Back to Catalog

Multilingual AI Agents for Poetry using GPT-5 & AutoGen/AG2

BeginnerGuided Project

Learn how to use AutoGen’s multi-agent framework with GPT-5 to collaboratively generate and refine poetry. The agents are multilingual—generate poems in any language you choose. You provide the theme (plus optional form and tone); a Muse proposes and selects the concept, a Verse Crafter writes the poem, and a Poetry Editor lightly polishes and signals POEM_COMPLETE. A simple, guided flow that shows how GPT-5 + AutoGen turn your idea into a finished poem—without the heavy technical setup. Learn AutoGen's multi-agent architecture by taking this hands-on project now!

Language

  • English

Topic

  • Artificial Intelligence

Skills You Will Learn

  • Artificial Intelligence, Autogen, Generative AI, AI Agent, Python, Multimodal AI

Offered By

  • IBMSkillsNetwork

Estimated Effort

  • 35 minutes

Platform

  • SkillsNetwork

Last Update

  • November 12, 2025
About this Guided Project
Creating beautiful poetry no longer needs to be daunting. This AI Poetry Studio is a multilingual, multi-agent system that transforms your poem’s theme and preferences into a fully crafted, polished piece—in any language you choose.
The journey begins with a single input from you: the theme of your poem, plus optional details like language, poetic form, and tone. From there, a team of specialized AI agents takes over, each with a distinct role in the creative process:
  • Author Agent captures your theme and preferences in one clear brief to kick off the session.
  • Muse Agent proposes three distinct poetic directions—titles, moods, and concepts—and selects the strongest one to pursue.
  • Verse Agent develops the selected idea into a complete poem with crisp line breaks and imagery tailored to your style.
  • Editor Agent lightly polishes for rhythm and clarity while preserving meaning, then signals completion with POEM_COMPLETE.
Working together via the AutoGen framework and powered by the GPT-5 nano model, these AI agents collaboratively create poetry that is well-structured and elegant, delivered in your chosen language. By the end of the session, you receive a beautifully finished poem that showcases the seamless orchestration of multiple intelligent agents blending creativity with precision.

This system empowers you to co-create original poetry with AI, experiencing the harmony between your input and advanced multi-agent workflows.

Who Should Enroll

  • Developers, data scientists, and AI enthusiasts interested in building creative applications with multi-agent systems
  • Writers, educators, and poetry lovers curious about how AI can assist in narrative generation and content design
  • Learners eager to explore practical applications of AutoGen (AG2) & OpenAI’s GPT-5 in collaborative creative workflows.

A Look at the Project Ahead

After completing this guided project, you will be able to do:
  • Understand AutoGen’s multi-agent architecture – Learn how to design and coordinate specialized agents to simulate a real-world poetry creation workflow.
  • Build intelligent writing agents – Create agents with defined roles such as Muse Generator, Verse Crafter, and Poetry Editor to handle different stages of poetic composition.
  • Orchestrate collaborative book creation – Combine individual agent contributions to generate cohesive poems with consistent rhythm, tone, and literary quality.
  • Learn to build and run agent workflows with AutoGen – Use Python and AutoGen to define agents, manage communication, and streamline task execution.
  • Deliver personalized poetic experiences – Produce customized poems based on user inputs like theme, mood, or phrase.

What You'll Need

Technical Requirements: A basic understanding of Python programming. Experience with AI or LLMs is helpful but not required.
Browser Setup: A modern web browser to access CrewAI tools, follow the guided environment, and run your code.

Instructors

Jigisha Barbhaya

Data Scientist

I am a Data scientist at IBM and Lead instructor at Skills network. I love to learn and educate. I have completed my MSc(Computer Application) specialisation in Data science from Symbiosis University.

Read more

Contributors

Wojciech "Victor" Fulmyk

Data Scientist at IBM

Wojciech "Victor" Fulmyk is a Data Scientist and AI Engineer on IBM’s Skills Network team, where he focuses on helping learners build expertise in data science, artificial intelligence, and machine learning. He is also a Kaggle competition expert, currently ranked in the top 3% globally among competition participants. An economist by training, he applies his knowledge of statistics and econometrics to bring a distinctive perspective to AI and ML—one that considers both technical depth and broader socioeconomic implications.

Read more