More memory cannot tell an agent what a system is supposed to do. This essay starts with the rules of the place the agent is entering, the people affected, and the ways its actions can be corrected, escalated, or stopped.
Problems are designed
These are examples of my projects, from games to tools and system demos. They show how I use multi-agent orchestration and my own models to bring ideas to life.
- VarsityApexA prototype that turns the files schools already produce into portable, attributable records.

- CoalitionAn escape game in one HTML file, where allies work in parallel and dice force you to plan around the people who fail to deliver.

- Cap BuffetLets a league try a salary cap system before adopting it, with 18 mechanics as swappable modules.

- Oregon HS Tennis Power RankingsRatings for every Oregon high school team from four years of results. The OSAA seeds its 2027 dual team championship from them.

- Occupant IndicesDaily price and activity indices for the AI economy, built from public data.

- MalloThe first advanced stats for pesäpallo.

- Play To ClinchTeam tennis on one rating scale, played point by point.

- ViperballAn invented gridiron sport with a probability engine and a 280 team universe.

- SuperInningsBaseball as one continuous 27 out half, documented in 140+ decision records.

- You Go FirstA matching model for dating apps built on game mechanics.

- BeachwaveLive audio rooms on ATProto. Fork it and run your own.

- Pensulo CardsA deck of 46 cards for getting past creative block.
Drag the marker along the techniques, or use the arrow keys.
Under the hood
These models use calculations and data from their source projects, checked against the originals. Coding agents brought them into the browser.
Oregon high school tennis rankings
Win-loss records ignore who you played and count every flight the same, so a coach could stack a lineup to look better. My flight-weighted score weights the eight flights from 1.00 down to 0.10, so depth counts and stacking stops paying. The Power Index blends it with an RPI-style strength of schedule, and the OSAA now seeds its dual team championship from it.
PI = 0.65·APR + 0.25·FQI + 0.10·oGS
FQI = (Σ flight_score·opp_strength + 5×0.5) / (duals + 5)
Drag a bar to change a flight’s weight. All 121 ranked 2026 boys teams re-rank.
Top 12 by Power Index, with each team’s change from the real weights.
Viperball kick decisions
Viperball has six downs to gain 20 yards, and the ball moves by running, lateral chains, and kick passes. A live-play drop kick is worth 5 and a place kick 3. Every rule creates a strategy, so on a late down the coach weighs both kicks against going for it.
distance = (100 − field position) + 10
drop kick EV = 5 × P(drop) place kick EV = 3 × P(place)
Drag the marker to change the kick distance. Highlighted line: drop kick. Plain line: place kick.
The call: GO FOR IT
O27 college prospects
In O27, a prospect’s box-score grade and actual ceiling are different things. Each player has a hidden ceiling and a fixed lens on it, so the grade you see is ceiling times lens. Two scouting reports estimate that ceiling with their own errors. I kept the lens fixed through college: a hidden gem can still look ordinary when draft day arrives. The decision is whether to trust the box score or two imperfect scouting reports. I explain the model in the development write-up.
shown = round(ceiling × lens) lens 0.40–0.95
growth = min(rate × ceiling, cap) cap 15 → 4
scout = ceiling ± fog fog 7–31
Pick the one you’d draft, then sign them and the lens drops. The plain bar is the box score. The highlighted bar is the real grade.
Play To Clinch point engine
College tennis is a team sport: three doubles matches make one point, six singles matches are a point each, and the first team to four wins. My engine plays every point, so a small edge per point adds up over a match.
P(server wins rally) = logistic(0.9·Δrally + 0.36 first | 0.10 second + …)
Drag to change the skill gap, on the game’s 20-80 scale.
Play To Clinch high school careers
The first high school model put seniors in 85.7% of No. 1 singles spots. I compared that with six seasons of Oregon boys tennis, then rebuilt development around starting ability, career peak, annual growth, and actual playing time. JV matches count for half the exposure of varsity, so five freshmen with the same ceiling can end up with very different careers.
gain = year's budget × playing time
playing time: bench 0.55 · full JV 0.81 · varsity 1.00
Five freshmen from one generated roster, all with the same ceiling. Dashes mark each career peak. Change their playing time.
Who plays No. 1 singles, by grade: Oregon boys over six seasons, and my sim before and after the change.
You Go First match score
Scores are asymmetric. What you want, 10 chips across five traits, is scored against what they are, a behavioral quiz: 0.7 × alignment + 0.3 × temperature. Move the chips and both scores change.
score = 0.7 × alignment + 0.3 × temperature
temperature = max(0, 100 − 2 × |quiz gap|)
You Go First: a week of matching
Swiping makes attention free, so a like tells you nothing and a few profiles get most of them. Everyone gets 15 picks a week in three tiers, and the other person sees the tier.
These are the app’s 14 test profiles in its simulator. Click a person to see who they picked.
The textbook stable-matching algorithm pairs all 14, but only by assuming everyone knows everyone and can propose without limit. Fifteen picks a week matched 12 by week 2.
Source: heypbj/src/lib/stableMatchingSimulator.ts and src/data/mockSimulation.ts, default seed.
Context-Aware Agents: Designing for Alignment in AX
February 23, 2025
Agents operate within existing systems of rules, responsibilities, and decisions. When those relationships are missing from their context, agents can complete a task while misunderstanding its purpose. I examine how context, authority, and oversight shape agent behavior, and why judging task completion alone misses important consequences.
Building Coalition with AI agents exposed a recurring problem: game rules, interface copy, and narrative kept getting mixed together. I developed a content schema that gives each a defined place, so agents can work on dialogue, game mechanics, or interface language while preserving the relationships between them. The schema is available as a standalone package.
When an agent should ask you
January 15, 2026
I adapted Judgment Routing for the person giving an agent a task. Uncertainty, stakes, authority, and novelty help route an action to execute, verify, approve, or refer. The person sets the limits, and each action leaves a receipt showing which permission allowed it.
What counts as proof that an agent did its job?
July 23, 2026
A tool call proves an attempt, and a provider response establishes only what that provider confirmed. I separate the request, approval, attempted action, acknowledgment, and observed result so a missing confirmation stays visible rather than turning into a generic success message.