A production-ready RAG starter where guardrails are part of the architecture: an input guard that...A production-ready RAG starter where guardrails are part of the architecture: an input guard that...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
A production-ready RAG starter where guardrails are part of the architecture: an input guard that blocks prompt injection and jailbreaks, an output guard that redacts PII (emails, SSNs, cards, API keys), and rate limiting. Qdrant semantic search, FastAPI, Next.js, PostgreSQL, plus a Terraform deploy repo.
I’ve been razzmatazzing and flibbertigibbeting with Claude Code and somehow ended up with a new yels.dev.
It finally feels like me: simple on the surface, slightly complicated underneath, and very much alive.
You can see who I am, what I do, the work behind Herodot, RaptorLabs, CyberLink Security and Solmint, plus a selection of projects I’ve built across AI, cybersecurity, Web3, product systems, education, archives, and experimental digital spaces.
The simple-on-the-surface, layered-underneath idea comes through so clearly in the presentation. I especially like how the project archive turns the site into something to explore rather than just a résumé of links.
Built the complete Admivo.in ecosystem from scratch for a foreign education consultancy, covering the student-facing platform and internal operations. The system includes country/destination discovery, application journey, counsellor workflows, resource libraries, live admission updates, document management, sessions, and an admin dashboard for managing the entire ecosystem.
Here's exactly what it looks like to work with me 👇
Hiring someone you've never worked with is a leap of faith... and honestly, most "hire me" posts don't help. They tell you what someone offers, not how it actually goes. So let me close that gap.
Before we even start: a quick discovery conversation
No commitment, no pressure. We talk through what's actually eating your time, what "support" would ideally look like for you, and whether I'm the right fit. If I'm not, I'll tell you and probably point you somewhere better.
Week one: I get the lay of the land
This isn't me disappearing into a task list. I ask questions about your tools, your workflow, your pet peeves, the thing you keep meaning to fix but haven't had time for. By the end of week one, I've usually already spotted at least one small inefficiency worth flagging.
Ongoing: communication that doesn't require babysitting
You'll get regular updates on what's moving, what's done, and what needs your input on a cadence we agree on upfront (daily check-in, weekly summary, whatever actually fits how you work). No mystery. No "what has she even been doing" moments.
What "done" looks like
Done means the task is complete and handed back in a way you can actually use labeled, organized, explained if needed. I don't consider something finished just because it's off my plate; it's finished when it's usable on yours.
The honest part: I'm not going to pretend every project is flawless from day one. Systems get refined. But refinement happens through clear communication, not radio silence and that's the part I take seriously.
If the biggest thing holding you back from hiring support is "but what am I actually getting into?" hopefully this answers it.
💬 Got a question about how this would work for your specific situation? Ask. I'd rather answer it now than have it be the reason you don't reach out.