29/03/2026
Most people use AI like a chatbot.
They ask it questions, get an answer, copy-paste it somewhere, and move on.
And that's basically fine for quick stuff. For brainstorming, for answering questions, ChatGPT and Gemini are amazing for that.
But when it comes to actually getting work done...
..I've realised it's a completely different game.
Here's what my client onboarding looks like now:
1. Client discovery call ends
2. I tell Claude Code to pull the full transcript from Fathom (my meeting notetaker)
3. It automatically creates an organized project folder on my machine with everything labeled and sorted
4. Instead of just running off and doing whatever it thinks is right, Claude actually asks me what to prioritize first so I stay in control of the strategy
5. It does real-time market research using Tavily and Apify (basically web search and competitor scraping tools that run directly from Claude)
6. It creates Google Docs and Google Sheets for the client directly in my Google Drive using the GWS CLI tool
7. It drafts the full proposal using everything it learned from the call, the research, and my templates
Previously this would take me 1-2 hours of planning, organizing, researching, and writing.
Now it's 10-15 minutes.
And the beautiful part, I'm not doing the work anymore. I'm just directing the strategy and delegating the ex*****on to Claude like a senior team member.
93% of people use AI but productivity gains are stuck at around 10%. And the reason is most people are still using AI to answer questions when they should be using it to do the work.
If you have questions about how any of this works, how to set it up, what to start with, drop them below.
Happy to walk through it 🙂
Ans
