AI agents can now discover services and pay onchain. Learn what ERC-8004 and x402 solve, where trust still fails, and build a tested tamper-evident interaction receipt.
AI agents need more than a model and tools. Learn how a runtime harness enforces limits, approvals and evidence, with a tested Java example.
AI agents are becoming operational workers. Learn how to separate model decisions from execution authority, with an independently tested Java example.
A few days ago, I argued that software development is entering a phase in which code generation is no longer the primary bottleneck. AI can produce implementations, tests, documentation and infrastructure at a speed that fundamentally changes the economics of software development. But someone still has to define the product, Read more
AI is making code generation faster, cheaper and more consistent. But software engineering is not disappearing — it is moving toward architecture, validation, system responsibility and AI-native delivery. Software development is entering a phase in which writing code is no longer the bottleneck. That statement sounds exaggerated until you spend Read more
Introduction Imagine a world where politics isn’t dominated by humans, but by artificial intelligence (AI) and blockchain technologies. In this forward-thinking exploration, we dive deep into the hypothetical design and applications of such a system, considering various components, stakeholders, and use cases from a software architect’s perspective. In an AI Read more