Fold years of journalling into a coach that talks back.
1. Build a Personal Coach From Your Own Journals
Rightly or wrongly, a lot of people use AI as their life coach/therapist.
Now look, I’m obviously not going to convince you that this is a bad idea… but if you have to do it, at least do it properly.
Don’t just go to ChatGPT or Gemini and start banging away your woes — you’ll end up with a bunch of generic advice because the AI knows next to nothing about you.
What you actually want to do is feed the AI your actual history.
Take your daily, weekly and monthly journal entries — plus whatever notes you keep on your purpose, values and motivation — and load them into an AI’s knowledge base. Now when you sit down for a review, you have a coach that challenges your assumptions and surfaces your blind spots based on your actual life history.
There are two ways to easily do this.
The simple route is a CustomGPT or Claude Project: export your journal, upload it as markdown files into knowledge, then interrogate your own patterns. I walk through the exact build in my Next Level Productivity course.
The more powerful route is to use a harness like Claude Code and to give it access to your journal files on disk. No export, no upload — it reads your whole history from the raw files and it’s always current.
If you have your journal in a markdown format like Obsidian, this is super easy — just select the folder.
If you live in Bear or Apple Notes, grab an MCP and hook it up.
The secret here isn’t in clever prompting, it’s in giving AI access to your own records and history, so that it has the right context to coach you.
2. AI Makes Us Productive Producers… Or Does It?
You are what you produce, not what you consume.
This is age-old advice, and today’s AI makes it that much harder to follow.
AI makes producing cheaper and easier, sure.
But it also makes consuming cheaper and easier too, and consuming is the seductive one: endless summaries, feeds, another round of “research” that’s really just reading with extra steps.
What many people have failed to realise is that production only counts if it’s meaningful.
AI has made starting something so easy that most people end up with a graveyard of half-finished projects.
This usually happens one of two ways:
- They start something and realise they never needed it in the first place.
- They start something and it starts to get outside of their comfort zone and experience levels, so they walk away.
A simple way to think about it is this: AI has largely solved coding syntax. But it hasn’t solved architecture, deployment and scalability.
A client recently had AI convince him to build a web app without a database because “just a JSON file holding thousands of rows of client data would be fine”.
Sure…
AI made it sound like his CTO was wrong, and he lacked the technical experience to tell that the AI was wrong.
And that’s how the graveyard fills up.
So don’t produce less, but make sure you’re producing things that matter and actually see them through.
Pick projects you’ll actually use, and be humble enough to know when you’re out of your depth — and when the AI is out of its.
3. Courses
I have a range of online courses that teach business people what they need to know about productivity and AI:
1. Next Level Productivity
A practical, straightforward course that teaches you how to achieve elite-level personal productivity in today’s constantly interrupted world.
2. The Complete Claude, Claude Code & AI for Work Productivity
A comprehensive course taking you from beginner AI concepts like prompt and context engineering, to cutting-edge AI productivity using terminal-based AI tools like Claude Code for non-coding office work. Usable with ChatGPT, Claude, Gemini and other current LLMs.
3. The AI Agents, Automations and Agentic Workflows Guide
This non-technical course shows business people and non-coders how they can build and use AI agents in ChatGPT and Zapier.
4. The AI Playbook
This is my longer premium course on how businesses can deploy AI tools and technology across their processes and teams.
5. ChatGPT for Managers
See how AI can solve complex management challenges in less than 30 seconds. Full prompt library and examples included.
That’s it for this week!
— Aaron