Tag
13 posts tagged Workflow.
A08 5 min read
When the game felt like an errand chain, I asked three AI designers the same neutral question and kept every other opinion, mine included, away from them until they had answered. How that ran, and what a month of building this way taught me.
A07 6 min read
My kids' playtest notes became four pieces of work, each with its own agent, and one agent above them merging the results. Over four days that settled into a team: a root that orchestrates, owners that build, one reviewer, and a single thing that stays mine.
A05 5 min read
Three times in a fortnight I asked the agents to stop building and measure how they worked: a retrospective from the commit log, a pass through three weeks of their own transcripts, and an overnight round that timed every wait. Each time the numbers corrected something I was sure of.
G28 6 min read
One evening I asked the agents for a whole story, and by the next morning Brackenmere had seven main quests, nine side quests, two named bosses and a finale on Lantern Night. Two reviews on paper and a playthrough by a fresh hero did most of the work; my own play found the rest.
A06 7 min read
In one week the agents' running costs became the bottleneck: byte limits that stalled good work, ceremony nobody read, and test suites that ran for hours. I asked where the time was going, and most of the answer was to do less.
G22 6 min read
On 8 October I asked the agents what makes a game feel real, as someone who is not a game designer. One research pass became 27 small pieces of atmosphere and polish, built and merged in a day, and a lesson about how many agents one Mac can carry.
A03 6 min read
Agents add code readily and almost never delete it. Three times in a fortnight I stopped feature work and had the agents audit what they had built, and the lesson was less about the audits than about what happened next: findings only got fixed once they became a queue of small, named jobs.
A04 6 min read
After a week of agents building fast, the repo itself became the bottleneck: too much to read and rules that lived only in prose. One morning made it easy to read; one night turned the golden rules into tests that fail.
A02 6 min read
In the cloud the game ran at under one frame a second, and a test suite that waited in real time fell apart. Stopping the clock fixed it; five days later, an honest bill for tests, reports and handoffs made the whole loop cheaper.
A01 6 min read
The first week of Brackenmere ran as several AI agents at once, each in its own worktree, each starting from one short page that said what was true. A week later the work moved to the cloud, my personal rules moved into the repo with it, and one session became five threads in a day.
G10 6 min read
A week in, Brackenmere ran well on my Mac and I had no idea what it cost anyone else. One day of measuring turned performance from a clean-up job into rules the tools enforce, and an overnight blind review stopped the agents optimising away detail my kids would see.
G09 6 min read
On 25 September every reusable object, light and effect in Brackenmere moved out of the worlds that first used it and into one catalogue, placed by id, measured, and drawn on a page I could browse. The next day a hamlet built only from those pieces showed where the kit was still weak.
G07 5 min read
On 24 September every world in Brackenmere became a piece of data run by one shared runtime. A small dark mine proved a new world needed no changes to the core, and that same evening three agents built a marsh, a frozen temple and a desert tomb side by side.