I build LLM systems that run in production. The clearest example is live: pick a sector at <a href="https://demo.consentleads.uk" rel="nofollow">https://demo.consentleads.uk and message it the way a customer would. Nothing is scripted. It runs on a free-tier ARM box behind a Cloudflare tunnel, is multi-tenant and has users, and nine scheduled jobs keep it going unattended.
If opt-out detection misses a phrase, the system keeps emailing someone who asked it to stop, and nothing crashes or alerts. So the suppression gate fails closed, and the eval fixtures cover that path and reply triage.
I also wrote claimcheck (MIT, <a href="https://github.com/visione4906/ctaio-claimcheck" rel="nofollow">https://github.com/visione4906/ctaio-claimcheck): give it a document and a codebase and a second agent has to prove every claim against the source with file and line citations, or the build fails. I built it after an outside review of my own writing turned up claims the code did not support.
Looking for AI engineering or AI automation work, remote.
Sal4906 · · focus · HN ↗
Remote: Yes, remote only
Willing to relocate: No
Technologies: Python, FastAPI, Anthropic Claude, TypeScript, Next.js, SQLite, Solidity, Oracle Cloud ARM, Cloudflare
Resume/CV: <a href="https://github.com/visione4906" rel="nofollow">https://github.com/visione4906
Email: crease.tm@outlook.com
I build LLM systems that run in production. The clearest example is live: pick a sector at <a href="https://demo.consentleads.uk" rel="nofollow">https://demo.consentleads.uk and message it the way a customer would. Nothing is scripted. It runs on a free-tier ARM box behind a Cloudflare tunnel, is multi-tenant and has users, and nine scheduled jobs keep it going unattended.
If opt-out detection misses a phrase, the system keeps emailing someone who asked it to stop, and nothing crashes or alerts. So the suppression gate fails closed, and the eval fixtures cover that path and reply triage.
I also wrote claimcheck (MIT, <a href="https://github.com/visione4906/ctaio-claimcheck" rel="nofollow">https://github.com/visione4906/ctaio-claimcheck): give it a document and a codebase and a second agent has to prove every claim against the source with file and line citations, or the build fails. I built it after an outside review of my own writing turned up claims the code did not support.
Looking for AI engineering or AI automation work, remote.