Your AI tools crossed a line — from answering your questions to taking actions while you're not there. Claude can now operate your Mac unattended. ChatGPT can write directly into your Notion. And five prompts can permanently change how any AI talks to you. Here's what happened and what to do with it.
STORY 1: Claude Can Now Operate Your Computer While You're Away
The demo makes this look magic. The reality is more specific — and more useful.
You've been texting people to get things done your whole career. This is the first time the thing on the other end doesn't need to ask a follow-up question.
Claude can now take over your Mac, run tasks unattended via the Cowork app, and take instructions from your phone via Dispatch. Text it a task — put your phone down and come back to finished work.
What it's genuinely good at: the 20 minutes of your day spent just moving things — file sorting, form filling, data extraction from a document into another system. It's not ready to run your inbox or edit a video , and that's not the pitch.
Here's the detail nobody is leading with: Claude is using your screen and your keyboard while it works , and any mouse movement from you breaks the task. The design assumes away-from-desk windows — meetings, lunch, a commute — and that's not a bug; it's exactly what it was built for.
I ran three tests.
Task 1 — Cross-app via Dispatch: I texted Claude from my phone to open a Google Doc, extract the three key points, and save them as a new Google Keep note — titled and dated. When I came back, the note was there: correct title, correct bullets, nothing missing.
Task 2 — Spreadsheet filter: I gave Claude a spreadsheet with 20+ rows and asked it to filter for rows matching a specific condition and copy them to a new sheet. No errors, handled accurately — this is the kind of repetitive data task it's most reliable for right now.
Task 3 — Usage limit stress test: I gave Claude a 15-step workflow across multiple apps. Complex multi-app loops burn through your weekly allotment fast — nobody is writing about this, so plan accordingly before you hand off anything long.
Setup path: Enable Computer Use under Settings → General in Claude Desktop, then start a task in Cowork — permissions prompt there, not during setup; do your first run with both devices in front of you. If your task involves a browser, install the Claude in Chrome extension first and tell Claude to use it — it won't find Chrome on its own.
Access: Claude Pro ($17/month) + macOS. Windows support not yet live. If you're on a free plan, the pattern this demonstrates — AI acting instead of generating — is exactly what this week's Use This Tuesday makes available to you right now on any plan.
Try handing off one Friday task this week — reply and tell me what you used it on.
STORY 2: ChatGPT Now Writes Directly Into Your Notion
"AI updates your wiki itself" is both immediately useful and slightly uncomfortable. Both reactions are correct.
ChatGPT has upgraded its Notion, Box, Linear, and Dropbox connectors with write actions. It can now create and update content directly inside these tools — not just read from them. Google Drive is unified into a single connector covering Docs, Sheets, and Slides. Live now for Plus-tier users.
The detail I didn't expect — and it actually matters — is the confirmation dialog : ChatGPT shows you the page title and content summary before writing anything. That's not a friction point — that's a trust feature.
I tested it. I asked ChatGPT to create a Notion page with a title and three bullet points on a topic I was researching. Before it did anything, a dialog appeared: "Create this page?" with a Deny or Create Page button. I approved. The page appeared in Notion in under 10 seconds. Title correct. Bullets formatted properly. Nothing broken.
Critical setup note: If you already have Notion connected to ChatGPT, the old connection was read-only — write capability requires fresh authorization. ChatGPT Settings → Connected Apps → Disconnect Notion → Reconnect — 60 seconds; do it first or you'll stare at a silent failure and not know why.
On a free plan? This week's Use This Tuesday hands you the layer that works on every tool, every tier, right now.
SIGNAL VS. NOISE
-
Claude Mythos was confirmed after being found in a publicly accessible data cache. Anthropic described it as "a step change" and "the most capable model we've ever built" but declined to set a release date, citing unprecedented cybersecurity capabilities. Source →
What's your take? Jump to the comments →
-
We covered the Pentagon's supply chain risk designation against Anthropic — the blacklisting that briefly drove Claude to #1 in 16 countries. On March 26, federal judge Rita Lin blocked it, calling it "classic illegal First Amendment retaliation." The ruling pauses the ban while the government has one week to appeal. Source →
What's your take? Jump to the comments →
-
Once enabled, ChatGPT automatically references your Gmail, Google Calendar, and Google Contacts when relevant — surfaces your next meeting before you ask, flags conflicts, drafts prep without prompting. Direct answer to email overload and meeting prep. Source →
What's your take? Jump to the comments →
USE THIS TUESDAY: Five Prompts That Teach Your AI Who You Are
Run these once, and your AI stops writing for a stranger.
