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.
Five tests across blind comparisons, editorial standards, and deadlines—here's what changed our setup
But it’s not perfect—it failed our editing test
It feels less like learning something new than a browser that has caught up to how we already want to work with AI
Five patterns from our Opus 4.5 Claude Code Camp you can apply today
Lessons from the team that built Codex and launched a number-one app with it
Setup, workflows, and principles for turning Codex into an operating system for email, writing, research, planning, and reporting—even if you’re not an engineer
Plus: Vercel and Lovable’s security woes, and how to make your agent your watchdog
OpenAI's latest model update excels at instruction-following and extended tasks, but don't expect it to surprise you
Turning a list of my writing foibles into a skill that stops me from getting away with them
Plus: Delegation versus collaboration, Dan’s inbox-zero Codex workflow, and the agentic version of Musk’s five rules of automation
The skills I transferred to my writing agent from playing Settlers of Catan
What it was like in the room, plus what the new Managed Agents features look like in production
How Every uses custom agents for prioritization, meeting notes, OKR planning, and growth tracking—plus sample prompts to build your own
Kieran Klaassen turned a prompt into a working app in an hour and shows you how
Everything we learned at Droid Camp about switching between GPT and Claude while staying in flow
My AI project manager reads my OKRs, calendar, Notion, and Slack so I can stay on top of my work
These four questions helped me decide which ones to keep, redesign, revisit, or retire
Demos, workflows, and hard-won lessons from building agents that run 24/7
Plus: Agent-designed automations, why final review belongs in the destination app, and how to use our compound knowledge plugin
A million words of failed drafts taught me that improving my AI setup sometimes means giving it fewer rules to follow
.png&w=3840&q=75)
.png&w=3840&q=75)
.png&w=3840&q=75)
Katie Parrott
Dan Shipper