Joy
Joy is my agent. It runs a thousand jobs overnight, files the evidence on our shared board, and only wakes me for the decisions that are actually mine.
home / reel
Thirteen systems, twenty-five seconds each.
Product films, not build logs: each one shows what the system does with its own screens, numbers, and copy. Sound on.
Cyrus-v2
Cyrus-v2 turns a backlog into agent sessions: five coding agents behind one relay, every token metered, a scheduler that knows when to stop, and a PM agent that grooms the board while you sleep.
SecondHome
SecondHome reads twenty county sources, keeps the source on every field, scores each lead with a formula you can inspect, and writes the reason to call before anyone dials.
Store-close reconciliation
Store-close reconciliation for a multi-store retailer: fifteen deterministic parsers, one model lane that can only propose, a review queue for every proposal, and two approval gates locked in code. June close: 295 of 315 checks, zero open amount differences.
ReCap Budget
ReCap Budget read the whole receipt: a CNN gate, Textract, and a GPT-3 classifier fine-tuned on 40,000 items turned 'CLGT TP $2.89' into Oral Hygiene, so the advice could be about what you actually bought.
Fit & Flourish
Fit & Flourish ran a creative loop that generated ad variants, killed the losers daily, and moved the budget, but nothing spent a dollar until a person approved it in Discord. 40,000 waitlist leads at 29 cents each.
GBrain and the Living Atlas
GBrain: the memory behind Joy. About 1,400 compiled pages and 6,800 source chunks on pgvector, every fact cited to a source with a time boundary, nightly updates that say what was learned, and a Living Atlas that can lend a bounded window into memory without handing out a credential.
Splice
Splice: write a YAML contract, let a model write exactly one function, run it in a sandbox, check the examples, cache it. One LLM call, thousands of executions.
VibeTest
VibeTest: describe your audience as a blueprint, let math build fifty personas with the exact split you asked for, run twenty interviews at once with the leading questions rewritten, and get consensus, variance, and outliers, labeled as a hypothesis, not a finding.
Cortex
Cortex: wear a recorder all day, let VAD cut it into segments, let a cheap model decide which ones deserve cloud transcription, extract twelve categories with source timestamps, and let Joy file the tasks.
Arcade cabinet
An arcade cabinet that's really a smart-home device: favorites first, joystick plus two buttons, and every setting, game, theme, and repair handled from the server by an agent you talk to in plain language. Cut the cable and the games still run.
Wake-word training and the LED mask
A helmet with an LED face: it reads your expression and emotes back, and it wakes on 'Hey Joy' with a model trained on nothing but synthetic speech: three voices, three phrasings, three rates, thirteen near-miss negatives, noise and jitter on top. Offline, on a handheld PC, on a convention floor.
Cyrus, first generation
Cyrus, first generation (2023): an event-driven multi-agent framework on the original LangChain, with a state-machine flow engine, one tool-calling contract across GPT-4, Gemini, Claude, and Bedrock, cost on every call, a shared workspace, a VS Code extension, and a vector DB with no server. It worked the week AutoGen launched.