justin 🌵

for 7 years as a PM, I've watched the same story repeat: ambitious product roadmaps vs. the reality of limited dev resources eventually you just accept it. the feature ideas that never make it. the "maybe next quarter" that never comes but I've also seen what's possible with high agency product teams (look at teams like Ramp) they don’t see this invisible separation of responsibility. both the engineering team and product team share the same passion for one thing - shipping responsible product fast so I've been building something It's called krosswalk - a tool that safely guides product teams to ask questions and build features in the existing codebase - NOT a prototype ask questions, get answers grounded in the actual code generate safe, reviewable, WORKING changes that get reviewed by your designers and product team before your engineers review and merge PMs can finally move from "I wish we could…" to "here's a working prototype." looking for PMs who feel this pain and want to join the next batch of users -> krosswalk.io

crying tears of joy, we can finally share insta comments 🔥🔥😭

@SaidAitmbarek @MicroLaunchHQ thanks for your support 🙏 will check this out

@JustinChitla dope value prop', upvoted feel free to launch it on @microlaunchhq too we get 30k+ makers/mo on the app

@b_migliaccio offer them a mac mini

How can we nerd snipe traditional devs to want to start building on Solana?

@_annakulina I just hate having to deal with aws bc they make it soooo hard to understand the bill and how to put a monthly spend limit

While everyone is getting Mac minis for ClawdBot👀... The real ones are just spinning up AWS EC2🙃 iykyk....

@SherryYanJiang super cool sherry! are you letting more folks get read access to the real repo(s) too? (for “current” prod functionality questions and better specs/prds)

we taught everyone at peek how to vibe code. this is how 2026 startups are built.

the best software teams will be made of 100% builders, differentiated less by title and more by what they optimize for: product intuition vs. systems rigor the first wave is already here - AI coding tools like claude code and cursor are letting non-technical teammates create real things but only the most innovate teams like ramp are adopting this “all builders” mindset this isn’t the destination! its just that current tooling is optimized for engineering workflows. the path from “i have an idea” to “this is safe to ship” is still messy. as more of the team becomes hands-on, we need an interface that makes changes easy to preview, easy to review, and hard to mess up krosswalk.io is the missing interface happy shipping 🤠

prompting is writing storytelling is writing reading is your training data

for 7 years as a PM, I've watched the same story repeat: ambitious product roadmaps vs. the reality of limited dev resources eventually you just accept it. the feature ideas that never make it. the "maybe next quarter" that never comes but I've also seen what's possible with high agency product teams (look at teams like Ramp) they don’t see this invisible separation of responsibility. both the engineering team and product team share the same passion for one thing - shipping responsible product fast so I've been building something It's called krosswalk - a tool that safely guides product teams to ask questions and build features in the existing codebase - NOT a prototype ask questions, get answers grounded in the actual code generate safe, reviewable, WORKING changes that get reviewed by your designers and product team before your engineers review and merge PMs can finally move from "I wish we could…" to "here's a working prototype." looking for PMs who feel this pain and want to join the next batch of users -> krosswalk.io

the best pms I know are obsessed with something completely unrelated to product

this is inspiring and exactly how I envision all ambitious product teams will work in the next few years! I've been working on a tool called krosswalk in case there are PMs/designers that are interested in building like the Ramp team! x.com/JustinChitla/s…

the single best thing you can do is constantly reset context - if you’re building a larger feature then I’ve laid out a method that works rly well here: x.com/justinchitla/s…

everyone is a builder! every day is launch day! everyone ships!

7/ the magic is the handoff: cursor ask mode → refine requirements interactively sprint .md files → turn plan into focused chunks fresh claude code agents → re-check reality + execute precisely each tool does what it’s best at

6/ claude code will usually spin up a few sub-agents to investigate what’s needed before implementing. this is where the quality comes from: smaller scope, sharper context, fewer bugs.

how i’m using cursor + claude code for consistently better results: