I'm Jos Deldime. Sometimes called a New Media Thinker, sometimes a developer or scripter and on occasion described as “doing something on the internet”.
Coding agents shouldn't have to rediscover your codebase for every task.
JetBrains Context gives them code context to improve outcomes and cut costs on production-scale codebases.
Available now in early access as part of the JetBrains AI for Teams and Organizations rollout.
Learn more: https://t.co/82G2oSbZat
Chrome DevTools for agents is now stable! 🏇 Don't miss out, and give your agent access to your website's runtime (console logs, network requests, ...), rather than just the static code. Deep dive from last week's #GoogleIO: https://t.co/a86wIAez0Q
4️⃣ Advanced annotation mode lets you directly adjust the way web pages look while leaving feedback, making it even easier to work together with Codex.
I’m designing an online course in software engineering with agents. In days past I would have used a popular language like Java or C# or JavaScript for that course. For this course I chose Go, not because it is popular but because it is fast. My students will see little of it; and they will not be forced to watch agents struggle with VM startup delays or browsers.
🇪🇺 EU Vice-President Henna Virkkunen warns VPNs will be addressed under upcoming online age and identity verification rules.
“VPN… must not allow the system to be circumvented,” she said, responding to concerns users could bypass the new EU age and ID system.
Follow: @europa
Auto-review is a new mode that lets Codex work longer with fewer approvals and safer execution.
It helps Codex keep moving through tests, builds, and more, including during long tasks and automations, while a separate agent checks higher-risk steps in context before they run.
Introducing GPT-5.5
A new class of intelligence for real work and powering agents, built to understand complex goals, use tools, check its work, and carry more tasks through to completion. It marks a new way of getting computer work done.
Now available in ChatGPT and Codex.
A new Plan mode in Air saves your execution plan to a Markdown file before you proceed to implementation.
Iterate on it, leave comments right in the file, then choose which agent executes it and where – locally, in a Git worktree, or Docker container.
Agentic AI speeds up code production, but the challenge is execution and control.
JetBrains Central is an open system for agentiс development across the SDLC, with governance, observability, and controlled execution.
Early access starts in Q2 2026.
Learn more: https://t.co/k0gDXhXuf6