I’m starting to think product intuition isn’t about magically seeing the best answer first.
It’s having a larger internal search space:
more patterns,
more alternatives,
more questions,
and better ways to challenge your first idea.
That feels much more trainable.
I realized something uncomfortable about the way I design products.
Once I find the first viable solution, my brain quietly decides:
“Problem solved. Now I just need to build it.”
And that’s often exactly when I stop thinking.
For now, I’m reviewing important interactions through four dimensions:
User Goal
What is the user actually trying to accomplish?
Shortest Path
Can this take one fewer step?
Discoverability
Will users know what they can do, and does it behave as expected?
Alternatives
Is there a fundamentally different solution?
A li’l quality-of-life update:
Before, you had to be really precise with your cursor so menus wouldn’t disappear on you. Should feel much more polished now 🫡
The default starting point has changed.
We used to build dashboards first and hope they answered the right questions.
Now AI can start with the question, find the data, run the analysis, and generate the best human-readable output.
The endpoint is still the same: clarity for human decision-making.
Every time you think you need a dashboard to look at data, stop yourself.
Do this instead:
1. Ask your agent to make sure that you have all the data to analyze something actually stored in the database.
2. Ask your agent to write a skill to gather that data.
3. Ask your agent to do the analysis and create a temp and throw-away HTML dashboard to answer the question(s) that you have
In my experience, every dashboard that I've created gets less and less use over time and decays.
It's much better to make sure your agent can get the data you need and answer the questions you have, on-demand.