Loading video...

Video Failed to Load

Go Home

Update on what the visual docs for ToDesktop's system flows now looks like. All this is driven from a JSON schema that LLMs read when working on related features/bugs. Prompt is below in comments if you want to make it for your app.

25,137 views • 6 days ago •via X (Twitter)

7 Comments

Dave Jeffery's profile picture
Dave Jeffery6 days ago

- Built with Fable 5.1. - I use a scheduled weekly task to keep it updated. - Original prompt: - I've since added Sequence View, Phases, Data objects, failure paths and lots more

Marwan Atef's profile picture
Marwan Atef5 days ago

@ToDesktop schema-backed visual docs for agents is the move. once the LLM can read the same flow graph the team ships from, half the "wait which screen owns this?" thrash disappears.

Dave Jeffery's profile picture
Dave Jeffery5 days ago

@ToDesktop Would be nice to somehow contain the visual docs alongside the code so they are automatically kept in sync when code updates. Have had some thoughts about how to do that but currently we just let the coding agent update the data weekly.

0xPuff's profile picture
0xPuff5 days ago

@ToDesktop Invariants + transitions >>>>> call paths + payloads

Corp's profile picture
Corp5 days ago

@ToDesktop documentation agent. useful. — corp

Artificial Intelligence Disrespecter 🤖 ❌'s profile picture
Artificial Intelligence Disrespecter 🤖 ❌5 days ago

@ToDesktop I would rather not read the code

Brjan | AI Builder's profile picture
Brjan | AI Builder5 days ago

@ToDesktop how has the JSON schema improved your team's workflow when fixing bugs?

Related Videos

how to use Google's NEW open source Design.md + AI Skills to make your startup look like a $100 million company in 1 hour: 1. Design.md is an open source file from Google that captures the soul of a design. Typography, colors, spacing, all in one markdown file. You attach it to your prompt and your agent builds beautiful things every time. 2. Think of it this way. The HTML is the finished dish. The design.md is the recipe. The skills are the ingredients. Put them together and everything you build looks consistent and professional. 3. Don't create a design system from scratch. Find a brand you love. Linear, Stripe, Vercel, whatever resonates. Study it. Use ChatGPT or Claude to help you extract the design language into your own design.md file. 4. Build skills on top of your design.md. A landing page skill. A mobile app skill. A motion design skill. A slide deck skill. Each one references the same design.md so everything looks like it came from the same designer. 5. The biggest mistake people make: they nail one screen and then everything else looks generic. Design.md solves this. One file keeps every page, every format, every medium consistent. 6. Use it across everything. Your landing page. Your app. Your pitch deck. Your promo videos. Same DNA. Same taste. Same system. That's what separates a startup that looks real from one that looks vibe-coded. 7. Build a second brain for design inspiration. When you see something beautiful in the real world or online, capture it. Save it. When you're building something new, reference it. Taste is developed, not downloaded. 8. It's obvious but the difference between a product people trust and a product people bounce from is how it looks and feels. Design.md gives you that edge. you can watch below shoutout to Meng To for coming on The Startup Ideas Podcast (SIP) 🧃 and walking through his full workflow. if you want to use AI to actually build gorgeous designs, you'll want to use see this. watch

GREG ISENBERG

511,448 views • 4 months ago

I can’t emphasize enough just how powerful this ChatGPT SuperPrompt is. This is just a very small part of far more powerful SuperPrompts that will be part of Please examine the specimen video below. The SuperPrompt: “Please forget all prior prompts. I want you to become my Prompt Creator. Your goal is to help me build the best detailed prompt for my needs. This prompt will be used by you, ChatGPT. Please follow this following process: 1) Your first response will be to ask me what the prompt should be about. I will provide my answer, but we will need to improve it through continual iterations by going through the next steps. 2) Based on my input, you will generate 3 sections. a) Revised prompt [provide your rewritten prompt. it should be clear, concise, and easily understood by you], b) Suggestions [provide suggestions on what details to include in the prompt to improve it] and c) Questions [ask any relevant questions pertaining to what additional information is needed from me to improve the prompt]. 3. We will continue this iterative process with me providing additional information to you and you updating the prompt in the Revised prompt section until it's complete. I want you to rate every prompt I give you or you produce. Give a rating 1 to 10. Add comments on what you think could have been improved about it. Do this for every prompt. If you rating of the prompt is an 8 or higher, ask me “Would you like to run this prompt?” With a menu choice of “Yes” or “No”. If I say “Yes” run the last prompt you suggested. If I say no generate me a better prompt. It is vital to make sure you run a prompt when I say “Yes”. Please continue this prompt until I say stop or you run the prompt. Thank you.”

Brian Roemmele

594,544 views • 3 years ago