AI Engineer · Video summary
One Registry to Rule them All - Sonny Merla, Mauro Luchetti, & Mattia Redaelli, Quantyca
Amplifon built an enterprise-grade AI registry system comprising an AI gateway, MCP registry, A2A registry, and use case registry to manage chaos and enable scalable, governed AI development across teams and continents.
Watch on YouTube ↗Key takeaways
- 🎯Decentralized AI development across many teams leads to chaos, including duplicated efforts, inconsistent security, and deployment issues.00:03
- 💡An 'Amplify' program with a defined operating model (control tower, committee) and focus areas (governance, platform, factory) is crucial for setting rules and driving AI adoption at scale.01:19
- 🚀Establish a central AI governance program with clear guidelines, a control tower for strategic decisions, and a committee for operational rollout.01:19
- 📈A centralized AI gateway provides unified access, enforces security via authentication, enables budget control for model usage, and facilitates auditing and monitoring.05:43
- 🔧Implement a unified AI gateway to manage access, security, budgeting, and monitoring for all AI model interactions.05:43
- 🔍Three interconnected registries are essential: MCP registry for tools/integrations, Agent-to-Agent (A2A) registry for AI agents using Agent Card standards, and a Use Case registry to map agents and tools to specific business needs.07:43
Chapters
- 0:03🎯 Introduction: Challenges of Decentralized AI Teams
- 0:45🎯 Overview of Amplifon and the AI Transformation
- 1:17🎯 The Amplify Program and Its Operating Model
- 2:11🎯 Focus Areas of the Amplify Program
- 3:22🎯 Problems Faced When Scaling AI in the Organization
- 3:44🎯 Addressing Technical Challenges in AI Operations
- 5:30🎯 Technical Solution: The AI Gateway
- 7:39🎯 Registries for Governance: MCP, A2A, and Use Case Registry
- 8:57🎯 Deep Dive into MCP and A2A Registries
- 12:42🎯 The Use Case Registry and Its Role in Governance
- 13:45🎯 Platform Overview and Developer Workflow
- 18:02🎯 Development and Deployment Pipelines
- 21:42🎯 Business Benefits of the Registry Platform
- 22:32🎯 Closing Remarks and Contact Invitation
The digest
High-Level Overview
Amplifon, a global leader in hearing care operating across 26 countries, faced significant complexity in managing multiple AI development teams spread worldwide. Each team built AI agents with unique infrastructure, security, and deployment processes, creating operational chaos. To tackle the challenge of scaling AI adoption responsibly and consistently, Amplifon launched the Amplify program, introducing a centralized registry system designed to govern, secure, and streamline the deployment and maintenance of AI agents across the enterprise. This overview explains Amplifon's strategic and technical approach to creating a unified AI gateway and multi-registry platform that facilitates governance, operational stability, and scalable development for AI agents.
Keep reading in The Digest
The full 6-minute article, 10 more sections, and every new episode from AI Engineer and the creators you follow.
- Structured Deep Dive
- 1. Amplify Program: Governance and Operating Model (00:15–03:22)
- 2. Core Challenges in Rolling Out AI at Scale (03:22–05:24)
- 3. Technical Solution: AI Gateway and Registries (05:24–13:42)
- 4. Platform Walkthrough and User Interface (13:42–17:55)
- 5. Developer Tooling and Enterprise Development Cycle (17:55–21:42)
- 6. Business Impact and Ongoing Development (21:42–22:43)
- Key Frameworks, Models, or Mental Maps
- Practical Implications & Takeaways
- Action-Oriented Summary
More from AI Engineer
Training an LLM from Scratch, Locally — Angelos Perivolaropoulos, ElevenLabs
In this hands-on workshop, Angelos Perivolaropoulos from ElevenLabs guides participants through the process of training an LLM from scratch using basic libraries like Torch, emphasizing the importance of tokenization and model architecture in building effective language models.
Skill Issue: How We Used AI to Make Agents Actually Good at Supabase — Pedro Rodrigues, Supabase
In this workshop, AI Engineer Pedro Rodrigues discusses how to enhance agent performance at Supabase using skills—structured workflows that improve agent interaction and efficiency. He shares insights on creating, testing, and implementing these skills, highlighting their significance in the development of agent-friendly applications.
Ralph Loops: Build Dumb AI Loops That Ship — Chris Parsons, Cherrypick
In this workshop, AI Engineer Chris Parsons introduces Ralph Loops, a method for building simple AI workflows that enhance productivity by iteratively refining tasks, using real coding examples like a Pomodoro timer. Participants learn to implement these loops practically, emphasizing the importance of context and feedback in AI-assisted coding.
Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked
In this video, Peter Werry from Unblocked discusses the importance of a context engine for AI agents, emphasizing how it optimizes task execution by providing relevant context and reducing cognitive load for users. He debunks common myths surrounding context engines and illustrates their effectiveness in enhancing productivity and understanding within organizations.
Context Is the New Code — Patrick Debois, Tessl
In this talk, Patrick Debois presents the concept that context is the new code, emphasizing the importance of creating, testing, and distributing context in the software development lifecycle, particularly when using AI coding agents. He advocates for a systematic approach to context development that involves generating reusable prompts, evaluating their effectiveness, and leveraging feedback to improve overall coding practices.
Mastering AI Pricing: Flexible & Agile Monetization — Mayank Pant, Stripe
In this video, Mayank Pant from Stripe discusses the challenges and strategies of AI pricing, emphasizing the need for hybrid pricing models that adapt rapidly to changing features and customer needs, allowing companies to maintain competitive margins while fostering customer trust and engagement.