Tag: agents
-
Last week was a big week for agents. I wrote about the agentweb on Tuesday. To compete with Anthropic’s managed agents service (which I’ve used a fair amount at this point and it is quite good) OpenAI released Workspace agents to a few customer segments, Google released enterprise agent platform, and Microsoft scrambled to release
-
First slowly, then all at once… the agentweb
Every app, website, SaaS product, cloud service, hosting platform, protocol, database, file system, and CLI is being rewritten for agents. What is an agent? An agent is an app that receives prompts, interacts with large language models, loops until it can satisfactorily resolve the prompt, and replies. Some agents know how to code, others know
-
Nikunj Kothari on “Token Anxiety”
Nikunj Kothari on the anxiety created by agentic workflows: The anxiety is rational, which is why it sticks. Every week some new benchmark drops that makes last month’s workflow feel prehistoric. Codex ships overnight processing. Opus gets faster. Context windows double. None of it reduces the pressure. It multiplies it. You can do more now.
-
Maggie Appleton on the state of AI Agents
Maggie Appleton, in a post titled simply January 2026: You might suggest that I spend less time on X, but I’m not inclined to look away just as the train gets up to full speed. Sure it’s a distorted reality, but it points to real ground truth: even if progress on language models slows this