There are many articles and diagrams on agentic loops - I wouldn't attempt to rehash them here. What I'll start with is picking a rough form, explore mapping our SPIRIT framework to see what fits, and what can be improved. Agentic Loop The rough form (and also a rough attempt at linking to our earlier 'TL;DR' term): Context-gathering The results from the previous loop. Loosely maps to learning .…
Taking a break from the usual programming (ha) to revisit an odyssey a jaunt I did this time last year, which I titled "Project 61: Quadjets + RTW!" Lufthansa has been meaning to sunset the A340-600 fleet for a while now, and as of May last year it's assumed that NS25 was going to be it. As such, I toyed with the idea of flying the remaining quadjets (A340, B747, A380 families) in one trip. What…
I embarked on the idea of a 'SPIRIT of Self' during the last week, now I'll like to adapt the same... framework for agentic-conscious teams (or ACT, a new initialism whee ). I also thought of agentic-friendly teams - a warm fuzzy feeling - but I felt that being conscious implies a more intended action of working with and learning best practices about agentic loops. Friendships are good and all,…
While I was tinkering with crafting AGENTS.md earlier this year, I wondered if I could distill my experiences into a set of guidelines - so a loose abstraction of how I think, what I learn, and which to do. When I figured out that the 'read' part of my 'tl;dr' can be a contributory factor to one of the six terms below, it was the further impetus for me to properly write them down for posterity. 😅…
Prolouge Back in late 2024, I did a short talk for an internal tech conference titled "Stories". The idea was to do a non-technical take on where teams can and should go with their software development expertise. In hindsight, I prepared this when I had no exposure to AI-assisted coding agents/output (except the memes LOL) and now, I can't be bothered to check what was considered…