Connecting form buttons to the next node
Python
@flow( name="feedback_form_flow", input_schema=None,)def build_feedback_form_flow(aflow: Flow) -> Flow: """ Create a flow with a feedback form that connects to a confirmation message. """ # Create a user flow user_flow = aflow.userflow() user_flow.spec.display_name = "Feedback Form" # Create the main form feedback_form = user_flow.form(name="feedback_form", display_name="Customer Feedback") # Add form fields feedback_form.text_input_field( name="customer_name", label="Name", required=True, placeholder_text="Enter your name" ) feedback_form.text_input_field( name="feedback_text", label="Feedback", required=True, placeholder_text="Share your feedback" ) # Create a confirmation message node confirmation_message = user_flow.field( direction="output", name="confirmation", display_name="Confirmation", kind=UserFieldKind.Text, text="Thank you for your feedback!" ) # Connect the form button to the confirmation message user_flow.edge(START, feedback_form) user_flow.edge(feedback_form, confirmation_message, button_label="Submit") user_flow.edge(confirmation_message, END) # Add the user flow to the main flow aflow.sequence(START, user_flow, END) return aflow
When you use forms in user nodes, the button_label parameter in the edge() function connects a specific button on the form to the next node. This connection enables the flow to transition to the appropriate next step when users click the button.
3
Import the agentic workflow
Import the agentic workflow as a tool using the orchestrate tools import command in the CLI.
