Engineering leadership · Coding agents · 3D

Leading an AI-augmented build

Kursi Kushti is a free satirical fighting game that runs in the browser. Coding agents wrote most of its code. My part was the brief and its later changes of direction, the gates every change had to pass (taken from my own working rules), a requirement that a separate agent review every change and that disputes be settled by measurement, the decisions only the owner could make, and the final check on a real phone. Reviewer agents did the reviews and agents took the measurements. This post is about how that setup worked, because it is the part I can honestly claim.

The question

What does leading a build look like when most of the code is written by agents? My answer after this project: much like leading people, with less tolerance for vague instructions. An agent does what the brief says, quickly and confidently, so the brief and the pass condition carry most of the weight.

The setup

The game is live at kursikushti.pages.dev. The repository is private; the numbers below come from its notes, tests and build output.

The gates

Every task in the plan ended with the same gate: typecheck, lint and the full test suite pass before a commit. Each phase added a browser check against a written script (load a match, press keys, confirm health drops, save a screenshot) and a demo to me. Later the same gate moved into deployment: a push to main deploys to Cloudflare Pages only after the check and the production build pass.

The path from brief to production Five steps in a row: written brief, agent implements, check (types, lint, tests), browser QA with screenshot and independent review, then push to main which deploys only if check and build pass. A failed gate returns the work to the implementer. Written briefpass condition Agent buildsone task Checktypes, lint, tests Browser QA+ separate review Deploycheck + build first a failed gate goes back to the implementer The path from brief to production Five steps top to bottom: written brief, agent implements, check, browser QA and separate review, deploy after check and build pass. A failed gate returns to the implementer. Written brief, pass condition Agent builds one task Check: types, lint, tests Browser QA + separate review Deploy after check + build fail: back
The loop each task went through. The dashed line is the usual outcome of a failed check or review: the implementer gets the finding and tries again.

When I re-ran the suite for this post it reported 3,852 passing tests in 138 files. That number deserves a caveat: 1,778 of them cover the simulation core, and everything else covers rendering, input, menus, app wiring, audio, the build scripts and the avatar tool. A large count is easy for agents to produce. What mattered more was tests that encode a decision. One review found that the signature combos could not land in open space. The fix had a written pass condition (all four combos land from every gap at which the opener connects, in both directions), and the chosen constant was the smallest value that met it. Another: a live match ended in 37 seconds, so the plan gained a test that AI-versus-AI rounds have a median length between 25 and 50 seconds.

Story one: choosing a model under real constraints

The fighters needed to become 3D models without a cloud service, on a 6 GB GPU, under a licence that allows use from South Korea, where I live, and commercial use later. Those three constraints removed most of the field before any quality test.

ModelOutcome
Hunyuan3DRuled out on licence: it excludes South Korea
TRELLISRuled out: too much GPU memory, and its texture step uses a non-commercial rasteriser
SPAR3DTested: too much GPU memory to run well on 6 GB, and flatter meshes on these drawings
SF3DChosen: about 6 GB, under a minute per fighter, free under US$1M annual revenue

The licence check came first: reading a licence is cheaper than tuning a model you cannot ship. SF3D's own obligations were written into the pipeline notes and shipped (the "Powered by Stability AI" credit line on the About screen, and a NOTICE file).

One variable at a time

The first meshes were flat cut-outs with a faint mirrored face on the back of the head. Instead of swapping models again, the next step was an experiment on one fighter that changed one thing per run: the same cut-out with a transparent background, the same cut-out on white, and a three-quarter view. On white, SF3D produced a round head with hair on the back. A plausible reason is that SF3D removes the background itself, as it does in training, so a white background is closer to what it expects. Nine of the 12 fighters were regenerated on white. The other three kept their earlier builds: one lost its legs on white, one stayed flat either way, and one was the pilot build.

Story two: floating fighters, measured instead of guessed

After the rounder models went in, some fighters looked as if they hovered above the floor. The easy guesses were the model, the normalisation step or the camera. Instead, a diagnostic page posed each skinned mesh and recorded its lowest point.

The measurement found the cause quickly. The rig set a minimum pelvis height of half the model's depth in every pose. That clearance was meant to stop a knocked-down body sinking through the floor, but it was applied while standing too. The rounder models were deeper, so they rose 0.26 to 0.55 units in the fighting stance. The fix scales the clearance with how far the body tilts: zero upright, half the depth lying flat. The change is a one-line function, with tests for upright, flat and in between.

Lowest point in the fighting stanceResult (game units)
Before the fix, rounder models+0.26 to +0.55above the floor
After the fix and later polish, 11 of 12 models-0.107 to +0.003
After the fix and later polish, the deepest model-0.221forward toe dips, open

The last row stays in on purpose: one toe still dips below the -0.15 band we set. A report saying "every fighter stands on the floor" would read better and be slightly wrong.

What I would keep

What I would do differently

Limits

Play it: kursikushti.pages.dev (free, in the browser, no account). Previous post: INT8 made my models 6 to 11 times slower.

← All posts