Designing Agent Conversations: From FIPA to Today’s Protocols
Last Updated on October 15, 2025 by Editorial Team
Author(s): Souradip Pal
Originally published on Towards AI.
How decades-old dreams of digital dialogue shaped the way modern AI agents talk today.
Did you know that back in the late ’90s, researchers were already dreaming about digital agents talking to each other as fluently as humans do? Yet here we are in 2025, and most agents still struggle to have conversations that go beyond shouting data back and forth.
The article explores the evolution of agent communication protocols, reflecting on the historical foundation laid by FIPA (Foundation for Intelligent Physical Agents) and its ambitions to create a common language for machines. Despite its elegant designs and theoretical insights, FIPA faced practical challenges, leading to the adoption of simpler, more flexible communication standards like REST APIs in modern systems. These new protocols emphasize developer experience, security, and real-time communication, aiming to facilitate meaningful interactions among AI agents while learning from FIPA’s lessons on semantic clarity and intent in communication.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
