- AI Business Insights
- Posts
- Claude can read your apps now
Claude can read your apps now
Three connectors beat twelve open tabs
In partnership with
For the longest time I lived inside twelve open tabs. Email here, meeting notes there, Slack buried somewhere behind them all. I'd copy from one, paste into another, then re-explain the whole mess to Claude before it understood a single word. If that sounds like your Tuesday, you're not alone.
Then I came across a sharp little walkthrough from a LinkedIn creator who shares practical AI workflows, and it quietly flipped how I use Claude day to day. The whole point: connect your actual apps to Claude so it reads them live, no copy-pasting required. I was impressed by how simple it looked, so I broke the entire thing down here.
The GTM bets that shouldn't have worked, and did
One grew revenue 50x after half his team quit over the strategy. One brought in 50K signups in a single day with no paid budget. One generated 100M+ views from a stunt that took 50 hours to conceive. One asked every prospect to demo the product themselves instead of demoing it for them.
None of them followed the safe playbook. They treated GTM like an experiment, moved before they had proof, and made bets most founders would never get approved.
HubSpot for Startups documented all 6 stories in the free Bold Bets Playbook. The risks they took, why it was risky, and what it returned.
*Ad
The idea is to stop making Claude work blind
The big shift is this. Claude does not have to guess at your context. Instead of feeding it scraps, you let it connect straight into the tools you already live in. Gmail, Slack, Notion, Granola. Once they're linked, Claude reads them in real time. The way the creator framed it stuck with me:
Claude now reads your apps. Live. 0 copy-pastes.
That single line is the whole pitch, and once I tried it I understood why.
The five-step setup takes about a minute
Here's the exact process, start to finish. It runs about 60 seconds, and every step has a clear reason behind it.
Open Claude. This is your home base for everything that follows.
Click the "+" inside the chatbox, not Settings. This is the part most people miss. The connector menu lives in the chatbox, not buried in your account settings.
Find "Connectors" and click "Add connector." This is the gateway that lets Claude talk to outside apps.
Search for your app. Gmail, Granola, Slack, Notion, whatever you actually want Claude to read from.
Authorize it, and you're done. Claude now has a live line into that app.
That's the whole mechanic. Quick to set up, but the real value comes from how you use it next.
Why you should not turn on all 200
This is where it gets smart. There are around 200 connectors available, and the instinct is to flip them all on. Resist that. The better move is to pick three that compound, meaning three tools that feed each other context.
Here's the stack I'd start with:
Your notetaker (Granola) so Claude can read your meetings and remember what was actually said.
Your email (Gmail) so Claude can draft replies with full awareness of the thread.
Your team chat (Slack) so Claude can pull the relevant threads instead of you hunting for them.
The secret is the context, not the prompting. With all three on in the same chat, Claude pulls your meetings, inbox, and team channels at once. No tabs. No searching. No re-explaining yourself.
I keep sitting with that point. We burn so much energy chasing the perfect prompt, when the real unlock is just handing the AI the right information to begin with.
PRDs by voice. Bug reports by voice. Ship faster.
Dictate acceptance criteria and reproductions inside Cursor or Warp. Wispr Flow auto-tags file names, preserves syntax, and gives you paste-ready text in seconds. 4x faster than typing.
*Ad
The one warning worth remembering
There's a catch, and I'm glad the creator flagged it. Do not leave your connectors on by default. They quietly burn tokens before you even type a word, because Claude is pulling context in the background. So switch them on when you need them for a focused task, then switch them off when you're done.
What this actually changes about your workflow
Let me connect this to something bigger. Most people treat AI like a vending machine. You type a request, you get an answer, and the machine forgets you the moment you walk away. Connectors change that relationship. Suddenly Claude works more like a teammate who already sat in your meeting, already skimmed your inbox, and already read the Slack thread before you asked.
A few ways I'd put this to work:
Meeting follow-ups. After a call, ask Claude to turn your Granola notes into a clean recap and draft the follow-up email in Gmail, all in one pass.
Inbox triage. Let Claude scan recent threads and draft replies that already match the tone of the conversation.
Team sync. Have Claude pull the key Slack threads from the week and tell you what actually needs your attention.
Each of those normally means jumping between three or four apps. With a compound connector stack, it collapses into a single chat.
What I'd actually try tonight
What I respect most about this approach is the restraint. Anyone can tell you to connect everything. It takes real insight to say connect three things that talk to each other, then turn them off when you're done. That's the line between a flashy demo and a workflow you'll actually keep.
If you've been drowning in open tabs like I was, this is worth ten minutes tonight. Open Claude, hit that "+" in the chatbox, and link your first connector. Then add two more that feed it context, run one real task, and watch how much you stop re-explaining yourself.
Hiring in 8 countries shouldn't require 8 different processes
This guide from Deel breaks down how to build one global hiring system. You’ll learn about assessment frameworks that scale, how to do headcount planning across regions, and even intake processes that work everywhere. As HR pros know, hiring in one country is hard enough. So let this free global hiring guide give you the tools you need to avoid global hiring headaches.
*Ad