The record
Five case studies and the systems under all of them. Every number on this page maps to a receipt: its measurement method, its scope, and the date it was verified. Open any marked number to read it. No receipt, no number.
A study lands here only after every number in it has been verified against a receipt. Newest first.
Client and internal systems, described rather than shown or linked. Beyond these we have shipped real-time consumer platforms to live users. Every one is whiteboard-able, in depth, on a call.
A client’s document plane, live in production. Email to decision in ~5 seconds, proven end to end. AI document review: vision extraction → deterministic rule engine → human-review queues → e-signature → ERP sync. Multi-tenant, AV-scanned, fully audited.
A production AI memory and identity substrate running since Q1 2026: persistent semantic memory, scheduled reflection cycles, multi-channel (chat, terminal, API), row-level-security firewalls. Recently live-migrated between databases with 12 minutes of downtime. Fail-closed security proven on prod, rollback armed throughout. AI systems with state are a different sport, and we play it daily.
The substrate under a client’s back office and under our own portfolio. Seven specialized agents over an operational warehouse: event bus, per-agent cognitive schemas, governance rules enforced in the database, and honesty contracts in code. The API returns “source unavailable” instead of fabricating when upstream is dark.
Runs our own portfolio: scheduled digest and drift-detection cycles, an AST-validated SQL sandbox, role-level cross-database firewall. The fleet manages itself so the humans can build.
Event-sourced AI applications where state, memory, and consequence persist across long sessions: a deterministic state kernel under the model → full event-sourced history → dozens of normalized domain tables, with a complete test suite and container pipeline. The hard kind of AI: it does not reset between sessions or change without a trace.
Forty-plus live external APIs → multi-source normalization → an algorithmic model layer → ranked, explainable decisions on an automated daily cadence. The same ingest–normalize–decide pattern we put on invoices, claims, market signals, and intake docs.
Complex work run as structured, checkpointed phases: fan-out → adversarial verify → consolidate → resume-on-failure. The control pattern behind agents that finish multi-step jobs without a human in every loop.