Product & AI Engineer. I build production-grade systems, not just wrappers. Bridging full-stack (Next.js, FastAPI, Postgres) with applied AI and autonomous work
If you validate LLM tool calls with Pydantic, don't just reject the bad ones.
Send the validation error back to the model as the next message: which field failed and why.
Most of the time the second attempt is correct. Cap it at one or two retries, then fail loudly.
Building AI products for Nigerian users taught me this:
Nobody wants to download your app.
But everyone has WhatsApp open all day.
If your users live in chat, your product should too. The interface people never close beats the one they forget to open.
I made a private group for builders.
698+ people are already inside.
What you get:
- Hackathons, grants and accelerators before everyone else
- 0% equity funding and visa programs, the ones I post here first
- AI tools and free credits worth claiming
- Remote jobs and internships
- Builders shipping the same stuff as you
Just opportunities, every week.
Want in? Reply "builder" and I'll send the link ๐
Orbit is in beta.
If you freelance or juggle multiple projects, I'd love you to use it free for 2 weeks and tell me honestly what's broken.
Reply "orbit" and I'll DM you the link.
Every freelance dev I know runs their business on the same "system":
Deadlines scattered across client WhatsApp chats and memory.
So instead of building another dashboard, I built Orbit: a project manager you just text on WhatsApp.
How it works under the hood ๐งต
Stack:
FastAPI
PostgreSQL + pgvector (Supabase)
Gemini
Groq Whisper
WhatsApp Cloud API
Paystack
Biggest lesson: the best interface for a productivity tool might be the one people never close.