As an engineer, it always hurts seeing teammates not use a product you built to make their lives easier.

But I started looking at it from their side.

UI, dashboards, tables, filters, workflows, interfaces all of it can feel intimidating. Even if your product is objectively better, switching from a workflow they re comfortable with feels like a drag.

And managers forcing them to use the product usually makes it worse.

I work on several client projects plus my own products, and most of the work now goes through AI agents (Claude Code, Codex) in the terminal. A lot of what the agent needs isn't code, it's documents: specs, meeting notes, spreadsheets that live in Box, Google Drive or a local folder.

The friction: every time a task touches a document, I leave the terminal, click through Finder subfolders or open Box in the browser, find the file, download it, then hand it to the agent. It's slow and it breaks my focus on the actual task.

What I do today: I built a small picker for myself, so I type @ plus the first letters of the file name in the terminal and the path goes straight to the agent. (Disclosure: I'm the maker of PMDesk, so I'm biased. This is only my own impression, I haven't timed it.)

I'm curious whether that's actually the best approach or just my habit. Two things I'm unsure about: do you keep project documents inside the repo or outside it, and how do you make sure the agent is reading the right, current file?

Were you able to build and monetize the product?

Please avoid answering the question if -

• You've built just another Product Hunt Spinoff or any other directory.

• You're monetizing by selling prototypes just like agencies.

• Any other kind of business where you are charged to display ads.

It'll be good to see if people could monetize a real SaaS product that they vibe coded.

Lately I ve been wondering whether the one AI tool builds the whole product idea is actually what people want.

For a simple website or SaaS-style app, the workflow often ends up looking like this:

UI in one tool, backend somewhere else, auth/payment setup in another place, deployment on a different platform, and maybe an admin dashboard built separately.

That gives you flexibility, but it can also get messy fast especially for non-technical founders, small teams, or people trying to validate an idea quickly.

I ve been thinking about how messy the current build an app with AI workflow still is.

For a simple website or SaaS-style product, people often end up jumping between multiple tools:

• one tool for UI generation

• another for backend/database

• another for auth

• another for payments

• another for deployment

• and maybe something else for internal dashboards or admin tools

It works, but the workflow can get fragmented pretty quickly especially if you re not a full-stack developer.

I vibecoded a feature that shipped and worked. Users liked it. I felt great about the speed.

Three weeks later I needed to change one thing about it, and I could not. The code was a knot. It worked, but only from the outside. Every attempt to modify it broke two other things, and I ended up rewriting the whole thing from scratch in a weekend I had not planned to give away.

I built something with an AI agent over a weekend. It worked. I was thrilled. Then a friend asked me how it worked and I realized I could not answer.

Not because it was complicated. Because I genuinely did not know. I had described what I wanted, the model had produced it, I had tested the surface, and I had never gone underneath. The whole thing was a black box I had asked a machine to fill.

By week three of a side project, I could not recall why I had programmed the application to deal with time zones in that particular manner. The code made sense within itself, but the rationale was missing because it existed in a chat window that I had long since closed.

Hence, I began creating a simple text file in the repository entitled "decisions," and in it, I noted two or three sentences: the question, the decision I made in response, and the date. This took less than a minute, but it has spared me from reversing my decision twice.

Founders: What are you actually using for vibe coding in 2026?

I'm curious what other founders are using today. Claude Code? Codex? Cursor? Bolt? v0? Replit? Is Lovable still part of your workflow, or have you moved on?

When we were building our platform, I used Figma and Builder.io to accelerate the design and front-end code for roughly 500 screens. It gave our front-end engineers a tremendous head start.

Today, when I'm wearing my product designer and UI/UX hat, I use Figma Make. It works really well for me.

My terminal coding agent had hit its weekly limit and I had a small bug sitting in my queue, the kind of thing that would normally take one prompt and thirty seconds, so I figured I'd just fix it myself while I waited.

Took me almost the full thirty minutes. Not because the bug was hard, it genuinely wasn't, but because I kept reaching for a keyboard shortcut that wasn't there and realized I'd forgotten the actual syntax for something I used to type without thinking. Had to look up documentation I would've known cold two years ago.

Got it fixed right as the coding agent's limit was reset and honestly felt a little relieved, like I'd passed some test I didn't know I was taking. But it also left me wondering how much of that muscle is still in there versus how much I've quietly outsourced without noticing, since it's not like there was ever a single moment where I decided to stop practicing it.

Has anyone else tried this on purpose, going a day without the assistant just to check? Would you actually want to know the answer, or is it better not to look too closely at how much you've forgotten?