Smoky Pepper
An AI agent running internal operations for a real restaurant.
The problem
Staff at multiple locations were sending the owner scattered messages throughout the day about things they needed. Supplies running low, questions about prep, requests that would come in at random times or not at all — someone would forget to mention they were out of something until it was too late. The purchasing manager had to track all of it mentally and compile orders from memory.
There was also the operational coordination piece: reminders that needed to go out at specific times ("start the chicken at 2," "check the rice before dinner rush"), training information that needed to reach staff in their language, and process updates that otherwise required showing up in person.
The question: could an AI agent sit in the middle of this and make it organized?
What was built
An AI agent that handles the staff-facing operational layer. The core of it:
Async message coordination. Staff tell the agent what they need whenever they notice it. The agent files each request through an Inventory API into a database. Later, it pulls from the database, organizes by supplier, and sends one structured message to the owner at the right time. Instead of random interruptions all day, the owner gets a single organized update when it's time to order.
Scheduled reminders. Cron-based, owner-configurable, per staff member. "It's 2 PM, make more chicken." "It's 6 PM, check rice for dinner rush." The owner sets them. The agent sends them.
Communication bridging. When non-standard training info or process changes need to go out in Burmese, the agent handles the translation. Day-to-day operations run fine in English and Thai — translation is for the cases where it's needed, not the default.
The architecture: LLM as the communication layer, tool calls to a deterministic database system. The agent talks to people. The database tracks the data. The guardrails keep it from doing anything it shouldn't.
This is staff and management-facing only. There is no customer-facing agent.
The POS system (separate build)
Shane also built the restaurant's POS from scratch — React Native, Expo, Supabase. He evaluated off-the-shelf options and nothing fit. Ugly interfaces. Hard to use. Hard to set up.
Third attempt worked. The result was intuitive enough that staff with zero prior POS experience figured it out on their own with basically no training. Currently in use.
What this demonstrates
A working AI system in a real environment. Not a demo built for a pitch. Real staff, real queries, real operational consequences when something goes wrong. It still runs.
The harness pattern. The agent works because it's restricted. It has access to specific tools and a specific database. It can file inventory requests and send reminders. It can't do anything else. The restrictions are what make it reliable.
Requirements-driven design. The agent handles what staff actually need because the design started with "what do they actually ask for and when" — not with "what's technically interesting to build."