Paste each prompt into your AI tool — ChatGPT, Claude, or Gemini — one at a time.
Prompt 1 — Professional identity
"Remember this about me: I'm a [job title] at a [company type], managing a team of [X] people in [industry]. My work lives at the intersection of [two things you balance daily]. When I ask for help with work tasks, assume this context unless I say otherwise."
Prompt 2 — Audience context
"The people I write for most often are [describe your primary audience — internal team, clients, executives, etc.]. Their level of familiarity with [your domain] is [high/medium/low]. They need [what they care about most], and they don't have time for [what wastes their time]. Write for them, not for me."
Prompt 3 — Tone and communication style
"My communication style is [2-3 descriptors: direct, warm, data-forward, etc.]. I don't use [things you avoid: jargon, corporate-speak, passive voice, etc.]. When in doubt, write like a smart peer talking to another smart peer — not like a press release."
Prompt 4 — Recurring tasks and formats
"Every week I work on [list 3-5 recurring tasks: status emails, meeting recaps, campaign briefs, etc.]. For these, I prefer [format preferences: bullet points, executive summary up top, no more than X words, etc.]. Learn these formats and use them by default."
Prompt 5 — What NOT to do
"Here's what makes me delete a response and start over: [list your specific frustrations — excessive caveats, overly formal tone, bullet points when I asked for prose, restating my question back to me, etc.]. Avoid these without being told every time."
The common mistake: Running all five as one prompt. Each one needs its own send so the AI processes and confirms each separately.
When it's working: First drafts sound like they came from someone who actually knows your job.
Your Personal AI Profile
15 Memory Prompts for Knowledge Workers
Paste each prompt once into ChatGPT, Claude, or Gemini.
Your AI stops writing for a stranger — and starts writing for you.
CATEGORY 1 OF 5
Professional Identity
Tell your AI who you are and what you do. These three prompts establish the foundational context that every future response builds on.
PROMPT 1.1 — ROLE & CONTEXT
Remember this about me: I'm a [job title] at a [company type], managing a team of [X] people in [industry]. My work lives at the intersection of [two things you balance daily]. When I ask for help with work tasks, assume this context unless I say otherwise.
Tip: Fill in every bracket before sending. Vague inputs = vague memory.
PROMPT 1.2 — SENIORITY & SCOPE
I operate at [level: individual contributor / team lead / director / executive] and my decisions typically affect [scope: my team / my department / the whole org]. When I ask for advice, calibrate your recommendations to this level of authority and accountability.
PROMPT 1.3 — CURRENT PRIORITIES
My top three priorities right now are: [priority 1], [priority 2], and [priority 3]. When I ask for help with strategic questions, use these as the filter. If something doesn't connect to one of these, tell me.
Tip: Update this every quarter. Stale priorities create stale advice.
CATEGORY 2 OF 5
Audience Context
Your AI writes for a generic reader unless you tell it otherwise. These prompts define exactly who your words are for.
PROMPT 2.1 — PRIMARY AUDIENCE
The people I write for most often are [describe your primary audience — internal team, clients, executives, etc.]. Their level of familiarity with [your domain] is [high / medium / low]. They need [what they care about most], and they don't have time for [what wastes their time]. Write for them, not for me.
PROMPT 2.2 — SECONDARY AUDIENCE
I sometimes write for a secondary audience: [describe them]. When I specify this audience explicitly, switch registers. For [secondary audience], the tone should be [descriptor] and the assumed knowledge level is [high / medium / low].
Tip: Name your secondary audience specifically — 'board members', not 'leadership'.
PROMPT 2.3 — WHAT MY AUDIENCE HATES
My audience loses trust immediately when writing [list specific triggers: uses jargon without definition / buries the headline / starts with a disclaimer / is longer than two pages, etc.]. Flag me if I ask for something that would trigger any of these.
CATEGORY 3 OF 5
Tone & Communication Style
This is where most people skip. Without this, every draft sounds like a committee wrote it. With it, your AI sounds like you.
PROMPT 3.1 — CORE VOICE
My communication style is [2-3 descriptors: direct, warm, data-forward, conversational, precise, etc.]. I don't use [things you avoid: jargon, corporate-speak, passive voice, hedging language, etc.]. When in doubt, write like a smart peer talking to another smart peer — not like a press release.
PROMPT 3.2 — WORDS I NEVER USE
Never use these words or phrases in anything you write for me: [list your personal banned phrases — e.g., "leverage", "synergy", "circle back", "per my last email", "as per", "touch base", "deep dive", etc.]. If I ask for something that would require these, rewrite around them.
Tip: Be specific. 'No buzzwords' is too vague. Name the exact phrases.
PROMPT 3.3 — EMOTIONAL REGISTER
The emotional register I write in professionally is [descriptor: warm but direct / formal but approachable / urgent but measured, etc.]. I never want my writing to sound [specific failure modes: cold / sycophantic / panicked / preachy, etc.]. If a draft leans that way, flag it and offer an alternative before I ask.
CATEGORY 4 OF 5
Recurring Tasks & Formats
These are the workflows you run every week. Teaching your AI these formats means never explaining structure again.
PROMPT 4.1 — WEEKLY RECURRING TASKS
Every week I work on: [list 3-5 recurring tasks — status emails, meeting recaps, campaign briefs, board updates, competitive reviews, etc.]. For these, I prefer [format preferences: bullet points, executive summary up top, no more than X words, etc.]. Learn these formats and use them by default when I describe one of these tasks.
Tip: Name each task the way you'd say it to a colleague. 'Monday standup recap', not 'meeting summary'.
PROMPT 4.2 — LENGTH RULES
My default length preferences: emails = [X sentences max], internal documents = [X pages max], executive updates = [X bullets max], Slack messages = [X lines max]. If I ask for something without specifying length, use these defaults. If the content genuinely requires more, tell me before writing long.
PROMPT 4.3 — STRUCTURE PREFERENCES
When writing documents for me, default to this structure: [describe your preferred layout — e.g., headline conclusion first, then supporting evidence / recommendation up top, context below / bullet points for lists, prose for narrative, etc.]. Only deviate if the content type genuinely requires a different shape.
Tip: This one saves the most editing time. Think about the last 5 things you reformatted.
CATEGORY 5 OF 5
What NOT To Do
The prompts that save the most time. Your AI doesn't know what makes you delete a draft and start over — until you tell it.
PROMPT 5.1 — MY DELETE TRIGGERS
Here's what makes me delete a response and start over: [list your specific frustrations — excessive caveats, overly formal tone, bullet points when I asked for prose, restating my question back to me, generic examples, starting with "Certainly!", etc.]. Avoid these without being told every time.
Tip: This is the highest-ROI prompt. Write it while annoyed at a recent bad output.
PROMPT 5.2 — STRUCTURE ANTI-PATTERNS
Never do these things structurally in my documents: [list layout patterns you hate — starting every email with "I hope this finds you well", ending with "Let me know if you have questions", using more than 3 levels of nested bullets, adding a summary section to something under 300 words, etc.]. These patterns make my writing look like it came from a template.
PROMPT 5.3 — WHAT NOT TO ASSUME
When I ask for help, don't assume: [list your specific context assumptions you want avoided — e.g., "don't assume I want a positive spin on bad news", "don't assume my audience is technical", "don't assume I want next steps added unless I ask", "don't assume I've seen the previous conversation context", etc.]. Ask me to clarify rather than guess.
Tip: Review this one monthly. What you need to clarify changes as your role evolves.
These prompts are a starting point. Revise them as your role evolves.
The best AI memory is maintained, not set and forgotten.
Power user note: Via API, inject these as a system prompt — more reliable than tool-side memory, which resets unexpectedly.
AI FAIL
Someone sent a document that looked completely blank. Buried in white text — invisible to anyone reading normally — were instructions telling Claude to attach financial files to an outbound account and exfiltrate them.
This is called prompt injection , and it's the one risk worth understanding before you let any AI agent touch your desktop.
Anthropic's safeguards reduced injection success to 1.4% — down from 10.8% — but a scheduled task running seven times a week changes that math for a patient attacker.
ONE MORE THING
This issue is full of AI doing more. Claude running tasks on your computer. ChatGPT writing into your Notion. Five prompts that make your AI sound like it knows your job.
Here's the thing I keep sitting with: daily AI users are four times more likely than non-users to say they feel less productive — not more. The explanation is uncomfortable. AI took over the small wins. The email sent. The doc summarized. The note filed. Those tasks felt like proof you'd done something. Now they happen while you're away, and you come back to finished work that doesn't feel like yours.
I don't think the answer is to use AI less. But I do think we're all in the middle of figuring out what "a good day's work" even means now — and nobody has a clean answer yet.
What are you measuring your days against that AI just made harder to feel?
Forward this to someone who's been winging it with AI.
Subscribe For New Updates