5
I built AI agents that do the grunt work solo founders hate
Hey HN,
I'm a solo founder. Every morning I was spending 2 hours doing the same things: checking competitors, reading AI news, monitoring my Stripe dashboard, looking at Google Trends for content ideas.
So I built Seleci to automate all of it.
What it does: You pick a template (Market Pulse, Revenue Radar, Trend Scout), click deploy, schedule it, and every morning you get a clean markdown report — no code, no Zapier flows, no prompt engineering.
How it works under the hood:
FastAPI backend with an agentic loop (tool-calling LLM with web search, Stripe API, Google Trends) Per-tool rate limiting to prevent runaway agent loops (web_search capped at 3 calls/run) React/Vite frontend, Supabase auth, deployed on Koyeb + Vercel The agent actually executes tools and returns structured results — not a chatbot wrapper What it's NOT:
Not another ChatGPT skin Not a no-code workflow builder (no nodes, no drag-and-drop) Not trying to replace developers — it's for the founder who doesn't have one Live demo: https://seleci.com
I'm applying to YC with this. Would love brutal feedback from HN via Discord — what's missing, what's broken, what would make you actually use this?
> checking competitors, reading AI news, monitoring my Stripe dashboard, looking at Google Trends for content ideas
This problem can be solved not only by automating the process. For example, one solution is to simply stop doing all of this. You don't need to analyze your competitors every morning; it's enough to do it once a month or even once a quarter. Reading news about AI is one way to procrastinate.
Your precious morning time should be spent on truly important tasks.
It has the same problems as most other AI systems
1) Claims feel a little inflated (10+ h saved) and that hurts credibility everywhere. How do you know it's 10 hours when you don't even convince me that you know what I spend 10 hours a week on. If you nailed this properly, you'd have the Manus effect - people would immediately start declaring it a fake and discrediting it everywhere.
2) Price is vague and excessive. What's a credit? Why is it USDC? Everyone seems to do this vagueness, including OpenAI (free for minimal use, go for more use, plus for morer use, max for maximum use). I appreciate the transparency and get that it's anchored to hiring humans. Sellers will sell it as "Starting from $49/month!" but buyers will read it as "Up to $499/month!"
3) This is an extremely high anchor then. If it were a problem, I'd just build it myself or ask ChatGPT to. How do I know something like Manus doesn't already do it? And since the site itself is lazy, how do I know it's not just an API connected to a Ralph Wiggum loop?
The core problem is (1) though, it adds up and amplifies the other two.
And it's USDC cause crypto payments are becoming more and more frequent and I neither can't use Stripe nor paypal due to geographical restrictions
I don't have time to check Stripe but do have time to figure out another crypto coin seems to be the wrong way around unless marketed to a very niche group.
I litterally can't recieve nor send money through stripe
Thanks for your feedback. I'll take note of it
You using x402 services on the backend for this btw?
If you are, I have a service (Obul) that gives access to all x402 APIs without needing a wallet or USDC.
https://my.obul.ai/