In my work with G7–G12 students at Force Academy, a research initiative in Chongqing, I sometimes take a project that appears to be finished and give another student responsibility for using, checking, or modifying it. The handoff is a test of understanding: Can the work still make sense when its creator is no longer there […]
This summer, I built a small experiment called ContextCue. The idea came from something I kept seeing during my internship. The engineers around me were using AI everywhere in the software development process. GitHub Copilot and Claude models helped with specs, code, reviews, and tests. The team also maintained reusable skills that taught coding agents […]
In my previous article, I argued that agentic development needs enough specification to make correctness checkable. A quick prompt can get implementation started quickly, but someone still has to decide whether the result does what we wanted. I left a fairly practical question unanswered, though. Once the agent has written the code, how should we […]
The following article originally appeared on Addy Osmani’s Elevate blog and is being republished here with the author’s permission. For much of human history, we’ve evaluated code quality via code review: Someone reads what you wrote and makes sure it’s clean, thoughtful, fast, understandable, and tests well. For agents, that approach doesn’t scale well; there’s […]
I use AI for writing all the time. But not because it’s good at writing. In fact, just the opposite is true. AI is so reliably bad at writing that I’ve actually taken advantage of that, and made its bad writing an integral part of my writing process. I’ve written a lot of books and […]
In my previous Radar article, “Architectural Guardrails for AI-Generated Code,” I argued that AI coding agents need a layer that can hold architectural decisions in a structured corpus, retrieve the relevant ones, put them into the agent’s context before it writes code, and enforce explicit constraints with reproducible checks. Testing that model exposed two distinctions […]
The following article originally appeared on the Agentic AI Foundation blog and is being reposted here with the author’s permission. Websites are designed for people. We can look at a page and quickly understand where to enter information or which control will complete an action. AI agents don’t see or use the web the same […]
On a recent episode of This Week in AI, we discussed that the number of nonhumans on the internet is greater than humans, 144 to 1. It’s an estimate, and the order of magnitude is more important than the number itself. What matters is what a ratio anywhere in that range does to a security […]
Artificial intelligence systems are difficult to reproduce because their behavior depends on nondeterministic models and on data, configurations, policies, and external services that continue to change. But exact reproducibility is not always what operators, investigators, or auditors need. They often need something different: historical reconstructability. The central claim is that reconstructability is a system property […]
This is the final post in a four-part series about post-training. If you missed them, check out part 1, part 2, and part 3. Time to get your hands dirty! I’ll take you through implementing the key pieces of the classic ChatGPT pipeline: SFT, then reward model training, then PPO. The goal isn’t to reproduce […]
The following article was originally published on the Agentic AI Foundation blog site and is being republished here with the author’s permission. A customer asks your company’s AI agent to update the shipping address on account 123. The agent relies on a support ticket with a typo and updates account 132 instead. The customer relationship […]
The following article was originally published on the Agentic AI Foundation blog site and is being republished here with the author’s permission. A customer asks your company’s AI agent to update the shipping address on account 123. The agent relies on a support ticket with a typo and updates account 132 instead. The customer relationship […]
The following article originally appeared on Duncan Davidson’s blog and is being republished here with the author’s permission. Decision records give coding agents durable project context—as long as they don’t turn every decision into a courtroom transcript. Architectural Decision Records (ADRs) help human teams establish rules and carry context forward in software projects. They capture […]
The following article originally appeared on Robert Englander’s blog site and is being reposted here with the author’s permission. The software industry has become deeply focused on autonomous AI systems. Agents that can replace workers. Agents that can write software. Agents that can operate applications on our behalf. Entire startups are now built around the […]
The following article originally appeared on Vanishing Gradients and is being republished here with the authors’ permission When an AI agent can explore a dataset, choose a modeling approach, run the analysis, and explain its findings, what should the data scientist do? Traditionally, data scientists chose each step and implemented much of the analysis themselves. […]