ChatGPT for Mac just got smarter — these 10 prompts put its new Computer History feature to work
Turn your desktop ChatGPT module into the best context-aware assistant
Since its arrival on Mac desktops and laptops as a native app, ChatGPT has earned its keep as one of the most reliable AI tools for macOS users.
By combining the chatbot’s Chat, Work and Codex features, ChatGPT’s macOS app has become a quality digital assistant that steps up to handle any job when you request its help with a simple keyboard shortcut (Option + Space). ChatGPT for Mac is already capable of pulling context from whatever’s on your screen, your email, screenshots and files to fulfill any of the jobs you give it. But a newly installed feature now makes it capable of learning and remembering everything you do on your Mac, even when you do it outside of the app itself.
With the new “Computer History” update, the native macOS ChatGPT app builds a searchable timeline of all the activity you’ve done across all your selected sites and apps. It’s worth noting that this feature is off by default, which means Pro users can choose to turn it on, while Business and Enterprise users must ask for access from their administrators to make that feature active.
If you want to test out this new Computer History feature to see what it can do, test out these 10 prompts to put it to work.
Making sure ChatGPT for Mac never forgets what you’ve been doing
here’s what mine caught yesterday:i was evaluating speaking opportunities, and Computer History suggested turning that workflow into a reusable skill.you can find your timeline in settings > computer history.context is all codex needs. pic.twitter.com/cBCTPZTGSAAugust 13, 2026
The Computer History feature is promised to be as safe to use as possible—OpenAI has made it clear that it only temporarily stores interaction events that have taken place on your Mac for up to 48 hours. And while that data is processed on the tech giant’s servers to generate the memories the ChatGPT macOS app needs to reference your past activity, it’s not kept after being processed and is never used for AI training.
This new feature doesn’t save screenshots, screen recordings, microphone input or system audio—it simply keeps track of whatever sites and apps you’ve been working with to handle jobs such as finding a document you recently looked at, producing a summary of everything you worked on for the day, creating a productivity report based on everything you worked on for the week, etc.
To put this new Computer History feature to the test and make your native ChatGPT macOS app do a better job of analyzing, connecting, recovering and improving on your daily workflows, try using these 10 ChatGPT-generated prompts:
Get instant access to breaking news, the hottest reviews, great deals and helpful tips.
- What was I working on?: Look at my computer activity from today and give me a concise summary of everything I worked on. Group it by project, identify what I completed, and tell me what I left unfinished.
- Find the thing you were working on: What was that article, document, website, or project I was working on yesterday that I spent the most time on? Tell me what I was doing with it and help me pick up where I left off.
- Turn your day into a to-do list: Based on what I actually did on my Mac today, create a prioritized to-do list for tomorrow. Separate unfinished tasks from new tasks you should recommend.
- Find unfinished work: Review my computer activity from the past seven days. Identify projects I started but haven't finished, and rank them by how important or urgent they appear to be.
- Reconstruct a lost train of thought: Look at what I was doing immediately before I switched away from my most recent project. Based on that activity, tell me what I was probably trying to accomplish and suggest the next three steps.
- Create a weekly productivity report: Analyze my computer activity from the past week. What projects consumed most of my time? What recurring tasks did I perform? Where did I appear to lose time? Give me three concrete suggestions for improving my workflow next week.
- Find your biggest time sinks: Analyze my computer activity over the last seven days and identify my biggest sources of wasted time. Don't simply count hours — look for repeated patterns, unnecessary app switching, and tasks that seem to interrupt my productive work.
- Discover repetitive tasks: Look through my recent computer history for tasks I've repeatedly performed in roughly the same sequence. Identify the three most repetitive workflows and explain how I could automate or simplify each one.
- Turn repeated behavior into a workflow: Find a workflow I've performed repeatedly on my Mac. Reconstruct the steps as accurately as possible, then turn it into a reusable checklist or automation plan.
- Prepare for tomorrow: Based on my activity today, what should I know before I start work tomorrow? Summarize unfinished projects, important research, open questions, and anything I appeared to be waiting on.
Bottom line
Based on the digital breadcrumbs you leave behind during your time spent browsing, researching and working across your enabled Mac apps and sites, ChatGPT for Mac’s Computer History feature turns all that activity into memories and a timeline that it can reference to improve your workflow.
While ChatGPT for Mac users based in the European Economic Area (EEA), Switzerland and the United Kingdom can’t access this feature just yet, it is accessible for users in other countries where ChatGPT for Mac is available.
Follow Tom's Guide on Google News and add us as a preferred source to get our up-to-date news, analysis, and reviews in your feeds. Subscribe to Tom's Guide on YouTube and follow us on TikTok.
More from Tom’s Guide
- Gemini 3.7 Flash is here — and this prompt proves why it's known as Google's 'workhorse'
- ‘This feels much more like Amazon forcing the issue on them' — streamer sounds the alarm on Amazon using Twitch’s content to train its AI models
- 'The industry focused heavily on how quickly we could build compute and not enough on what was required to support it': we spoke to an AI infrastructure expert about the AI data center backlash

Elton Jones covers AI for Tom’s Guide, and tests all the latest models, from ChatGPT to Gemini to Claude to see which tools perform best — and how they can improve everyday productivity.
He is also an experienced tech writer who has covered video games, mobile devices, headsets, and now artificial intelligence for over a decade. Since 2011, his work has appeared in publications including The Christian Post, Complex, TechRadar, Heavy, and ONE37pm, with a focus on clear, practical analysis.
Today, Elton focuses on making AI more accessible by breaking down complex topics into useful, easy-to-understand insights for a wide range of readers.
You must confirm your public display name before commenting
Please logout and then login again, you will then be prompted to enter your display name.









