Agentic AI 103: Constructing Multi-Agent Groups

Introduction

articles right here in TDS, we explored the basics of Agentic AI. I’ve been sharing with you some ideas that may enable you navigate by way of this sea of content material we now have been seeing on the market.

Within the final two articles, we explored issues like:

• Learn how to create your first agent
• What are instruments and find out how to implement them in your agent
• Reminiscence and reasoning
• Guardrails
• Agent analysis and monitoring

Good! If you wish to examine it, I counsel you take a look at the articles [1] and [2] from the References part.

Agentic AI is among the hottest topics for the time being, and there are a number of frameworks you possibly can select from. Luckily, one factor that I’ve seen from my expertise studying about brokers is that these basic ideas could be carried over from one to a different.

For instance, the category Agent from one framework turns into chat in one other, and even one thing else, however often with related arguments and the exact same goal of connecting with a Giant Language Mannequin (LLM).

So let’s take one other step in our studying journey.

On this submit, we’ll learn to create multi-agent groups, opening alternatives for us to let AI carry out extra advanced duties for us.

For the sake of consistency, I’ll proceed to make use of Agno as our framework.

Let’s do that.

Multi-Agent Groups

A multi-agent workforce is nothing greater than what the phrase means: a workforce with multiple agent.

However why do we want that?

Effectively, I created this straightforward rule of thumb for myself that, if an agent wants to make use of greater than 2 or 3 instruments, it’s time to create a workforce. The explanation for that is that two specialists working collectively will do a lot better than a generalist.

If you attempt to create the “swiss-knife agent”, the likelihood of seeing issues going backwards is excessive. The agent will develop into too overwhelmed with completely different directions and the amount of instruments to cope with, so it finally ends up throwing an error or returning a poor consequence.

However, while you create brokers with a single objective, they’ll want only one instrument to resolve that downside, due to this fact growing efficiency and enhancing the consequence.

To coordinate this workforce of specialists, we’ll use the category Workforce from Agno, which is ready to assign duties to the correct agent.

Let’s transfer on and perceive what we’ll construct subsequent.

Undertaking

Our venture shall be targeted on the social media content material technology business. We’ll construct a workforce of brokers that generates an Instagram submit and suggests a picture primarily based on the subject supplied by the consumer.

1. The consumer sends a immediate for a submit.
2. The coordinator sends the duty to the Author
   • It goes to the web and searches for that matter.
3. The Author returns textual content for the social media submit.
4. As soon as the coordinator has the primary consequence, it routes that textual content to the Illustrator agent, so it may create a immediate for a picture for the submit.

Discover how we’re separating the duties very properly, so every agent can focus solely on their job. The coordinator will ensure that every agent does their work, and they’re going to collaborate for a great remaining consequence.

To make our workforce much more performant, I’ll prohibit the topic for the posts to be created about Wine & Wonderful Meals. This manner, we slender down much more the scope of data wanted from our agent, and we will make its position clearer and extra targeted.

Let’s code that now.

Code

First, set up the mandatory libraries.

pip set up agno duckduckgo-search google-genai

Create a file for atmosphere variables .env and add the wanted API Keys for Gemini and any search mechanism you might be utilizing, if wanted. DuckDuckGo doesn’t require one.

GEMINI_API_KEY="your api key"
SEARCH_TOOL_API_KEY="api key"

Import the libraries.

# Imports
import os
from textwrap import dedent
from agno.agent import Agent
from agno.fashions.google import Gemini
from agno.workforce import Workforce
from agno.instruments.duckduckgo import DuckDuckGoTools
from agno.instruments.file import FileTools
from pathlib import Path

Creating the Brokers

Subsequent, we’ll create the primary agent. It’s a sommelier and specialist in gourmand meals.

• It wants a title for simpler identification by the workforce.
• The position telling it what its specialty is.
• A description to inform the agent find out how to behave.
• The instruments that it may use to carry out the duty.
• add_name_to_instructions is to ship together with the response the title of the agent who labored on that activity.
• We describe the expected_output.
• The mannequin is the mind of the agent.
• exponential_backoff and delay_between_retries are to keep away from too many requests to LLMs (error 429).

# Create particular person specialised brokers
author = Agent(
    title="Author",
    position=dedent("""
                You're an skilled digital marketer who makes a speciality of Instagram posts.
                You understand how to jot down an interesting, Web optimization-friendly submit.
                You understand all about wine, cheese, and gourmand meals present in grocery shops.
                You're additionally a wine sommelier who is aware of find out how to make suggestions.
                
                """),
    description=dedent("""
                Write clear, participating content material utilizing a impartial to enjoyable and conversational tone.
                Write an Instagram caption in regards to the requested {matter}.
                Write a brief name to motion on the finish of the message.
                Add 5 hashtags to the caption.
                In the event you encounter a personality encoding error, take away the character earlier than sending your response to the Coordinator.
                        
                        """),
    instruments=[DuckDuckGoTools()],
    add_name_to_instructions=True,
    expected_output=dedent("Caption for Instagram in regards to the {matter}."),
    mannequin=Gemini(id="gemini-2.0-flash-lite", api_key=os.environ.get("GEMINI_API_KEY")),
    exponential_backoff=True,
    delay_between_retries=2
)

Now, allow us to create the Illustrator agent. The arguments are the identical.

