I wanted to test how far AI coding tools could take a production project. Not a prototype. A social media management platform with 12 first-party API integrations, multi-tenant auth, encrypted credential storage, background job processing, approval workflows, and a unified inbox. The scope would normally keep a solo developer busy for the better part of a year. I shipped it in 3 weeks.
I broke the specs into tasks that could run in parallel across multiple agents versus tasks with dependencies that had to merge first. This planning step was the whole game. Without it, the agents produce a mess.
I used Opus 4.6 (Claude Code) for planning and building the first pass of backend and UI. Opus holds large context better and makes architectural decisions across files more reliably. Then I used Codex 5.3 to challenge every implementation, surface security issues, and catch bugs. Token spend was roughly even between the two.
Where AI coding worked well: Django models, views, serializers, standard CRUD. Provider modules for well-documented APIs like Facebook and LinkedIn. Tailwind layouts and HTMX interactions. Test generation. Cross-file refactoring, where Opus was particularly good at cascading changes across models, views, and templates when I restructured the permission system.
Where it fell apart: TikTok's Content Posting API has poor docs and an unusual two-step upload flow. Both tools generated wrong code confidently, over and over. Multi-tenant permission logic produced code that worked for a single workspace but leaked data across tenants in multi-workspace setups. These bugs passed tests, which is what made them dangerous. OAuth edge cases like token refresh, revoked permissions, and platform-specific error codes all needed manual work. Happy path was fine, defensive code was not. Background task orchestration (retry logic, rate-limit backoff, error handling) also required writing by hand.
One thing I underestimated: Without dedicated UI designs, getting a consistent UX was brutal. All the functionality was there, but screens were unintuitive and some flows weren't reachable through the UI at all. 80% of features worked in 20% of the time. The remaining 80% went to polish and making the experience actually usable.
The project is open source under AGPL-3.0. 12 platform integrations, all first-party APIs. Django 5.x + HTMX + Alpine.js + Tailwind CSS 4 + PostgreSQL. No Redis. Docker Compose deploy, 4 containers.
Ask me anything about the spec-driven approach, platform API quirks, or how I split work between the two models.
First, congrats on your accomplishment(s) and leveraging your AI+Python+WebDev talents.
Isn't this a SaaS-pocaplyse testament? What's stopping anyone from doing the same to BrightBean? What's stopping anyone with a little of domain knowledge and a $200+ Claude to clone your app and build yet another gap-filling, slightly improved content-syndication version and go-to-market? Is it worth taking it to the market when anyone can perpetuate the cycle?
I'm genuinely interested in knowing your thoughts.
I built something very, very similar for a client to post their content on schedule to about 9 different social networks. It was my first major vibe-coded app -- I normally vibe-code a function or small apps. Took about two hours with Claude [0] by just building up the functionality in layers, testing each layer as we went. If I'd rawdogged it, 2022-style, it would probably have taken me a month to write.
It's been running flawlessly for months without a single error. In fact, spooky good. I still feel nervous about it, though and check it every morning.
It is built mostly as a web app in .NET 10 Razor with SQLite db.
The APIs for the social networks are the hazy bit. As OP mentions, some are badly documented. Some are a pain to get access to. I was using a driven browser to post to Twitter, but they opened their API recently, which was nice.
[0] I used Claude in Github Copilot, so total cost was less than the $10/month in credits.
Recently I built a "azure devops deployment central" tool just because microsoft is unable to make their ui usable at scale.
The tool shows all pipelines, builds, buildagents and approval ready in one place at a glance. For the most actions I use the public api but approval I use the internal api because they are still not public, since 4 years.
The tool runs so smooth it scares me too! My guess is that the apis are so stable that it will work for the next 10 years.
I am genuinely in the "target market" for a tool such as this, but having evaluated one previously I found the quality and self-hosting experience to be pretty bad, and that a proprietary freemium product was still a better experience.
I'm hesitant to even take a look at this project due to the whole "vibe coded in 3 weeks" thing, though. Hearing that says to me that this is not serious or battle-tested and might go unmaintained or such. Do you think these are valid concerns to have?
I think the same way, I'd love a social media management tool, all of the ones I found were insanely expensive or not usable / had horrible usability issues. Pitching a product by telling me it's built quickly with AI does the opposite of convincing me to try it, even though I'm in the market for the solution offered.
My gut is -- of course these concerns are valid, but, especially with "newfangled" software projects like this, I'd genuinely be surprised to see major quality differences between "human" and "vibe-coded."
I think what I mean by "newfangled" is; this isn't a low-level C memory managed bit flipping thing; this is the sort of thing that's already built on top of layer of layer of the cruft that the web already is, for better or worse.
I was hoping this was the opposite of a creators platform - a social media users platform. Download all social media to one place (stories/posts) where you can view on your own schedule.
tiktok certainly seems to prefer if you post a draft using api and then manually publish it using the tiktok app on your phone, but the other platforms like youtube, instagram and facebook don't seem to mind. Its also recommended that you warm up an account manually before posting to it using an api. I've recently built and agent first social media scheduling tool: https://mallary.ai
Nice! A bot-built tool for posting content mostly generated by other bots and engaged with by bots.
I don't mean to belittle the cool tool you made, I'm just grumpy about the loss of what the social network could have been and what we got when it morphed into social media.
AI generated README, AI generated code, and the creator can't even be bothered to write comments without generating them with AI (which btw goes against the rules of this site). How is this being upvoted - did the creator use his own tool to bot this submission?
44 comments
[ 4.5 ms ] story [ 85.6 ms ] threadBefore writing any code, I spent time on detailed specs, an architecture doc, and a style guide. All public: https://github.com/brightbeanxyz/brightbean-studio/tree/main...
I broke the specs into tasks that could run in parallel across multiple agents versus tasks with dependencies that had to merge first. This planning step was the whole game. Without it, the agents produce a mess.
I used Opus 4.6 (Claude Code) for planning and building the first pass of backend and UI. Opus holds large context better and makes architectural decisions across files more reliably. Then I used Codex 5.3 to challenge every implementation, surface security issues, and catch bugs. Token spend was roughly even between the two.
Where AI coding worked well: Django models, views, serializers, standard CRUD. Provider modules for well-documented APIs like Facebook and LinkedIn. Tailwind layouts and HTMX interactions. Test generation. Cross-file refactoring, where Opus was particularly good at cascading changes across models, views, and templates when I restructured the permission system.
Where it fell apart: TikTok's Content Posting API has poor docs and an unusual two-step upload flow. Both tools generated wrong code confidently, over and over. Multi-tenant permission logic produced code that worked for a single workspace but leaked data across tenants in multi-workspace setups. These bugs passed tests, which is what made them dangerous. OAuth edge cases like token refresh, revoked permissions, and platform-specific error codes all needed manual work. Happy path was fine, defensive code was not. Background task orchestration (retry logic, rate-limit backoff, error handling) also required writing by hand.
One thing I underestimated: Without dedicated UI designs, getting a consistent UX was brutal. All the functionality was there, but screens were unintuitive and some flows weren't reachable through the UI at all. 80% of features worked in 20% of the time. The remaining 80% went to polish and making the experience actually usable.
The project is open source under AGPL-3.0. 12 platform integrations, all first-party APIs. Django 5.x + HTMX + Alpine.js + Tailwind CSS 4 + PostgreSQL. No Redis. Docker Compose deploy, 4 containers.
Ask me anything about the spec-driven approach, platform API quirks, or how I split work between the two models.
Isn't this a SaaS-pocaplyse testament? What's stopping anyone from doing the same to BrightBean? What's stopping anyone with a little of domain knowledge and a $200+ Claude to clone your app and build yet another gap-filling, slightly improved content-syndication version and go-to-market? Is it worth taking it to the market when anyone can perpetuate the cycle?
I'm genuinely interested in knowing your thoughts.
It's been running flawlessly for months without a single error. In fact, spooky good. I still feel nervous about it, though and check it every morning.
It is built mostly as a web app in .NET 10 Razor with SQLite db.
The APIs for the social networks are the hazy bit. As OP mentions, some are badly documented. Some are a pain to get access to. I was using a driven browser to post to Twitter, but they opened their API recently, which was nice.
[0] I used Claude in Github Copilot, so total cost was less than the $10/month in credits.
The tool shows all pipelines, builds, buildagents and approval ready in one place at a glance. For the most actions I use the public api but approval I use the internal api because they are still not public, since 4 years.
The tool runs so smooth it scares me too! My guess is that the apis are so stable that it will work for the next 10 years.
I'm hesitant to even take a look at this project due to the whole "vibe coded in 3 weeks" thing, though. Hearing that says to me that this is not serious or battle-tested and might go unmaintained or such. Do you think these are valid concerns to have?
Last time I “vibe coded” something (internal) and I liked it because I couldn’t find external solution.
I admire coders who can finish their code into deliverable and usable piece.
Issue here is software abundance and ppl will start to hesitate due to absurd pile that they should evaluate.
It reminds me the statistics of ice cream global sales. People want certainty so they choose chocolate or vanilla :)
Therefore many good software projects will have a problem to find users.
It can be done though. And i say it as a developer for 20 years now.
I think what I mean by "newfangled" is; this isn't a low-level C memory managed bit flipping thing; this is the sort of thing that's already built on top of layer of layer of the cruft that the web already is, for better or worse.
Is there anything like that out there?
I don't mean to belittle the cool tool you made, I'm just grumpy about the loss of what the social network could have been and what we got when it morphed into social media.