Aiden Muneath
Director of Applied AI | Agentic Product Factory | Enterprise AI (Pharma / Life Sciences)
- Prompt
- Memory
- Harness
- Loop
- Eval gate
- Ship
- Writer
- Researcher
- Reviewer
- Operator
I lead applied AI at a healthcare marketing agency. Most days I'm building agent systems, the memory, harness, loops, and evals that let AI do real work in a regulated industry, and teaching teammates how to work with them.
This site is where I think out loud. I write about what I'm testing, what broke, and how my view on building with AI keeps changing.
Latest Thoughts
Inside the Agent Loop
One agent run, step by step: where the model decides, where my code decides, and where each guard actually sits.
How I Built the Ask Chat
A chat box that only knows what this site says, and says so when it doesn't.
Hard Rules Inside Claude Code
AI agents are good but never fully predictable. Claude Code mods let me put hard rules around one, and the simple ones cost nothing to run.
How I Use pstack
Lauren Tan's pstack, explained plainly, and where it sits in my own workflow: an outer loop above the coding agents, proof before merge, and a person who says GO.