Aggregator

Agents contribute specialized outputs that are collected and synthesized by an aggregator agent into a single, well-formatted result.

Overview

Reach for this pattern when multiple agents (or tools) produce complementary information and you want a unified summary. Executive briefings, dashboards, and cross-team status reports are common fits.

Demo Scenario: Daily Briefing Synthesizer

This runnable example assembles a morning briefing by combining three specialists:

• Time & calendar agent – pulls the current time and today's events

• Weather agent – reports the local forecast

• Aggregator agent – stitches everything together into a friendly briefing

Each specialist uses a mock tool that returns static values so the demo works out of the box; swap the tools for real integrations to connect to live data.

Diagram

Implementation Steps

1. Import tools and create specialist agents

   from glaip_sdk import Agent
   from tools import MockTimeTool, MockCalendarTool, MockWeatherTool
   
   time_calendar_agent = Agent(
       name="time_calendar_agent",
       instruction="Use mock_time to get the current time and mock_calendar to get today's highlights.",
       description="Time Calendar Agent",
       tools=[MockTimeTool, MockCalendarTool],
   )
   
   weather_agent = Agent(
       name="weather_agent",
       instruction="Use mock_weather to get today's weather forecast.",
       description="Weather Agent",
       tools=[MockWeatherTool],
   )
   
   aggregator_agent = Agent(
       name="aggregator_agent",
       instruction="Synthesize a concise morning briefing from provided inputs.",
   )

2. Run specialists, pass their outputs to the aggregator, and print the result

   time_calendar_output = time_calendar_agent.run(
       "Get the current time and today's main calendar highlights."
   )
   weather_output = weather_agent.run("Get today's weather forecast.")
   
   prompt = (
       "Synthesize a friendly morning briefing from the following inputs.\n"
       f"- {time_calendar_output}\n"
       f"- {weather_output}"
   )
   aggregator_agent.run(prompt)

3. Clean up demo agents

   # Only needed if agents were deployed
   # aggregator_agent.delete()
   # weather_agent.delete()
   # time_calendar_agent.delete()

How to Run

From the repository root glaip-sdk/python/glaip-sdk:

poetry run python examples/multi-agent-system-patterns/aggregator/aggregator.py

Ensure your .env contains:

OPENAI_API_KEY=your-openai-key-here

Output

───────────────────────── 🤖 aggregator_agent  ✓ · 4.0s ────────────────────────────╮
│ Good morning! It’s 9:00 AM UTC.                                                        │
│                                                                                       │
│ • Today’s highlight: meeting with the development team at 2 PM.                       │
│ • Weather: partly cloudy, rain starting around 3 PM with temps near 72°F.             │
│                                                                                       │
│ Have a productive day!                                                                │
╰───────────────────────────────────────────────────────────────────────────────────────╯

Notes

• Replace the mock tool scripts under examples/multi-agent-system-patterns/aggregator/tools/ with real integrations to connect to live systems.

• Add more specialists (finance, news, incidents) and expand the prompt to build richer reports.

• Combine this pattern with a router or scheduler for automated briefings.

Related Documentation

• Agents guide — Configure agent instructions and manage lifecycles.

• Tools guide — Upload Python tools and reference their IDs.

• Automation & scripting — Schedule or orchestrate the aggregator run in CI.

• Security & privacy — Apply PII masking or output-sharing policies when aggregating data.