priyadarshy

I think we're all under-indexing on how important it is going to be to be able to play-test an agent's changes before shipping it as a hedge against slop. I don't think people will do it unless it feels effortless, like clicking a preview link from a GitHub PR. If there's any friction, people will just click merge PR and move on with their life and your product-level slop will acccummulate.

I think high-taste products require you to actually use the thing that was built to feel the gaps in your spec.

I routinely find I am doing something dead simple that an agent will one-shot, e.g. add a new sort by option in the panel that lists a user's Linear tasks. If I looked at the PR diff I'd immediately think it was perfect and ship it. It's only when I actually get in there and play around with a dynamic UI that I realize, "you know this option really belongs at the top" or "hm, there's enough options here now that this dropdown feels cramped and we might need to consider another option". Simple examples obviously but the principle is that when I am landing the last 10% of a fix or a feature that when I need to interact and play-test. At the speed agents can generate fixes to new bugs or customer requests, I am bottle necked just doing that last 10% of steering and even the basic git mechanics to try something locally are enough to get me to not want to do it.

Right now, it seems like the state of the art is to review PR diffs and just merge them in or if you are more sophisticated have your agent generate screenshots or screen recordings. Screenshots and images are moving in the right direction but if you are building something interactive, you've really got to interact with it to know if it feels great.

My dream was to start my day with an agent having handled every bug and small enhancement request that came my way that day, worked on, and ready for my review, so I could spend an hour each day just steering them to the finish line.

I could do this linearly, picking off a branch an agent worked on, testing it and iterating but most of these small fixes each day aren't big brain stuff, I can effectively multi-task them but when I've tried doing it on my own machine it's either worktree hell, git gymnastics, or agents deadlocking - one agent wants to self test with Chrome MCP but can't cause another is editing code causing hot reloads.

I ended up building a Desktop app version of what OP posted to do this for myself and my team at Sunsama, it's called Macro: - Website: https://macro.land - Demo: https://www.loom.com/share/89c273e3a92d45cfb6860790d7b78bf6

I had a couple other specific needs that these repos don't cover: - I want complete control of what MCP tools my team uses and the ability to control their input/output etc e.g. I don't want someone using the Intercom MCP to accidentally reply to a customer with an agent. - I don't want my engineers spending time configuring all the boring stuff (preview urls, mcps, chrome mcp, etc) - I wanted the ability to steer agents to the finish line together. In Macro, any user can join the chat and steer the agent e.g. a colleague with UI taste jumps into tweak the last bits - I want to see common failure agentic failure cases across my team so I can improve our Claude.md and agentic practices so all work flowing through one interface allows that

The wildest thing I read was:

> Harvard will immediately report to federal authorities, including the Department of Homeland Security and State Department, any foreign student, including those on visas and with green cards, who commits a conduct violation.

Conduct violations at Universities are a pretty broad set of rules at universities and don't necessarily line up with what's legal or not but more with the university's cultural and social norms.

Her sleep is terrible since she's breastfeeding, so even when she does get some sleep, it'll be while dozing off in some unexpected and ergonomically diabolical position.

For our first baby, I had that on-edge feeling, I woke at every hint of a cry but this time I can just sleep through it and rely on my wife letting me know if I'm needed. It's not fair but it means at least one of us has the emotional resilience to deal with our toddler during the day :)

I've recently been on a five week streak of 100% sleep scores on my Whoop (couple days of 98%) by "volume" sleeping at consistent times. The five week streak started on the day we came home with our second child and we changed our sleep routine.

Me, my wife, my 2.5 yo, and newborn all get into bed (or bassinet) at 8 PM. From 8 - 9 PM we're juggling feeding newborn, reading to toddler, and signing toddler to sleep in whatever order is necessary for that night. Then we sleep around 9 PM till 7 AM with multiple wake ups for diaper changes in the night.

As the newborns gotten longer stretches of sleep, so have I and I can tell my sleep quality is better. I do see significantly higher REM/SWS times on a night where I do one diaper change versus 4 like the first week.

Subjectively, my sleep quality is bad - I feel tired but way less tired than with my first when I didn't try and "volume sleep". But my Whoop is happy to hand out 100% score because I've gamed the system with an insane amount of hours.

Given the circumstances, I'm sleeping as well as anyone could hope. And there might be some value in just "being in bed" longer if you can't guarantee sleep quality. I know I'm way less tired than I was with my first.

Is the final image on the splash page demo (with the car) from Cal Ave in Palo Alto?

Founder at Sunsama here.

What would close the gap between "closest" and "perfect for you"?

At Sunsama we address this directly in our pricing: https://help.sunsama.com/docs/pricing-manifesto

Shutting down or acquisition is the norm for calendar/task tools.

