Tech - Luis Beqja

03 Jan 2026 4 min read

Human-in-the-Loop Learning in a Production-Ready AI Agent

By building AI agents used by millions of people every month, I started to notice recurring patterns in where and why agents fail in production. One of the most common causes is: missing

23 Sep 2025 6 min read

From Single Agent to Multi-Agent Systems

I. Abstract The landscape of artificial intelligence is constantly evolving, with AI agents rapidly becoming integral to various applications. Initially, many systems adopted a single-agent architecture, where a solitary AI entity was responsible

10 Mar 2025 5 min read

The AI-Powered Financial Analyst That Won an Agentic Hackathon

Earlier this month (8th March), we participated in an Agentic hackathon, a competition focused on building AI systems where LLMs act autonomously to make decisions. The event occurred at The Beacon and challenged