Banya LabsBanya Labs/Apps/Leriso POS
In progress

App 08  ·  FIG. 008

Leriso POS logo

Leriso POS

Keep orders and sales moving together

HospitalityPoint of SaleRestaurantsOrdersSales Records

Customer Target

Restaurant, bar and cafe owners, managers and staff in Southern Africa

Status

In progress

Agent Surface B

MCP Ready

Model Context Protocol Enabled

Registered in /.well-known/mcp.json & /llms.txt with deterministic Zod schema validation.

About Product

Leriso POS is being developed to help restaurants, bars and cafes keep orders and sales organised during service. Staff can work from the menu and prices set for the venue.

Enter a customer’s order, check the total and record the payment. Managers can review the sales records and compare them with the money received.

The product focuses on food and drink businesses. It is currently in development.

Dual-Surface Execution

Human vs. Agent Flow

Every action in Leriso POS is mapped bi-directionally across Surface A (Visual UI) and Surface B (Programmatic MCP Engine).

Surface A — Human Ergonomics Flow
  1. 01Add the menu and prices.
  2. 02Enter the customer’s order.
  3. 03Check the order and total.
  4. 04Record the payment.
  5. 05Review sales and the money received.
Surface B — Agentic Machine Execution Rails
Protocol: Model Context Protocol (MCP 1.0)Auth: Bearer banya_ag_...

1. Discovery: Scraper/Agent fetches /llms.txt or /.well-known/mcp.json manifest.

2. Tool Invocation: Executes deterministic Zod-validated tool contracts matching leriso operations.

3. Replay Protection: Enforces Idempotency-Key: <uuid> to prevent duplicate mutations during LLM retry loops.

4. Token Compression: Returns structured, PII-minimized Markdown/JSON stripping all layout noise.