Team with Followup Suggestions

Generate actionable followup prompts after every team response.

Set followups=True on a Team to automatically generate followup prompt suggestions after each response. Works the same way as agent followups, with support for all team modes.

Create a Python file

1from kern.agent import Agent
2from kern.models.openai import OpenAIResponses
3from kern.team.team import Team
4from kern.team.mode import TeamMode
5
6researcher = Agent(
7    name="Researcher",
8    role="Research topics thoroughly",
9    model=OpenAIResponses(id="gpt-4o"),
10)
11
12team = Team(
13    name="Research Team",
14    model=OpenAIResponses(id="gpt-4o"),
15    mode=TeamMode.coordinate,
16    members=[researcher],
17    followups=True,
18    num_followups=3,
19)
20
21response = team.run("What are the latest advances in fusion energy?")
22
23print(response.content)
24print("\nFollowup suggestions:")
25for i, suggestion in enumerate(response.followups, 1):
26    print(f"  {i}. {suggestion}")

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Install dependencies

1uv pip install -U kern-ai openai

Export your OpenAI API key

1export OPENAI_API_KEY="your_openai_api_key_here"

1$Env:OPENAI_API_KEY="your_openai_api_key_here"

Run Team

1python team_followup_suggestions.py

Options

Parameter	Type	Default	Description
`followups`	`bool`	`False`	Enable followup suggestion generation
`num_followups`	`int`	`3`	Number of suggestions to generate (minimum 1)
`followup_model`	`Model`	Team's model	Separate model for generating followups. Use a smaller model to reduce cost.

Streaming

Followup suggestions are available via events when streaming.

1import asyncio
2
3from kern.agent import Agent
4from kern.models.openai import OpenAIResponses
5from kern.team.team import Team
6from kern.team.mode import TeamMode
7from kern.team import TeamRunEvent
8
9researcher = Agent(
10    name="Researcher",
11    role="Research topics thoroughly",
12    model=OpenAIResponses(id="gpt-4o"),
13)
14
15team = Team(
16    name="Research Team",
17    model=OpenAIResponses(id="gpt-4o"),
18    mode=TeamMode.coordinate,
19    members=[researcher],
20    followups=True,
21    num_followups=3,
22)
23
24
25async def main():
26    async for event in team.arun(
27        "What are the latest advances in fusion energy?",
28        stream=True,
29        stream_events=True,
30    ):
31        if event.event == TeamRunEvent.run_content and event.content:
32            print(event.content, end="", flush=True)
33
34        if event.event == TeamRunEvent.followups_completed:
35            print("\n\nFollowup suggestions:")
36            for i, suggestion in enumerate(event.followups, 1):
37                print(f"  {i}. {suggestion}")
38
39
40asyncio.run(main())