Microsoft's Mads Kristensen said subagents are "coming soon" to Copilot in Visual Studio, while VS Code already documents subagent support across context isolation, custom agents, parallel execution and search.

Ingress-NGINX had been handling our traffic routing since moving to Kubernetes, but when it was announced it would be retired, we were forced to consider a new traffic routing solution.

Adobe today announced a new Acrobat-powered productivity agent so you can chat with PDFs, discover document insights, and more.

The post Adobe Announces an AI Productivity Agent appeared first on Thurrott.com.

Join us for the Big Technology AI Summit on June, 18, 2026 at the Commonwealth Club in San Francisco. The lineup: OpenAI President Greg Brockman, Perplexity CEO Aravind Srinivas, Box CEO Aaron Levie, Wired senior correspondant Lauren Goode, and more on the way! Get your tickets here: summit.bigtechnology.com

Learn more about your ad choices. Visit megaphone.fm/adchoices

Download audio: https://pdst.fm/e/tracking.swap.fm/track/t7yC0rGPUqahTF4et8YD/pscrb.fm/rss/p/traffic.megaphone.fm/AMPP4793224480.mp3

Birol Yildiz, CEO and co-founder of iLert, joins host Kanchan Shringi to explore how iLert built an AI SRE — an autonomous agent for handling production incidents — and what the experience revealed about building AI agents in the real world. Birol explains why incident response is a fundamentally agentic problem, where the unpredictability of novel incidents makes rule-based runbooks insufficient and reasoning models essential. He describes how the AI SRE evolved from an early browser-based approach to its current architecture, built around two key ingredients: reasoning models and the Model Context Protocol.

The conversation examines the four layers of the AI SRE in depth: an orchestration layer that routes requests and abstracts model providers; a knowledge layer built on plain text memory and agentic search rather than vector databases; an evaluation framework based on recorded live investigations replayed against new model versions; and a human-in-the-loop constraint layer. The episode concludes with practical advice for teams building agents: own your context completely, avoid off-the-shelf frameworks that obscure what enters the model, and get out of the way of the reasoning model rather than over-prescribing its steps.

Download audio: https://traffic.libsyn.com/secure/seradio/719-birol-yildiz-agentic-ai-sre.mp3?dest-id=23379

When OpenAI trained GPT-3, they didn't roll their own orchestration layer. They used Ray, an open source Python framework born out of the same Berkeley research lab lineage that gave us Apache Spark. And here's the twist: Ray was originally built for reinforcement learning research, then quietly faded as RL hit a wall. Until ChatGPT showed up. Suddenly reinforcement learning was back, as the post-training step that turns a raw language model into something genuinely useful.

Edward Oakes and Richard Laiw, two founding engineers behind Ray and AnyScale, join me on Talk Python to tell that story. We'll trace Ray from its RISE Lab origins at UC Berkeley to powering some of the largest training runs in the world. We'll talk about what Ray actually is, a distributed execution engine for AI workloads, and how a few lines of Python become work running across hundreds of GPUs. We'll cover Ray Data for multimodal pipelines, the dashboard, the VS Code remote debugger, KubRay for Kubernetes, and where Ray fits alongside Dask, multiprocessing, and asyncio.

If you've ever stared at a single-machine Python script and thought, "there has to be a better way to scale this", this one's for you

Episode sponsors

Sentry Error Monitoring, Code talkpython26
AgentField AI
Talk Python Courses

Links from the show

Download audio: https://talkpython.fm/episodes/download/547/parallel-python-at-any-scale-with-ray.mp3