Work

Each case study leads with the constraint, because the constraint is what makes the architecture worth reading. Client code is private. Where a system has a public repo or a published evaluation, it is linked.

Little Bear Foundry

Production · 2026

Nine role-specialized agents deployed beside a customer's live operation, on their hardware

The constraint: The operational data could not leave the building, and a 7B model authored valid triples at roughly a 0% exact-match rate. Both facts are load-bearing. The first ruled out a frontier API in the decision path. The second ruled out letting agents write to the substrate at all, which is why the graph is a read-only derived cache with a projector as its sole writer.

Read the case study

OTTER

Production, in daily use · 2025 to present

The operations platform a 30-employee Florida contractor runs its business on, daily

The constraint: Invoicing rules were not uniform. Each client and each operating division wanted a different document, in a different format, built from the same field data. That is why the document pipeline is a first-class subsystem rather than a report button, and why the permission model goes down to per-user overrides instead of stopping at roles.

Read the case study

Always-on agent runtime

Production · 2025 to present

Roughly 10 scheduled agent workflows running unattended for weeks, with a human approving every state change

The constraint: An unattended agent with write access to production is a liability, not a feature. Everything here is built around that: a default-deny trust ladder, a human approval step on every state-changing action, and no auto-merge anywhere in the pipeline.

Read the case study

Shafer Law Payments

Production · 2026

Card and ACH payments for a law firm, under PCI SAQ-A

The constraint: A replayed Stripe webhook that double-applies a payment is not a bug you apologize for at a law firm, and the audit trail has to survive bar-association review. That is why money is integer cents, invoice numbering is atomic, deduplication is two-layer, and the log is append-only.

Read the case study

Also built

Airport

Public repo · 2025

An AI transaction coordinator for Florida real-estate deals

The constraint: Florida statutory deadlines are counted in business days from a triggering event, and a miscount has legal consequences. The deadline math is therefore its own module with its own tests, not an inline date calculation.

Read the case study

WINRATE

Internal R&D · 2025

An autonomous RFP-response platform with 5-agent orchestration

The constraint: One missed compliance requirement disqualifies an entire bid, so the compliance agent is a gate rather than a reviewer, and a human signs off at each quality checkpoint.

Read the case study