Hi everyone, just wanted to share this project of mine, I shared it a long time ago in here whilst it was just a landing page, now the full product is available in Beta and everything is free for the duration of the beta.<p>ChartMyLife.ai simplifies diary keeping and life tracking. Leveraging OpenAI's GPT-4, our app turns your spoken words into organized diary entries, tracks key metrics like diet and exercise, and offers personalized quests and insights from AI coaches. It's a straightforward tool for self-improvement and staying on top of your goals.<p>Now for the nerds of HN, some more technical stuff<p>- ChartMyLife uses GPT-4 and whisper to let you talk about your day and store it in a structured way. This means both a text based diary (today I did so and so) and tracker entries (Lunch: 560 calories etc.)<p>- A second set of AI prompts review the diary weekly and can give you "quests" with an experience point system. The AI judges how much each quest is worth based on a barem it was given<p>- Dalle-3 is used to generate Quest icons<p>- This is made using NextJS with app router, server actions and cron jobs. Entirely serverless, and running with mongodb for the DB. The biggest challenge with this architecture is dealing with dates, as server side rendered component might run on UTC whereas component ran on the user's device are in a local time zone.<p>- I'm using JoyUI (from the makers of MaterialUI) which has been mostly a nice experience.<p>- One cool tidbit is I have AI tests to test my prompts. They look like this:<p>- All the illustrations are generated by dalle-3 or Midjourney V5.<p>```
it('knows how to extract a meal and a workout', async () => {
const result = await aiPrompt("I ate 6 nigiri sushis and I ran 5km", simpleUser, "23/11/2023, 12:08:58");<p><pre><code> const validation = await aiValidate(
result,
'It should create one entry in the meal tracker for 6 sushis, and an entry in the gym sessions tracker for 5km. It should not create any other entries.'
)
});</code></pre>
```
An AI is used to validate the result so it's the ultimate integration test that is easy to write. Each test is run 10 times as some prompts have a tendency to work some times and not some other times. I'm looking at 90% success for now to consider a prompt successfull, though most of them are 100%. It's ran on CI only when changes happen in the file related to prompting openAI.