- Published on
Menu nutrition is a unique-hash problem. Deduplicate by brand and dish, cache LLM rows locally, fan out onto one DynamoDB item per store, and keep spend on the unique set — a full marketplace catalog for about four dollars.
Read more →Motions Technologies Canada
Software that moves products from idea to production.
Engineering notes and production software from Motions Technologies — marketplaces, payments, ops platforms, and web apps we ship.
Shipped products
Live deployments across marketplaces, payments, ops, and consumer apps.
Platforms
UmaMeats
Cloud restaurant platform for orders, menus, billing, and payments — the customer-facing SaaS home for kitchens and private cooks.
Visit →Platforms
UmaMeats Customer App
Ordering experience for diners — browse menus, checkout, and track fulfillment across the UmaMeats marketplace.
Visit →Platforms
UmaMeats Driver App
Driver-facing delivery console with live job flow, GPS tracking hooks, and Stripe Connect payouts.
Visit →Operations
UmaMeats Ops Dashboard
Internal operations console for UmaMeats — monitor orders, merchants, and platform health.
Visit →Products
Fortex Pay
Modern payment rails and settlement UX — cloud-native payment experiences for financial workflows.
Visit →Products
Vault
Secure vault product for credentials and protected assets — privacy-first web app on a custom domain.
Visit →Latest writing
Architecture, delivery, and production lessons.
- Published on
Why reactive next-token agents feel amnesiac — and how Mneme applies hierarchical memory, global-workspace bottlenecks, and typed beliefs as the meta-intelligence layer for AetherCrew.
Read more →- Published on
The Motions scientific paradigm — why we treat production AI as structured agency under information and cost constraints, not as unbounded chat.
Read more →- Published on
What we are building with AetherCrew — a supervisor-graph AI team with hard human gates, pay-per-use compute, and a scientific operating loop from trigger to digest.
Read more →- Published on
Technical report notes on UmaMeats Streaming Meeting Factorization (UM-SMF) — a causal factorization theorem and overlapped ASR→policy→TTS algorithm that targets GPT-4o Realtime feel without abandoning auditability.
Read more →
Next step
Book a call
Talk with Motions about platforms, research, or a build — pick a time that works for you.
Subscribe to the newsletter