You can use locul.ai for that; makes your memory layer far more robust and it ports over to claude code/desktop as well. Also uses your linkedin, dictation notes(wispr flow. Etc) and tons of other sources to build and auto update your second brain too

Since I went full-time on my startup there's a voice in my head that says "you should be working" whenever I watch a movie or go to bed. I took my first planned weekend off 16 months in. Does that voice ever go quiet for you?

Photo: @Scobleizer (Didn't know it was captured by him)

WOW! The original photographer showing up in the replies I think is the best outcome this post could get. If you don't mind me asking, what did you make of Burbn when you first saw it? Anddd did the pivot surprise you at all?

Thanks @Substack! Loving the platform! 🫶🏼

The full prompt and setup: contextli.com/loop-engineeri…

So the agent asks by email, I answer with a voice note labeled "claude", and the same Claude Code session carries on within 10 minutes.

Two lines in my /loop prompt fixed it. "Email me any question instead of waiting." And: "If a note is feedback on an earlier task, apply it to that task."

The most annoying thing about coding agents: they stop halfway to ask you a question, you're not there, and the task just sits.

I'm going to do one of these a day for a while: a famous company move, and what it looked like when I tried it at my size. Follow along if that sounds useful.

People usually tell this as a story about focus. I think the more useful bit is that the users told them what to keep. Photos weren't the plan. They were just the thing people kept doing. Look at your own product this week. What do people do in it without being asked? That's your Instagram. The rest might be Burbn.

Since then I run one rule. One product, for about a year. I only start the next one when the previous one has a growth loop that runs mostly on its own, like SEO or LinkedIn. I've repeated that up to product nine.

My first startup was Burbn times four. We built four products at the same time. All four stalled at about 60%. None of them got finished properly, and nobody used them. Looking back, the ideas were fine. There were just too many of them at once.

Cutting sounds easy when you read it in a startup story. When it's your app, every feature has a story attached. The week you spent on it. The person who asked for it. Deleting it feels like admitting that time was wasted, so most founders keep it.

Systrom and Mike Krieger looked at what Burbn users actually did. They skipped the check-ins. They ignored the plans. They posted photos. So the two of them threw away most of what they had built and kept photos, comments and likes. They called it Instagram.

In 2010 Kevin Systrom had an app called Burbn. Check-ins, plans, points, photos. It was running low on cash and people didn't stick around. So he deleted almost all of it. The stripped-down version had 25,000 people sign up on its first day. 18 months later Facebook paid about $1 billion for it, with 13 employees. My first startup did the exact opposite 🧵

how do I get the last 4 points? anyone got any pointers?

IF you run a SaaS and you DON'T have this, you're ngmi. THIS PLUGIN CAPTURES RATINGS FROM USERS IN-APP AT ALL THE "wow" moments. And then shows you everyone who almost gave feedback but bolted i.e. -> HOT LEAD! Best part: It has a lifetime deal -- and an agency plan for multiple brands in one place!

Turns out I couldn't do a startup part-time. It needed all of me, with no salary to fall back on. So I left. I'm on product nine now, still bootstrapped. If you have a job and want to start something, what's stopping you?

I quit a six-figure job (after tax) in 2024 to work on my own products full time. Before that I built on the side while still employed. Two startups and an Amazon store in Australia. Each one lasted 8 to 10 months.