You can add Cron to your list too. They were just acquired last month by Notion. I think Cron had more traction than Sunrise/Woven too.

I've used ngrok every single day for ~8 years for work and didn't have the slightest clue how it worked. I'll still be paying for it but I learned a lot reading this.

Founder of Sunsama here. Just wanted to chime in to say that we've basically rebuilt the product from the ground up over the past 6 months to make sure things are fast and reliable.

I disagree, since it was spread orally and these texts were widespread in the subcontinent you could measure the similarity in different current renditions. If you looked at enough people's renderings you could even get a sense of how the transmission corrupts over time.

I'd been wondering if Hey.com was taking off after so much fanfare and drama when they released. The fact that they're doing this for an inherently viral product which had a massive launch probably means interest has now subsided?

Thanks for bringing this up. In fact, we also chose a "opt in" upgrade, where you pay after your trial is up. I'm of the opinion that "opt out" trials are a dark pattern. That being said, we realize the wording in the survey can be off putting but we think it's the right way to communicate expectations from the beginning and in the long run.

Nice little growth hack, I see you cover all the HN launches on your YT Channel!

That's true and one of the reasons we're keen to add an Outlook integration ASAP. We're a tiny team of five so building an integration with Google and Outlook from the get go wasn't feasible.

Thanks for being so frank. Perhaps that section needs to be re-written since Sunsama doesn't do reminders or use any sort of any algorithm to prioritize your tasks. Instead, we provide a guided daily planning workflow that nudges the user to make good decisions about what to do. In fact, one thing we feel strongly about is that you will make a better decision about what to work on than an algorithm.

Do you mean work being a queue of queues or superhuman?

We put this in place so that folks aren't going through the entire product onboarding which takes several minutes only to find out later there's no way to add an Outlook calendar.

Thanks, we've worked tirelessly on it and it's still not perfect!

Yup, the one thing about Sunsama that's different than Todoist and other task tools is that it's not useful unless you use it with your calendar.

We are definitely shooting for the "professionals who perform their job at an elite level" vibe more than a socioeconomic distinction. That being said, this is a valid criticism since "elite" has some obvious connotations.

1. One of our challenges will be to quickly add robust integrations with lots of other tools. Clubhouse is already a highly requested tool. 2. Yes, we think this the direction the world is moving is one where task tools specialize by role, if that isn't already the case.

And yes, the daily planning workflow is definitely opinionated, I can't disagree!

Thanks for that feedback. We put that in place so that folks weren't surprised after using it that Sunsama doesn't have a free tier since people assume that all productivity tools have a free version. If you just change your answer, you can proceed!

Yup, right now we've only been able to build an integration with Google Calendar. Turns out building a near replica of Google Calendar isn't easy! Once we add more services, we'll open it more broadly and make the questionnaire less cumbersome.

We found a lot of inspiration from Superhuman but there are some key differences: there's no required concierge onboarding and we don't require an invite from another user.

Andrew Montalenti's post on work being a queue of queues is fascinating in its own right. One of the things we're betting on is that we'll live in a world with more work queues as SaaS tools proliferate and specialize. We're hoping to build a place where you can build your queue for the day.

Sunsama is $20/user/month if paid monthly, $16 if paid yearly. Thanks for giving it a shot so early on!

I've wanted both of these things for so long. In some cases, I do like the to learn about the tradition and culture of a food but I wish that was under the recipe.

If your job is being reactive and sending e-mails it can be the center of gravity. This is particularly true for investors, executives and sales people.

However, if your job requires you to "build" whether it's code, slides, designs, etc then proactive work planning is essential and turning emails into tasks to be deferred is essential. I think of these as people who teeter between the maker and managers schedule: http://www.paulgraham.com/makersschedule.html

Obviously, I'm biased because I build a Daily Planner: Sunsama (https://sunsama.com)

This takes the idea of work being a queue of queues to the extreme: https://amontalenti.com/2019/11/04/work-is-a-queue-of-queues

Luckily, highly interesting and good design are not mutually exclusive.

I think Juggernaut tries to be "highly interesting" and "competes for our attention" with high quality content and writing. As they get their product out there they'll improve and mature their design.

I think the trend of startups with bad web design is actually interesting. If they can get away with something ugly maybe that means there's something intrinsically valuable in what they're building and their early customers/adopters are willing to look past that. Perhaps this trend is good and it indicates that these startups are focusing on their core value instead of a pretty facade?

If the product is content, then the text should be all that matters?

Awesome that they are open sourcing this. I've always felt funny about paying a ton of money to FullStory for this. I wonder what this means for FullStory and HotJar?

the youtube rollerblading community is pretty interesting. it feels like everyone knows one another even though they're spread across the globe.