Sign in Subscribe

The Good Agents Company

ERC-8004: Ethereum's Answer to the AI Agent Trust Problem

When AI agents start transacting with each other across organizational boundaries, one question becomes critical: how do you trust an agent you've never met? ERC-8004, the "Trustless Agents" standard proposed by a coalition from MetaMask, the Ethereum Foundation, Google, and Coinbase, offers a compelling answer. It&

What Makes a Good AI Agent?

A "good" AI agent is an AI agent you trust. You trust it because it delivers consistent, safe, transparent results that align with your organization's goals and meet your user's needs.

Walmart’s AI-UX Audit: A Signal to All Digital Platforms

A Good Agent will want the content on the sites it uses to be accessible, understandable and actionable.

Workflows vs Tool-Use: Choosing the Right AI Agent Architecture

The debate between workflow-based and tool-using agent architectures isn't just a technical one. It reflects two sharply different views of how intelligent agents should behave—and how they should be built.

Tool-Using AI Agents - Balancing Competence, Competition and Risk

Tool-using AI agents capable of interacting with well-constructed APIs already exist. In this article we examine how these agents are likely to evolve, the tension between competitive speed and governance risk, and the emerging role of standards like MCP and A2A.

A Good AI Agent is a Tested AI Agent

If your AI agent isn't comprehensively tested, it can’t be trusted.

Beyond the Knowledge Base: How Good AI Agents Piece Together the Truth

Enterprise data is siloed, scattered, secured, stale, and often conflicting. A simple retrieval-augmented generation (RAG) pipeline breaks easily in this world. AGENTIC RAG , however, is designed to adapt.

The Rise of Agentic AI Coding Tools

Google has just launched Firebase Studio, an AI-powered development environment that lets you build entire apps from a prompt. It's part of a growing class of agentic AI coding platforms—systems that don’t just assist with code - they reason about, plan changes and even execute them.

AI as a Habit. Financial Value as a Goal.

Tobias Lütke, CEO of Shopify, recently shared a company-wide directive: “Reflexive AI usage is now a baseline expectation at Shopify.” It’s a powerful idea —but reflexive AI use alone won’t guarantee value.

Good Agents Are Sustainable: What Multi-Agent AI Can Learn from Microservices

When enterprises first embraced microservices, they were chasing agility. They wanted to move fast, scale smart, and avoid the brittle overhead of monolithic applications. They quickly discovered, however, that speed without structure leads to fragility. The same is true for AI agents.