This is interesting. I'm curious how you calibrate it. I've found that sometimes AI is very confident about being able to do something (or not do something), and I've had to pick its response apart a bit to see what the real answer is. Are you getting accurate results with one pass?

This is helpful. Right now I'm managing all of this myself, which requires a lot of thoughts and organization. This would simplify things. Does it give you the ability to create your own sections so it is customizable to the person/project?

I think you can be non technical, but that does not mean just blindly trusting AI. And it will probably take you WAY longer to get it correct. You still have to know (or figure out through iteration) what questions to ask, what edge cases might exists, etc. But I also think building things with AI, if you really lean into it, can be a great way for people without a technical background to learn.

This is great! I find myself using Gemini to double check Claude, idea being that they are different models so can be force multipliers/sanity checks for one another

thank you so much for the feedback! if you find any issues with the plugin, please let me know.

This is cool! I like projects that simplify things for non-technical users, while also educating them

I think building something really well with AI takes a lot of work. You can certainly ask it to do things and it will comply, and produce something pretty good. But you don't know what you don't know, especially when it speaks to you authoritatively. So checking its work from many different angles and making sure it's precise can be a challenge. Will be interesting to see how all of this iterates over time.

I agree 100%. At the same time, I feel like this piece, and our comments on it are snapshots in time because of the rate of advancement in the industry. These coding models are already significantly better than they were even nine months ago.

I can't help but read complaints about the capabilities of AI – and I'm certainly not accusing you of complaining about AI, just a general thought – and think "Yet" to myself every time.

Exactly! I completely agree. I think figuring out how to use this new tool well develop into a bit of an art form, which we will race to keep up with.

> But you don't know what you don't know, especially when it speaks to you authoritatively. So checking its work from many different angles and making sure it's precise can be a challenge.

I've spent far more time pitting one AI context against another (reviewing each other's work) than I have using AI to build stuff these days.

The benefit is that since it mostly happens asynchronously, I'm free to do other stuff.

If I don’t know what I don’t know, how am I going to build something any better than a coding agent? An approach on a couple of projects has been to prototype with the agent, learn, write a design and then start over. I then know the areas to look into more detail.

That's really the catch, and I think we're just figuring out how to approach this. I think your iteration approach is correct. I do a lot of asking AI to tell me about blind spots, to double check it's work in specific ways. I've asked it to let me know what it might have hallucinated, where it cut corners, and a bunch of other things along these lines. It will be interesting to see how things evolve in this area, and if AI gets good to the point that we have to do this less.

Yep. It's quite good at getting you to 80% of the solution. The other 20% depends on the problem!

I really appreciate this. A lot of people don't know what they don't know. They look for suggested prompts, but should be looking for principles

I like this a lot An interesting next iteration would be to add a functionality that evaluates a user's work for inefficiencies and suggests where they can improve cut cost. Might be outside the scope of your project, but it could be interesting.

already on that probably in an hour it will be published. will let you know once it does.

Awesome!

I think this is a really cool concept. Sharing thoughts on a few things that could strengthen it. After I read the report (which was really cool) and went into the "the record" section, I couldn't figure out how to get back to the report. I wanted to run this for other members of my family to share with them, but couldn't figure out how to get back to the birthday selection input field. Also, at the end of the AI generated summary, it thought it was 2024 and then later in the paragraph 2023. It was also a little tricky to navigate back and forth between windows and figure out what each one was for. Good luck with this, it has a lot of potential!

Thanks — all 3 were real bugs and they're fixed. Just shipped:

  1. "Your story" button in the header so you can always come back to the report
  2. "New report" button to enter a different birthday (for family members)
  3. The year thing — prompt wasn't giving Claude the current date, it was hallucinating 2023/2024. Now it knows it's 2026.

  The family-sharing use case is the one I completely missed. Really appreciate you calling it out.

Ad astra per aspera