# Illustrator Agent
illustrator = Agent(
    title="Illustrator",
    position="You're an illustrator who makes a speciality of footage of wines, cheeses, and positive meals present in grocery shops.",
    description=dedent("""
                Based mostly on the caption created by Marketer, create a immediate to generate an interesting photograph in regards to the requested {matter}.
                In the event you encounter a personality encoding error, take away the character earlier than sending your response to the Coordinator.
                
                """),
    expected_output= "Immediate to generate an image.",
    add_name_to_instructions=True,
    mannequin=Gemini(id="gemini-2.0-flash", api_key=os.environ.get("GEMINI_API_KEY")),
    exponential_backoff=True,
    delay_between_retries=2
)

Creating the Workforce

To make these two specialised brokers work collectively, we have to use the category Agent. We give it a reputation and use the argument to find out the kind of interplay that the workforce can have. Agno makes obtainable the modes coordinate, route or collaborate.

Additionally, don’t overlook to make use of share_member_interactions=True to ensure that the responses will move easily among the many brokers. You too can use enable_agentic_context, that permits workforce context to be shared with workforce members.

The argument monitoring is good if you wish to use Agno’s built-in monitor dashboard, obtainable at https://app.agno.com/

# Create a workforce with these brokers
writing_team = Workforce(
    title="Instagram Workforce",
    mode="coordinate",
    members=[writer, illustrator],
    directions=dedent("""
                        You're a workforce of content material writers working collectively to create participating Instagram posts.
                        First, you ask the 'Author' to create a caption for the requested {matter}.
                        Subsequent, you ask the 'Illustrator' to create a immediate to generate an interesting illustration for the requested {matter}.
                        Don't use emojis within the caption.
                        In the event you encounter a personality encoding error, take away the character earlier than saving the file.
                        Use the next template to generate the output:
                        - Put up
                        - Immediate to generate an illustration
                        
                        """),
    mannequin=Gemini(id="gemini-2.0-flash", api_key=os.environ.get("GEMINI_API_KEY")),
    instruments=[FileTools(base_dir=Path("./output"))],
    expected_output="A textual content named 'submit.txt' with the content material of the Instagram submit and the immediate to generate an image.",
    share_member_interactions=True,
    markdown=True,
    monitoring=True
)

Let’s run it.

# Immediate
immediate = "Write a submit about: Glowing Water and sugestion of meals to accompany."

# Run the workforce with a activity
writing_team.print_response(immediate)

That is the response.

That is how the textual content file appears to be like like.

- Put up
Elevate your refreshment recreation with the effervescence of glowing water! 
Overlook the sugary sodas, and embrace the crisp, clear style of bubbles. 
Glowing water is the final word palate cleanser and a flexible companion for 
your culinary adventures.

Pair your favourite glowing water with gourmand delights out of your native
grocery retailer.
Attempt these pleasant duos:

*   **For the Traditional:** Glowing water with a squeeze of lime, served with 
creamy brie and crusty bread.
*   **For the Adventurous:** Glowing water with a splash of cranberry, 
alongside a pointy cheddar and artisan crackers.
*   **For the Wine Lover:** Glowing water with a touch of elderflower, 
paired with prosciutto and melon.

Glowing water is not only a drink; it is an expertise. 
It is the right method to get pleasure from these particular moments.

What are your favourite glowing water pairings?

#SparklingWater #FoodPairing #GourmetGrocery #CheeseAndWine #HealthyDrinks

- Immediate to generate a picture
A vibrant, eye-level shot inside a gourmand grocery retailer, showcasing a variety
of glowing water bottles with varied flavors. Prepare pairings round 
the bottles, together with a wedge of creamy brie with crusty bread, sharp cheddar 
with artisan crackers, and prosciutto with melon. The lighting must be shiny 
and welcoming, highlighting the textures and colours of the meals and drinks.

After we now have this textual content file, we will go to no matter LLM we like higher to create pictures, and simply copy and paste the Immediate to generate a picture.

And here’s a mockup of how the submit could be.

Fairly good, I’d say. What do you assume?

Earlier than You Go

On this submit, we took one other step in studying about Agentic AI. This matter is scorching, and there are various frameworks obtainable out there. I simply stopped attempting to be taught all of them and selected one to start out really constructing one thing.

Right here, we had been capable of semi-automate the creation of social media posts. Now, all we now have to do is select a subject, regulate the immediate, and run the Workforce. After that, it’s all about going to social media and creating the submit.

Definitely, there’s extra automation that may be executed on this move, however it’s out of scope right here.

Concerning constructing brokers, I like to recommend that you simply take the better frameworks to start out, and as you want extra customization, you possibly can transfer on to LangGraph, for instance, which permits you that.

Contact and On-line Presence

In the event you preferred this content material, discover extra of my work and social media in my web site:

https://gustavorsantos.me

GitHub Repository

https://github.com/gurezende/agno-ai-labs

References

[1. Agentic AI 101: Starting Your Journey Building AI Agents] https://towardsdatascience.com/agentic-ai-101-starting-your-journey-building-ai-agents/

[2. Agentic AI 102: Guardrails and Agent Evaluation] https://towardsdatascience.com/agentic-ai-102-guardrails-and-agent-evaluation/

[3. Agno] https://docs.agno.com/introduction

[4. Agno Team class] https://docs.agno.com/reference/groups/workforce