agentic_mode.py
"""
User Profile: Agentic Mode (Deep Dive)
======================================
Agent-controlled profile updates via explicit tools.
AGENTIC mode gives the agent a tool to update profile fields.
You'll see tool calls in the response - more transparent than ALWAYS mode.
Compare with: 01_always_extraction.py for automatic extraction.
See also: 01_basics/1b_user_profile_agentic.py for the basics.
"""
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.learn import LearningMachine, LearningMode, UserProfileConfig
from agno.models.openai import OpenAIResponses
# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
db = PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai")
agent = Agent(
model=OpenAIResponses(id="gpt-5.5"),
db=db,
instructions=(
"You are a helpful assistant. "
"When users share their name or preferences, use update_user_profile to save it."
),
learning=LearningMachine(
user_profile=UserProfileConfig(
mode=LearningMode.AGENTIC,
),
),
markdown=True,
)
# ---------------------------------------------------------------------------
# Run Demo
# ---------------------------------------------------------------------------
if __name__ == "__main__":
user_id = "jordan@example.com"
# Session 1: Share name - watch for tool calls
print("\n" + "=" * 60)
print("SESSION 1: Share name (watch for tool calls)")
print("=" * 60 + "\n")
agent.print_response(
"Hi! I'm Jordan Chen, but everyone calls me JC.",
user_id=user_id,
session_id="session_1",
stream=True,
)
agent.learning_machine.user_profile_store.print(user_id=user_id)
# Session 2: Recall in new session
print("\n" + "=" * 60)
print("SESSION 2: Profile recalled in new session")
print("=" * 60 + "\n")
agent.print_response(
"What's my name and what should you call me?",
user_id=user_id,
session_id="session_2",
stream=True,
)
agent.learning_machine.user_profile_store.print(user_id=user_id)
# Session 3: Update preferred name
print("\n" + "=" * 60)
print("SESSION 3: Update preferred name")
print("=" * 60 + "\n")
agent.print_response(
"Actually, I'd prefer you call me Jordan from now on.",
user_id=user_id,
session_id="session_3",
stream=True,
)
agent.learning_machine.user_profile_store.print(user_id=user_id)
Run the Example
1
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
2
Install dependencies
uv pip install -U agno openai psycopg-binary sqlalchemy
3
Export your OpenAI API key
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
4
Run PgVector
docker run -d \
-e POSTGRES_DB=ai \
-e POSTGRES_USER=ai \
-e POSTGRES_PASSWORD=ai \
-e PGDATA=/var/lib/postgresql/data/pgdata \
-v pgvolume:/var/lib/postgresql/data \
-p 5532:5432 \
--name pgvector \
agnohq/pgvector:18
5
Run the example
Save the code above as
agentic_mode.py, then run:python agentic_mode.py