Upgalax
Abstract star-chart constellation map in soft daylight tones, thin pale-gold lines connecting points of light

Research

Notes from the build log.

Specific, technical writing on agentic AI, agent architecture, and product development — grounded in problems we've actually solved, not recycled explainers.

Book a call
FeaturedAgent Safety9 min

Action hallucination in AI agents: what causes it and how we fixed it

Agents that invent tool calls are the most dangerous failure mode in production. Here is the root cause and the guardrail pattern that eliminated it for us.

Read the article
Engineering7 min

Cron-based AI scheduling without loading a full app on every tick

Running an agent on a schedule should not mean cold-starting your entire stack every minute. A lightweight pattern for efficient, reliable agent cron.

Agent Safety8 min

Why tool allowlists matter more than prompt engineering for agent safety

You cannot prompt your way to a safe agent. The strongest safety lever is constraining what the agent can do, not what you tell it — here is the evidence.

Case Study11 min

Building a WordPress AI assistant: lessons from a real deployment

We shipped an AI assistant inside a production WordPress site. These are the integration, latency, and content-grounding lessons that only show up in the real world.

Want these insights applied to your product? Let's talk.

Book a call