Beautiful example of the kind of software that just wouldn’t exist pre-AI. Climbers have been wanting this kind of app forever, but really good hold detection from any photo was the blocker. For the past two months I spent ~10 mins every few days asking Fable to test models, create evals, create an entire app for me to quickly QA results, etc etc and last week we cracked it. 18 months ago building this would’ve meant hiring a 6-figure salary dev to spend 3-6 months on something like most likely wouldn’t ever work, so it just wouldn’t ever happen. Wild.

Not sure when it happened, but Codex is great at building Google Sheets now. Was struggling a bit to get a flexible financial forecasting tool baked in to our app, found myself typing "no i want a spreadsheet-like ui... wait a second...🤔" -- it builds and updates a Sheet effortlessly (formulas, assumptions, charts, live app data + APIs) and is exactly what i wanted ✅

Possibly my most popular all time tweet (😂) now probably wrong? marketing site is now a part of the full stack rails app. Unlocks so many neat app/agent-powered features that would be so much harder with a separate CMS.

Not sure if any of this is a good idea or not, but here's my "stack" for AI-assisted SaaS building: 1/ I use both the Claude Code and Codex native apps. I like both for slightly different reasons. In particular, Codex's preview browser with annotation markup is really helpful. 2/ also have CC and Codex installed on a remote VPS with a hand-off skill to hand off tasks from desktop app to VPS as needed. 3/ I use Fable primarily to orchestrate larger feature builds. It's set up to delegate coding tasks to Codex or Opus/Sonnet agents as needed and then reviews and iterates. Really big features start with it building a clickable mockup for me to approve. 4/ smaller, more direct tasks, bug fixes, etc., usually directly in Codex using 5.6 Sol. 5/ PRs get batched into a review queue, and then Fable reviews in a batch, runs tests, CI, and deploys to a staging environment. 6/ full manual browser QA in staging before release. I'll often have the agent compile a PDF of screenshots of every step of the QA so I can check for any weird UI bugs. 7/ Once it's good on staging, promote staging to main. After every deploy, Fable is instructed to keep an eye out post-deploy for any immediate bugs, errors, or issues. 8/ I also have Hermes installed on a VPS and a post-deploy hook where Hermes does a non-destructive browser QA of the production app to look for any immediate issues. 9/ a scheduled Codex task checks Sentry multiple times per day for any new errors and has a triaging workflow to either immediately create PRs and add them to a monitoring queue. In the case of extremely urgent, problematic issues, it can push a PR hotfix to main and notify me immediately in Slack. This Codex session has its own internal dashboard, which is an HTML artifact that it keeps up to date with: recurring issues, what can be learned to improve testing , what it pushed, etc 10/ For example, it appropriately nudged me to upgrade our Hetzner server, which it pretty much handled for me. It has a recurring task to check the overall health of our servers and databases, ensure backups are running properly, do dry runs of the backup restore, make any recommendations based on usage and capacity 11/ our team has a Slack channel for reporting bugs and feature requests. Codex skill checks that Slack channel for me periodically and proactively investigates and creates PRs for me to review. It's scheduled to close the loop and reply back in Slack when things have been resolved or features have been added.

some more thoughts: do i think every business owner will build their own custom SaaS? No. do i think every vertical B2B SaaS should do this? Yes. If you own the customer and the billing, it's pretty easy to build a good enough replacement for almost very other software they pay for now and capture more wallet share.

it takes time but i feel like i spend about the same amount of time i would be fussing with and zapping together 15 different tools, but this time i always get exactly what i want. No waiting for support either :) bugs and stability is a bunch of agent loops monitoring performance and errors and automatically pushing fixes. Also loops like a channel in slack where staff can report bugs or request features and agents just check it and create PRs automatically (and report back in slack when fixed). The benefits of having everything all in one place, no extra accounts to onboard staff, no per seat pricing, everything integrates/syncs perfectly, and my agents have full visibility/control seems really outweigh the costs so far.

Hoo boy. @bkup_climbing has been ready for people climb in it for 3 months but we're still waiting for the NYC DOB inspections/permitting process to complete. Brick & mortar is next level difficulty!

I can't over-emphasize this enough for folks at the earliest stage of building your SaaS. Put the application on a subdomain like app.your-product[dot]com and have your main .com be an easy to use CMS marketing site like Wordpress or Webflow. So annoying to unwind after the fact.