Five systems. Every one of them has something you can check.

A five-role agent loop — analyst, trader, challenger, evaluator, reviewer — paper-trading live market data, which this month measured its own alpha for the first time and spent a week fixing what that number exposed.

A financial agent that gives a household real planning power over its own money — budgets, net worth, cash-flow forecasts, anomaly detection — running unattended against live data from any Plaid-supported bank.

Five replaceable market-intelligence experts — collection, enrichment, novelty, evaluation, signal — wrapping a production pipeline Trader Joe already reads from today, with a ReAct orchestrator built and staged behind them.

25 pipeline stages orchestrated across two GPUs — one serving the local model, one rendering — and two production modes: fully autonomous for trending news — and for the deeply personal work, an AI that interviews a family, live, by voice, to fill in the gaps in their own story.

Wall Street is itself a small multi-agent system: an orchestrator on a lightweight ReAct loop, a connection-recommender, and a data-interpreter, each config-driven down to its LLM tier. The deployed gateway has no model wired into its environment today, so the recommender's deterministic rule path answers every request, while the ReAct loop and the interpreter are built and waiting on that one config entry. Five phases, twenty-four tickets, shipped.