Karpathy’s Agentic Engineering finally has proper DevTools! When an agent stops working, the model is only one possible cause. The problem could be a failed tool, a lost connection, an interface update that never appeared, or something earlier in the conversation. @CopilotKit has rebuilt its open-source Inspector around this problem. It sits inside the application and watches the full interaction between the user, the interface, and the agent. When something fails, the Inspector button turns red, names the failure, and opens the spot where it happened. But even a much harder problem is reproducing that failure. This is because agents do not always follow the same path twice. Running the same prompt again may trigger another tool, produce another response, or start with a different application state. Inspector handles this through saved Threads and an isolated Agent Playground. A developer can open the conversation where the problem occurred, choose "Try from here," and copy everything up to that point into the Playground. The original conversation remains unchanged while another response or tool path is tested. Threads can open inside the live application, while assistant messages can jump back to their matching context in Inspector. Everything runs underneath AG-UI, the protocol that carries messages, tool activity, state changes, and other events between the agent and the interface. Those interactions can also feed CopilotKit Intelligence so that when the same issue or useful behavior appears repeatedly, it can become an evidence-backed Insight and a proposed SKILL(.)md file. Developers can review, edit, and approve the improvement before the agent inherits it. The tool also helps developers find a problem, recreate its surrounding context, test another path, and turn repeated lessons into agent improvements. It is open source and included with CopilotKit development builds. Intelligence setup starts with one prompt. Here are the docs: I am testing this extensively and will cover this in more detail soon with a hands-on demo.

If you’ve ever opened Chrome DevTools, or optimized a page for Core Web Vitals, you’ve used software built by @addyosmani. Timestamps: 00:00 Intro 02:50 Addy’s current workflow 05:11 Addy’s path into tech 15:04 Addy’s work on jQuery 16:44 TodoMVC 21:44 Getting hired at Google and working on Chrome 27:17 Building dev tools 40:15 Core Web Vitals 45:42 Google’s engineering culture 51:03 Addy’s career trajectory at Google 57:55 The director role at Google 1:01:40 Cognitive debt and cognitive surrender 1:03:03 Working with agents 1:05:52 Loop engineering 1:12:55 The changing role of the software engineer 1:18:15 How Addy uses AI in writing 1:27:40 What’s next for Addy 1:28:47 Career advice Brought to you by: • @AntithesisHQ – verify your system’s correctness without human review or traditional integration tests – and avoid bugs or outages. Teams like Jane Street, and the etcd community use Antithesis to ship better code, faster. • @sentry – application monitoring software considered “not bad” by millions of developers. • Google Cloud Run – run untrusted agent code without the security anxiety. Cloud Run sandboxes deliver hyper-isolated, ephemeral execution environments that spin up in milliseconds. Check them out: Here's Addy's advice on where he believes engineers should invest efforts, in the coming years, in his words: “What we are very likely to see happen next with engineering careers (as well as product and other roles) is the unbundling of them, so that an engineer also has product sense, while a product person also has engineering sense, or UX sense. You should think about the non-engineering things if you don’t [usually] have the time to think about product or technical evangelism, or go-to-market approaches, or any other parts of how businesses are successful. If you can show employers that you are not just a builder, but someone that can help them as roles start to become a little bit fuzzier, then I think that you can be successful in these times. Don’t be just an engineer.”

we've audited AI search visibility for 10 devtools in the last month every company that ranks #1# in their category does the same 4 things: > they have a page for every "how do i [problem]" query in their space. not feature pages. pages that answer the question first and mention the product second. > they have comparison pages for every competitor. vercel has 13 "[vercel] vs [competitor]" pages. when someone asks chatgpt "vercel vs netlify" theres a page ready to be cited. > they answer cost queries. "cheapest [category] for startups". most companies ignore this. elevenlabs loses every single cost query to amazon polly and deepgram because they have no page addressing price. > they write pages matching the exact phrasing ppl type into AI. not "our analytics platform" but "how to measure user onboarding drop off." amplitude has hundreds of these. posthog has zero. companies doing all 4: vercel (48% citation share), elevenlabs (33%), zapier (25%) companies missing 2+: losing to competitors 1/10th their size dm me if u run a devtool and want to know where u stand we'll run the audit free

The one MCP you should always have installed if you work on frontend chrome-devtools-mcp lets Claude Code control a real Chrome browser Reproduce bugs, inspect network requests, debug console errors, analyze performance, and automate browser interactions You can ask Claude to open localhost:3000, reproduce a bug, and find what’s broken Install it in Claude Code: /plugin marketplace add ChromeDevTools/chrome-devtools-mcp /plugin install chrome-devtools-mcp@chrome-devtools-plugins The latest update lets you analyze heap snapshots without a live Chrome connection, making it easier to investigate memory leaks offline Github:

we been talking to geo/aeo people at some of the top devtools and the same thing keeps happening everyone is figuring this out alone there isnt any one size fits all playbook. its kinda a black box. the most common question i get from every single one of them: "what are the other companies doing?" thinking about starting a small private group for ppl actually doing this work. but wanna gauge interest first. most of these ppl already wanna join if thats u or someone u know, lmk :)

Stop hunting for ghosts in the heap → Learn how to use DevTools for agents to enable your coding agent to find and fix memory leaks like detached DOM nodes in your web app.