> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Team Learning: Always Mode

> Set learning=True on a Team to enable automatic learning.

```python team_always_learn.py theme={null}
"""
Team Learning: Always Mode
==========================
Set learning=True on a Team to enable automatic learning.

The team automatically captures:
- User profile: name, role, preferences
- User memory: observations, context, patterns

Extraction runs in parallel after each response.
This is the simplest way to add learning to a team.
"""

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIResponses
from agno.team import Team

db = PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai")


# ---------------------------------------------------------------------------
# Create Members
# ---------------------------------------------------------------------------
researcher = Agent(
    name="Researcher",
    model=OpenAIResponses(id="gpt-5.2"),
    role="Research topics and provide detailed information.",
)

writer = Agent(
    name="Writer",
    model=OpenAIResponses(id="gpt-5.2"),
    role="Write clear, concise content based on research.",
)


# ---------------------------------------------------------------------------
# Create Team
# ---------------------------------------------------------------------------
team = Team(
    name="Research Team",
    model=OpenAIResponses(id="gpt-5.2"),
    members=[researcher, writer],
    db=db,
    learning=True,
    markdown=True,
    show_members_responses=True,
)


# ---------------------------------------------------------------------------
# Run Demo
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    user_id = "alice@example.com"

    # Session 1: Share information naturally
    print("\n" + "=" * 60)
    print("SESSION 1: Team learns about the user automatically")
    print("=" * 60 + "\n")

    team.print_response(
        "Hi! I'm Alice, a machine learning engineer. "
        "I prefer technical explanations with code examples. "
        "Can you explain how attention mechanisms work?",
        user_id=user_id,
        session_id="session_1",
        stream=True,
    )

    lm = team.learning_machine
    print("\n--- Learned Profile ---")
    lm.user_profile_store.print(user_id=user_id)
    print("\n--- Learned Memories ---")
    lm.user_memory_store.print(user_id=user_id)

    # Session 2: New session - team remembers
    print("\n" + "=" * 60)
    print("SESSION 2: Team remembers across sessions")
    print("=" * 60 + "\n")

    team.print_response(
        "What do you know about me? And can you explain transformers?",
        user_id=user_id,
        session_id="session_2",
        stream=True,
    )
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno "psycopg[binary]" openai sqlalchemy
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Snippet file="run-pgvector-step.mdx" />

  <Step title="Run the example">
    Save the code above as `team_always_learn.py`, then run:

    ```bash theme={null}
    python team_always_learn.py
    ```
  </Step>
</Steps>

Full source: [cookbook/03\_teams/12\_learning/01\_team\_always\_learn.py](https://github.com/agno-agi/agno/blob/main/cookbook/03_teams/12_learning/01_team_always_learn.py)