Live in Production

Autonomous AI Agent for Conversational Commerce

A production-grade WhatsApp ordering system powered by frontier LLMs. Processing real customer orders 24/7 with natural language understanding, multi-step workflows, and integrated payments.

130+
Menu Items
<5s
Avg Response
24/7
Autonomous
1M
Context Window

System Architecture

End-to-end AI pipeline from WhatsApp message to POS terminal, fully autonomous with zero human intervention.

Input Layer

WhatsApp Channel

Receives customer messages via WhatsApp Web protocol. Supports text, images, and location sharing. 500ms debounce for multi-message batching.

AI Brain

LLM Agent Runtime

OpenClaw agent framework with GPT-5.4 primary model. 578 lines of behavioral rules, multi-model fallback chain, per-customer session memory.

Processing

Order Evaluator

State machine validates order completeness. Handles draft/final queue, entity normalization, fulfillment routing (delivery, pickup, dine-in).

Integrations

Payment + POS

Doku QRIS generation with auto-verification polling. Pawoon POS sync for kitchen display. Supabase for persistent storage and real-time dashboard.

Prompt Engineering

578 Lines of Production Agent Rules

Comprehensive behavioral specification including: 7-step ordering flow, one-shot order detection, alias parsing for 130+ menu items, ambiguity resolution, upsell logic, idle conversation management, prompt injection defense, and time-based personality adaptation. The agent reads customer profiles, order history, and live menu schema on every interaction.

Order Processing Pipeline

From natural language to kitchen display in under 30 seconds.

WhatsApp Message

Customer sends natural language text

LLM Processing

Intent detection + entity extraction

Order Validation

State machine + queue evaluation

QRIS Payment

Auto-generated QR + verification

POS + Kitchen

Pawoon sync + courier dispatch

Live System in Action

Real conversation with the AI agent processing an actual delivery order end-to-end.

AI agent conversation: order placement, NLU parsing, upsell suggestion, fulfillment selection
Step 1-4: NLU parsing, entity extraction, upsell, fulfillment
AI agent: location processing, delivery fee calculation, QRIS payment QR generation
Step 5-7: Location calc, fee compute, QRIS generation

Model Migration to MiMo

Replacing GPT-5.4 with Xiaomi MiMo as the primary inference model for all conversational AI processing.

Current

GPT-5.4

OpenAI Codex provider with Claude Opus 4.6 fallback. High cost, rate-limited, no local inference option.

Migrate
Target

Xiaomi MiMo V2.5

Flagship reasoning model via MiMo API Platform. Direct integration with OpenClaw agent runtime. Lower latency, competitive pricing.

AI Capabilities in Production

Every capability listed here is actively running in production, processing real customer orders daily.

NLU

Natural Language Understanding

Processes casual Bahasa Indonesia including slang, abbreviations, and typos. "kopsu 2 less sugar" is parsed correctly.

Intent

Multi-Intent Detection

Identifies ordering, browsing, complaints, reservations, and info queries from a single message.

Extraction

Entity Extraction

Extracts items, quantities, names, table numbers, fulfillment method, and payment preference from free text.

Memory

Session + Profile Memory

Maintains multi-turn conversation state and remembers returning customer preferences across sessions.

Tools

Function Calling

Executes backend scripts for distance calculation, payment generation, order history lookup, and menu queries.

Safety

Prompt Injection Defense

Explicit rejection rules for manipulation attempts. Restricted file access and command execution boundaries.

Projected Token Consumption

Estimated MiMo API usage based on current production traffic patterns.

~22K

Tokens per Order

Average context bootstrap (system prompt + menu schema + customer profile + conversation history) per interaction.

128K

Max Output Tokens

Configured maximum output for complex multi-tool responses including order state writes and payment generation.

5-7

Turns per Order

Average conversation length from greeting to payment confirmation. One-shot orders complete in 3 turns.

1M

Context Window

Full session context including conversation history, tool outputs, and agent memory for complex multi-turn flows.

Technology Stack

Xiaomi MiMo V2.5 (target) GPT-5.4 (current) Claude Opus 4.6 OpenClaw Runtime Node.js Next.js 16 Supabase WhatsApp Web Doku QRIS Pawoon POS Express.js React 19

Ready for MiMo Integration

This system is architecturally prepared for model swap. The OpenClaw runtime supports any OpenAI-compatible API endpoint.

Try the Live System