Josh Quintal

I’ve noticed use of the word “quietly” is quietly increasing. Probably another AI writing quirk.

@toddsaunders Build in vertical slices. Helps keep changes easy to review and you’ll have something functional to use at each slice. You get tests and vibes in one. I also made a skill for this: github.com/DiscRisknBisqu…

I want to level up my skills in codex. What are you using that I should try?

@Aabbhhz Found some exmaples. Sometimes there’s also an opening show with a band, games, etc. There was a Nintendo one where they hosted a few little tournaments. Another cool one I didn’t photograph: an airline put up a cabin for you to sit in to demo their amenities.

@Aabbhhz China is ahead on this and I’m not sure why. I’ve noticed malls throughout the country still have lavish in-person events for everything from cars to tv shows to kitchenware. Feels like they’ve recaptured something we lost in the 90s/00s.

moving forward, irl activations and experiences are going to be a key moat for brands. the thesis is simple: as AI rapidly takes over, people will naturally incline to engage with 'made by human' things. staying in the spotlight now means building worlds that allow consumers to step inside, engage, and perhaps alter it. the craving for deeper engagement, belonging, and authenticity cannot alone be solved with just content.

@trybasis So good I just applied for the Intelligence Architect role

What do all these things have in common? 🍕🎂🥧 … been a while since I shipped #devtools

@krzyzanowskim I wrote my own skill for this reason. Most spec skills produce an overwhelming amount of material. What I want is to own the roadmap and feed it to the agent to get reviewable vertical slices in return. github.com/DiscRisknBisqu…

"skill issue" - a whole day of writing PRD/specification - half day grilling the PRD/specification - 16h /goal implementing PRD it doesn't work. IT DOESN'T WORK. it doesn't work at all, but also it doesn't work as specified. why broken? "So implementation drift" I'm done with this shit!

@NondualStew @nosilverv Yeah I’m trying to be funny but I get what OP is saying: there’s a difference between analysis paralysis leading to inaction and purposeful analysis to prepare for your next action.

@DiscRisknBisque @nosilverv The primary problem

Is this something? Did I just solve the “Meaning Crisis”?

@Marsadist ARTEMIS

Introducing Artemis. The worlds first AI agent that runs your entire GTM motion from a single prompt. If you're running outreach, Artemis can make you $100k+ in 60 days. Comment “ARTEMIS” and I’ll send you access for free.

@mehuljindal18 A plain-language companion app to help patients transitioning from surgery or those with chronic care needs. For providers, our app helps the bill this lost revenue ($10-30k/clinic/year) and flag any care gaps that may arise for the patient at home. obtego.io

Y Combinator's deadline is in 10 days, if you are applying and want to have a look at my application that got us selected into YC, comment what you are building below and I will send you that application! Bonus: For top ideas, will refer & help with the application/interview!

Does anyone notice they tend to prompt "context-first"? Oftentimes I think I'm going to describe a task to an LLM, only to find I've instead described the situation, so I wrap it in a <context> tag and write the now succinct <goal> above it.

@Jason I’m in

We started an AI founder twitter group... reply with "I'm in" if you're a founder and want to be added

This demonstrates why we have a UI in @ObtegoHealth and not just a chat box. A chat box means you also need context in your head; you need your know what to ask. For a complex medical patient, a chat box (with no other UI) isn’t the best option.

@im_roy_lee Yeah, I forget where I read this, but the good point was that dashboards tend to give consumers more work rather than insights. Thanks

@DiscRisknBisque unsure, i suspect a sufficiently conversational llm with enough personal data, snark, and tool calling could do it for me what i don’t need is a health score and dashboard

here's my two cents on this as a random gen z kid first impression: i only wanna see this sort of font when i open duolingo or candy crush, not 24/7 when im on my phone. feels too silly. when you're taking a swing so big as to change the entire default ux of an iphone, you need mass consumer adoption to win and can't get away with just being a prosumer tool so, here's my thoughts on every single proposed feature as it relates to me: - reading list: i read maybe 2 books a year, which is 2 more than 99% of my friends. - personalized weather: i rarely open the weather app bc i don't care that much and would never even opt for a "weather app widget" much less a daily notification about it on my home screen - drafts email replies: before starting company, i literally had ~zero use for my email, much less drafting emails of my own. i consistently wonder how useful this will be to non-prosumers as a primary data source - prepares you for meetings & trips: think this is personally more nifty than necessary, but this potentially seems like a more useful feature. ie if im going to the beach and never bought sunscreen, would it try and remind me of that? feels too good to be true based on current llms, but that could be cool - suspicious charges: i feel this problem is completely solved for me with just an email from my bank. my cards never get stolen - reminders: i never use the reminder app because i am too lazy to type in a reminder and arrogantly assume that i can just remember to do the thing - tracks your health: i'm most interested to see this. a problem i have with all "AI" health apps is that i don't wanna see a dashboard + score + chatbot; i want something that actually gets me out of the door and taking steps or going to the gym, which is definitely doable with llm - one tap intel on wherever you are: my particular use case i got excited about is that i would personally love some sort of agent that proactively suggests events i or a girlfriend might find interesting. tickets just dropped for a rave of an artist someone im talking to likes? i would like to know + buy i am very interested to try it, this is exciting and more net new than 99% of consumer ai tech i've seen

Patients who don’t understand their care plan can’t meaningfully participate in their own recovery. We started Obtego because we know the complexity of the medical system can harm patients when at their most vulnerable. Our companion app makes care easy to understand and manage, while our backend systems help providers ensure nothing gets lost. If you share our vision for the future of patient communication, show your support by voting for us in the HealthTech Impact Awards. Winning this round will let us pitch their select investors so we can continue realizing a more connected and engaging future for healthcare! Vote here: awards.healthboardadvisors.com/awards-public-… After selecting Obtego in the Digital Health category, if you aren't aware of the companies in the other categories, they can be left blank.

We had a great time at #HEALTHTECHWEEK last week in San Francisco! Big thank you to @Echtman and all the volunteers for putting on a great event. If you want to check out the video of the EHR, Digital Health and Value Based Care panel with Alana Arnold, MD, MBA; Anthony Gerardi and myself; here it is: youtube.com/live/2UMMUwp2w…

@garrytan Regarding that last sentence, what’s the benefit of the new hiring knowing you’ll step back in if they fail? I could see peace of mind for the hire and for some roles a greater ability to take risks as a result.

Hire out of pain. Don't hire because you think you'll need someone soon or maybe sometime later. Wait until you or your team are actually hurting: working weekends, missing family dinners, dropping balls. That pain is the signal that the role is real. I learned this the hard way after watching founders (including myself) hire ahead of need and end up with people in roles that weren't fully formed yet. When you hire out of pain, you know exactly what the job is because you've been doing it yourself. You can evaluate performance because you know what good looks like. And the new hire knows you'll step back in if they fail, because you were just doing it last week.

Next week I'll be at SF HealthTech week! Catch me on Wednesday the 14th's panel at 12:15 PM: EHR, Digital Health, & Value Based Care. Looking forward to seeing the latest uses of AI in healthcare.