App 10 · FIG. 010

Marii
Send clear quotes with less retyping
Customer Target
South African tradespeople, service businesses and shops that regularly prepare quotes
Status
In progress
Agent Surface B
MCP ReadyModel Context Protocol Enabled
Registered in /.well-known/mcp.json & /llms.txt with deterministic Zod schema validation.
About Product
Marii is being developed to help businesses prepare quotes without typing the same details every time. Keep your products, services and prices in one catalogue, ready for the next customer request.
Choose the items and quantities, check the prices and prepare the quote in a reusable layout. Keep past quotes so you can find them again when a customer follows up.
The planned assistant helps match customer requests to your catalogue and asks when something is unclear. You review the quote before sharing it. Marii is currently in development.
Dual-Surface Execution
Human vs. Agent Flow
Every action in Marii is mapped bi-directionally across Surface A (Visual UI) and Surface B (Programmatic MCP Engine).
- 01Add your products, services and prices.
- 02Start a quote for the customer.
- 03Choose items and fill in missing details.
- 04Check quantities, prices and layout.
- 05Prepare the quote and save it for later.
1. Discovery: Scraper/Agent fetches /llms.txt or /.well-known/mcp.json manifest.
2. Tool Invocation: Executes deterministic Zod-validated tool contracts matching marii 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.