The case for personal:
An example SaaS today has 50 features.
I need about 6 features, 2 of those features are not in the 50 features that the SaaS offer or they are locked behind an Enterprise plan.
I don’t have time to scout around for alternatives. I also don’t want my data to be locked into the SaaS vendor.
Vibe coding my own tool will probably take 1 day. It’s pretty simple math.
@diamondarm_com@marclou@stemonte Build trust via free trial, not free plan, big difference.
Solo builders lose money on free plans.
Might work for large vc funded companies as distribution, but depends on the biz.
@MulticaAI has become my daily agent organization tool now.
Super useful to have all your tasks in a Kanban board and agents working alongside you
Thanks for open-sourcing it @jiayuan_jy https://t.co/DXM4j4L04l
SaaSpocalypse incoming?
I doubt it.
For overpriced SaaS with high cost which is easy to be replaced more churn and rising competition
So yes in that sense.
BUT: Building a cool product, maintaining and securing it and dividing the cost of overship by many people will survive.
Bye bye Beehiiv 👋
I vibe-coded my own newsletter platform:
📧 Campaign management w/ editor
🖥️ Web archives (https://t.co/pypYdNhdlZ)
🔗 API support
🫧 List cleanup, deliverability reports
It took a few prompts with Opus 5.5.
I left Beehiiv because they raised prices for the 3rd time in 2 years.
- My first yearly bill was $1,000.
- My future bill would have been $4,000.
Now I'm using AWS SES + MongoDB, and I will pay less than $300/year.
Newsletter platforms charge per subscriber, when in fact the real cost is the number of emails sent. Subscribers will naturally become inactive, so you end up paying more for something that hurts your deliverability (sending to dormant subscribers = spam trap).
So I've set a cleanup cron job for my newsletter alternative. It marks inactive subs as dormant, sends one last re-engaging email, and stops emailing them. Money saved. Deliverability increased.
I also gain a priceless feature: Freedom. I can change the UI, add features, connect all my apps - anything is possible with just a prompt.
I'm replacing Resend next. I love it, but it's very expensive ($400/mo)
You need to be careful with giving access of personal info to agents.
An agent had access to the bank account and another agent access to the company's slack.
Shane wanted to post it in his agent "exec chat", but the agents assumed the company exec channel was the right call.
Embarrassed to share this, but it scared the shit out of me
Last Thursday, an AI agent posted my personal bank balances into our company Slack. As me
It broke down all my expenses in detail. Then it apologized
Be careful of the dark side of proactive agents
More below...
Yes and no.
For an individual run yes.
For your orchestration of tasks / todos etc I have a better experience having a dedicated platform which then calls codex / Claude as parallel agents.
a weird inversion with LLMs is the models improve faster than the tinkerers
when i see people with custom workflows and setups they're all addressing problems that don't exist anymore
the person naively using vanilla codex is more likely to be experiencing state of the art
@johaugum I think just focusing on the pain, so go where users have a real problem and you can save them a lot of time. Build a solid solution, then word of mouth picks up. Focus on less technical people's problems.