Calendar Daily Briefing

daily_briefing.py

"""
Calendar Daily Briefing
=======================
Summarizes today's schedule into a structured briefing with meeting prep notes.

The agent fetches today's events, classifies each by type (meeting, focus time,
personal), identifies gaps, and flags conflicts or back-to-back meetings.

Key concepts:
- output_schema: structured briefing matching DailyBriefing model
- add_datetime_to_context: agent knows today's date for time-aware queries
- get_event + list_events: fetches overview then drills into details

Setup:
1. Create OAuth credentials at https://console.cloud.google.com (enable Calendar API)
2. Export GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, GOOGLE_PROJECT_ID env vars
3. pip install openai google-api-python-client google-auth-httplib2 google-auth-oauthlib
4. First run opens browser for OAuth consent, saves token.json for reuse
"""

from typing import List, Literal, Optional

from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.tools.google.calendar import GoogleCalendarTools
from pydantic import BaseModel, Field


class MeetingItem(BaseModel):
    title: str = Field(..., description="Event title")
    start_time: str = Field(..., description="Start time (HH:MM format)")
    end_time: str = Field(..., description="End time (HH:MM format)")
    duration_minutes: int = Field(..., description="Duration in minutes")
    category: Literal["meeting", "focus_time", "personal", "travel", "other"] = Field(
        ..., description="Event category based on title and attendees"
    )
    attendee_count: int = Field(0, description="Number of attendees")
    location: Optional[str] = Field(None, description="Event location or video link")
    prep_note: Optional[str] = Field(
        None, description="One-line prep note if this is a meeting with others"
    )


class DailyBriefing(BaseModel):
    date: str = Field(..., description="Today's date in YYYY-MM-DD format")
    total_events: int = Field(..., description="Total number of events today")
    total_meeting_hours: float = Field(..., description="Total hours in meetings")
    free_hours: float = Field(..., description="Estimated free hours between 9am-6pm")
    events: List[MeetingItem] = Field(
        default_factory=list, description="All events in chronological order"
    )
    conflicts: List[str] = Field(
        default_factory=list,
        description="Overlapping events or back-to-back warnings",
    )
    summary: str = Field(..., description="2-3 sentence overview of the day")


agent = Agent(
    name="Daily Briefing Agent",
    model=OpenAIResponses(id="gpt-5.5"),
    tools=[
        GoogleCalendarTools(
            create_event=False,
            update_event=False,
            delete_event=False,
        )
    ],
    instructions=[
        "Fetch today's events and classify each as meeting, focus_time, personal, travel, or other.",
        "A 'meeting' has 2+ attendees. 'focus_time' is a solo block. 'personal' is non-work.",
        "Calculate total meeting hours and free hours (9am-6pm minus events).",
        "Flag conflicts: overlapping events or back-to-back meetings with no gap.",
        "Add a prep_note for meetings: mention the key attendee or agenda if visible.",
        "Write a 2-3 sentence summary highlighting the busiest part of the day.",
    ],
    output_schema=DailyBriefing,
    add_datetime_to_context=True,
    markdown=True,
)


if __name__ == "__main__":
    agent.print_response(
        "Give me my daily briefing for today",
        stream=True,
    )

    # Briefing for a specific date
    # agent.print_response(
    #     "Give me a briefing for next Monday",
    #     stream=True,
    # )

For a full-day briefing, instruct the agent to pass explicit local-midnight start and end timestamps with UTC offsets, then follow nextPageToken. list_events otherwise starts at the current time and returns one page. Meeting totals and free hours are model calculations; overlapping and all-day events need to be accounted for rather than simply summing durations.

Run the Example

Set up your virtual environment

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

Install dependencies

uv pip install -U agno google-api-python-client google-auth google-auth-httplib2 google-auth-oauthlib openai

Configure Google OAuth

Enable the Google API used by this example, configure the consent screen, and create a Desktop OAuth client in your Cloud project. Export its GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, and GOOGLE_PROJECT_ID, or place the downloaded client JSON at credentials.json in the directory where you run Python. Google's Python quickstart shows the Desktop client setup.

The first tool call opens a browser for consent and caches credentials in token.json. Use a separate token_path when switching accounts. Passing an Agno user_id does not switch the authenticated Google account.

Export environment variables

export GOOGLE_CLIENT_ID="your_google_client_id_here"
export GOOGLE_CLIENT_SECRET="your_google_client_secret_here"
export GOOGLE_PROJECT_ID="your_google_project_id_here"
export OPENAI_API_KEY="your_openai_api_key_here"

Run the example

Save the code above as daily_briefing.py, then run:

python daily_briefing.py

Full source: cookbook/91_tools/google/calendar/daily_briefing.py