We use analytics and advertising tools by default. You can update this anytime.
Manage optional tracking categories. Necessary cookies stay on so the site can function.
Staff Writer & AI Editorial Lead
Katie Parrott is a staff writer. She writes Working Overtime and contributes to Vibe Checks, Source Code, and Context Window.
Demos, workflows, and hard-won lessons from building agents that run 24/7
Plus: The Vatican weighs in on AI labor, and our Codex playbook
Power users revolt at OpenAI’s tool combination. Plus: The battle for knowledge-work OS, managing agents with Fable, and a 53 percent error-rate drop
A mini-Vibe Check on Gas City, a Grok classifier that grades your X drafts, and why HTML is the new markdown
Start with three simple tools, and let the AI figure out the rest
The asynchronous, agentic workflow developers love is finally accessible to everyone—but the polish isn't there yet
I had a quarter of OKRs and no clue whether I was hitting them. Enter Codex.
A new lab says the sameness of AI prose is a training problem. It made the writing less predictable—but not necessarily any better.
Plus Claude joins Slack, and design gets its own AI tells.
Plus: What to do when your coding model disappears, GitHub's COO on 14 billion agent commits, and engineers questioning their future
Sonnet 4.6 delivers Opus-close performance at half the price—but speed didn't come along for the ride
OpenAI nailed the interface. But it's built for hardcore engineering.
The app worked. Nobody, including me, had checked whether it was safe.
Plus: the number KateBench taught us to count, and a six-agent solar crew helping decide whether to run the dryer
Cursor team members share their thoughts on building software with AI and why model selection beats prompting tricks
Plus: Perplexity’s rules for agent skills, the office politics of dictation, and creating a weekend AI piano coach
Off-the-shelf AI couldn’t meet Headway’s security and workflow needs, so it built its own. Now the whole company uses it.
Plus: 13 beliefs about writing with AI, and an antivirus for the AI age
Anthropic's latest Opus is more precise, more literal, and the best coding model we've tested on well-specified tasks—but it won't fill in the gaps for you anymore
Plus: Dan’s attempt to clone Kate, a shortcut for turning demonstrations into skills, and the human goals machines still need us to set
.png&w=3840&q=75)
Katie Parrott
Laura Entis
Dan Shipper