AI Workflows
Stories, explainers, and practical ideas tagged AI Workflows.
Stories
OpenAI’s Dots can keep working when you are not. Start with the approval map
OpenAI Dots can keep working across apps after you leave the chat. Before giving an always-on agent a recurring job, map exactly what it may read,…
Claude Sonnet 5.5 is here. Here is what to use it for at work
Claude Sonnet 5.5 brings stronger everyday capability to Anthropic's mid-tier model. Here are practical jobs to try first and when to move up.
Before you give an AI agent access to your work, run this 3-permission check
AI agents are getting access to more of our work. Use this simple Read → Act → Approve check before connecting one to your files, inbox,…
Microsoft just rebuilt Copilot around three kinds of work. Here is what to use each one for
Microsoft's new Copilot separates AI work into Home, Code and Autopilot. Here is a practical way to decide when to ask, build or delegate — plus…
Adobe is putting Photoshop and Acrobat inside AI chat. Here are 6 workflows worth trying
Adobe is bringing creative and document tools into Gemini and Claude. Here are six practical workflows to try, plus where human review should stay.
AI help desks are changing but a better support request still starts with five details
A practical five-part support request template for faster troubleshooting, whether an AI assistant or a human help desk responds.
Claude can now build documents and slides. The bigger change is what happens between the prompt and the finished file
Anthropic is pushing Claude beyond answering questions and toward producing finished work. Here is what that changes for everyday knowledge work — and where human review…
ChatGPT can now connect work and personal accounts. Here is how to use that without creating a mess
ChatGPT can now connect multiple work and personal accounts through supported plugins. The useful part is not merging everything, but reducing the time spent jumping between…
AI is most useful at work when it does not try to do your job
A lot of AI advice still starts with automation, as though the goal is to hand over as much work as possible. The more useful shift…
AI that earns its place in your inbox.
The tools worth trying, a prompt you can steal, and the news that affects your work. No hype, no jargon.