Unified DuoCode product cockpit showing customer-agent runtime, Gemini audit, and Design Studio debug views

DuoCode AI Customer-Service Operating System

DuoCode helps Malaysian SMEs answer customers from approved evidence, route risky actions to human approval, and inspect every AI run before it becomes a business problem. The customer-agent runtime, Gemini audit lane, and Design Studio debug view all share one product base.

See the Product
Unified product system

Customer support, audit, and Design Studio debugging now share the same base

The latest DuoCode product direction is not a collection of demos. It is one customer-agent foundation with three practical views: the runtime that serves customers, the audit lane that explains what happened, and the Design Studio lane that stress-tests new service workflows in real time.

Provider-backed evidence

Citations come from real OpenAI File Search payloads and are persisted back to Convex for replay, deletion, and audit.

Shadow review, not auto-control

Gemini reviews the audit bundle and flags risk. It never approves refunds, changes tickets, or replaces operator judgement.

DuoCode unified agent cockpit with runtime chat, Gemini audit review, and Design Studio debug panels

Runtime view

Live customer chat, sources, tool calls, order context, and human handoff state for merchant support.

Gemini audit view

Structured review of evidence, citations, tool execution, latency, and risky commitments after each run.

Design Studio debug view

A third product view for testing prototype briefs, artifact runs, delivery state, and support workflows before launch.

Product modules that share one runtime truth

DuoCode is designed as an AI customer-service product first: every module writes back to the same product state, audit trail, source governance, and approval workflow.

Customer
Agent
Tools

Customer-Agent Runtime

A multilingual support agent that streams answers from approved sources, customer context, orders, payments, inventory, and tenant-scoped tools instead of loose prompt memory.

Trace
Risk
Review

Gemini Audit Layer

A shadow reviewer over the Convex audit bundle. It comments on safety, evidence, and handoff quality without answering customers or mutating product state.

Brief
Run
Artifact

Design Studio Debug View

A live product lane for testing website prototype workflows, source-grounded briefs, worker runs, artifact state, and support questions before they become customer-facing features.

Source
Release
Citation

Evidence & Source Governance

OpenAI File Search provides retrieval, while Convex owns source authorization, releases, provider file ids, citations, deletion jobs, and replayable evidence.

Queue
Context
Approve

Human Approval Cockpit

Refunds, data access, account changes, and unsupported policy exceptions route to an operator queue with context, trace, source evidence, and one-click decisions.

Order
Payment
Delivery

SME Integrations

Payments, orders, CRM, POS, inventory, delivery, websites, and internal systems connect through audited custom actions instead of hidden automation shortcuts.

How the product moves from source to answer

Every customer-facing reply passes through source governance, runtime execution, audit, and operator control.

01

Authorize Sources

Policies, product facts, orders, and workflow docs are reviewed, versioned, and indexed before the agent can use them.

02

Run With Tools

The customer-agent streams from File Search and tenant-scoped tools, with identity checks around every business action.

03

Audit The Trace

Convex records messages, citations, tool executions, events, and Gemini shadow review for replayable debugging.

04

Approve Or Improve

Operators approve risky actions, adjust policies, and use Design Studio debug runs to test new workflows safely.

113+ shipped SME workflow references informing the product

Workflow Evidence Library

113+

Workflow References

These shipped references are not the main product. They are the operating evidence behind DuoCode's approved business knowledge, support workflows, Design Studio testing, and SME integrations. Use them to see the industries and workflows the product is designed to support.

Built around product truth, not chatbot guesses

A Malaysia-based software company turning SME support, approvals, and workflow design into one inspectable AI product

DuoCode Technology is registered with SSM Malaysia (Reg. No. 202603062356) and headquartered in Klang, Selangor. The product is built around one principle: Convex owns product truth, OpenAI answers from approved retrieval, Gemini audits in shadow, and operators keep final authority over risky business actions. Our studio delivery track now feeds the same system through Design Studio, where workflows and prototype runs can be tested before they reach customers.

SSM Registered

Reg. No. 202603062356 (LA0087244-A) · Klang, Selangor

Shared Runtime Truth

Conversations, tickets, tools, citations, run events, and reviews in one trace

Audit-First AI

RAG, tool validation, Gemini review, approval queues, and grounded answers

Local SME Fit

English, Chinese, Bahasa Malaysia · FPX, wallets, marketplace workflows

Malaysian SME commerce counter connected by DuoCode AI, payments, inventory, delivery, and analytics workflows
Insights

Read Our Engineering Blog

Deep dives into AI agents, guardrails, and the technology behind DuoCode — powered by a cutting-edge editorial text engine.

Explore Articles

Frequently Asked Questions

Common questions about the DuoCode product system

What does DuoCode actually do?

DuoCode is a multilingual, guardrail-first AI customer-service operating system for Malaysian SMEs. It combines a customer-agent runtime, approved-source retrieval, tool execution, human approval queues, Gemini shadow audit, and a Design Studio debug view for testing new workflows.

What is the 5-layer guardrail pipeline?

It's the core defensible difference of the DuoCode product. Layer 1 catches prompt injections before any LLM round-trip. Layer 2 verifies every claim is grounded in tool results or cited policy. Layer 3 validates every tool call against a strict schema and identity check. Layer 4 runs a self-critique LLM pass for unauthorized commitments. Layer 5 routes high-stakes actions (refunds above a threshold, address changes after shipment) to one-click human approval. The pipeline is already running against live LLMs in our internal cockpit.

Who is the DuoCode product for?

Malaysian D2C and SME merchants doing 200–2,000 customer conversations a month — typically on Shopee, Shopify, or WooCommerce — who can't afford the leading enterprise AI customer-service products at USD 0.99 per resolved conversation and don't trust generic chatbots not to hallucinate refund commitments. Year 1 focus: Klang Valley and Penang.

How is DuoCode priced?

Hybrid base + per-resolution. Starter is RM 299/month (200 resolutions included, RM 1.50/extra). Growth is RM 799/month (800 resolutions, RM 1.20/extra, multi-language, custom policies). Scale is RM 1,899/month (2,500 resolutions, RM 0.90/extra, unlimited stores). All tiers come with the full guardrail cockpit. Final pricing is being calibrated against the first 10 design partners.

Is DuoCode a real registered company?

Yes. DuoCode Technology is registered with the Companies Commission of Malaysia (SSM) under registration number 202603062356 (LA0087244-A) and headquartered in Klang, Selangor. The public site uses the current registered entity name consistently across legal pages, metadata, and structured data.

I'm interested as a design partner / investor — how do I get in touch?

Drop a note via the contact section above or email duocodetechu@duocodetech.com. We're actively in conversation with Malaysian D2C brands about beta access, and with SEA-focused angel investors about the pre-seed round. Live demos of the operator cockpit and the 5-layer guardrail pipeline are available on request.

Talk to DuoCode

Whether you're a SME exploring the AI agent, a partner who wants to integrate, or an investor who wants to see the demo — drop us a note and we'll be in touch within 24 hours.

or