Bryce

3 weeks into this and I’m clawing my eyes out

@erbybody @andrewxroas I have the simplest idea that’s been proven but not in the wedge I’ve dressed the app in and I’ve been doubting if it’ll work but what I’m concluding from your replies in the thread the only way to find out is to distribute heavily

Last month, I quit my 6 figure job. 2 days ago, I hit my first > 1k day. Ask me anything. P.S. @andrewxroas changed my trajectory, thanks.

@SrDevMX @Argona0x I attempted recreating a small version of this and the varying details of reqs and rapidly changing feature requests were hard to account for but maybe I didn’t flesh out the system enough for quality of my liking

@Argona0x this would work for a niche problem space, for others definitely needs more contact with the outside world, which is the role that I play as a dev when using AI, I'm the one that enters the messy variability of reality into this closed system I see this having a future, yes

a 28-year-old in Berlin runs a 7-agent software factory off a remote server she approves checkpoints from her phone at midnight; her workspace has no desk, no city, no fixed machine - any screen is just a terminal she quoted $28,000 for a scope a local agency priced at $74,000 and told the client 'minimum 6 weeks.' the agents shipped a validated PR in 19 hours the agency was still revising their proposal i've been running a version of this for the past few months. the setup sounds absurd until the first time it works, and then you can't go back the factory lives on a remote VPS - always on, eight tmux panes, already mid-session. ssh in from whatever screen is nearby: laptop at home, phone on a train, tablet at a café at 1am. the environment never moves. you're just a terminal window connecting to something that was already running agencies price the way they do because their overhead is structural. a $74,000 quote on a 6-week scope is real math: account managers, a senior dev who gets rotated to a bigger client by week three, revision cycles that exist because context lives in fourteen slack threads instead of one file the factory collapses all of that into a CLAUDE.md → a 100-line markdown file at the repo root loads the entire project into every new agent session - stack, architectural rules, banned patterns - so no session starts blind and no context drifts between runs → agent one is read-only: maps the existing codebase, documents patterns, flags risks before any agent touches the code → agent two writes the user story and acceptance criteria, locking the exact definition of done before engineering starts → agent three produces the technical brief: data model changes, API shapes, a precise list of every file that will move - this locks before any builder runs → backend and frontend build in parallel but in isolation, each scoped to its own directories, so they can't reach across and corrupt each other's work → agent six writes acceptance tests against the original user story criteria before the implementation is considered complete → agent seven runs a final read-only audit: missing auth, tenant isolation gaps, any deviation from the brief gets flagged back into the loop before the pr is cut → three checkpoints pause the entire chain for human approval - story, spec, pre-merge - each one a 30-second phone tap when the upstream work was done right the 19 hours is the output. what compressed was everything underneath: the pm relaying a question to an engineer who responds two days later, the architectural mistake that only surfaces after code is written, the context drift between sessions because the memory layer is a human brain instead of a file that loads before anything runs the loop closes itself. validator flags a gap, builder fixes it, verifier confirms, pr is clean by morning the agency sent their revised proposal at 9am. the pr had been merged for 14 hours she approved the final checkpoint at midnight, 30 seconds on her phone. the agents were already done the desk, the office, the fixed machine - she left them out

@marcusle_ How did you learn how to manage people

just hired first static ad designer, and wish i done it sooner now i need to create a feedback loop so they can evolve their ads i was afraid of hiring for so long as i lost alot of money hiring and i didn't know how to manage people

@molaerga I’ve heard lower paid conversion in comparison to tiktok/meta but let me know how it goes

@cainology Yes!

Day 65 of 90 - road to $1k MRR MRR: $0 - submitted YAK update to test flight - made a landing page with lovable - posted on Yt & Tt - created more images for next batch

I used to think that if I launched a simple app / MVP someone could copy it The real differentiator between winners and losers is: Shipping and iteration speed Extremely sticky core loop Crushing distribution

10 followers in my 24 hours let’s keep going

@simpsoka I’ve learned my lesson. Watching older people navigate UI’s the next step or action point has to be blatantly obvious and clear

You should always sacrifice cleverness for clarity in design. And sometimes you even have to sacrifice simplicity for clarity.

@dramaricic Probably before that, 1.5k in profit monthly for 3 months and I’m out of there

Will you quit your full time job when your SaaS hits $5k MRR?

@thepushpesh Retention, can’t have a big exit without it

What’s harder right now Shipping your app fast or actually making users come back every day?

Push to Summer day 2/30 ASC & RevenueCat finished Today’s goal: Sort out marketing and make my first TikTok creative Should I warm up another TikTok account or just use the one I have (I’ve done some off niche scrolling lol and wonder if it will fuck my ads)

@JoelIslasx1 Cold outreach

@cainology Exactly. I debated for so long to just give the tool for free and get users but I decided to charge from day 1. This is the only way to validate your idea. How do you currently get your first paying users for your products?

When I was stuck at $0 MRR, the biggest thing for me was just having the audacity to charge people Don’t be scared to charge for your product & hard work You may think your build is too simple or easy to recreate, but the vast majority of the world is not technical

@kenrt_ The value it provides Relief of pain (my app) remedy of insecurity (looksmaxing apps) novel insights (CalAI) It enables the user to do something they couldn’t do without it

What makes a great product idea? Is it originality, the value it provides, or something entirely different. I want to hear some thoughts on this.

@jakubmuzzik Do you run ads or organic?

just woke up to $3,000 MRR last month I focused less on marketing and more on building so the growth been a bit more flat still have a few features and improvements to finish before I'll double down marketing again excited to see how far this can go 🔥

Building after work is a different game You don’t just need a good idea You need a system that still works when your brain is fried, your time is limited, and every bug feels a little more buggy

@YairDev I have seen some beautiful swift ui’s + animations so I can’t deny that

@cainology faster builds, swift ui is really nice, super reliable

best decision I've done building mobile apps is to use Swift instead of Expo can't even begin to describe how better the experience is