DuoCode Product · Private Beta

The AI Customer Service Agent Malaysian SMEs Can Actually Trust

Five guardrail layers stop hallucinations before they reach your customer. Native FPX, GrabPay, Boost, Shopee, J&T, and Pos Laju integrations. Pricing that doesn't punish you for being a small business.

DuoCode operator cockpit — live refund approval flow

DuoCode operator cockpit — RM500 refund queued at L5, waiting on one-click approval

The Problem

Why current AI agents don't fit Malaysian SMEs

The leading enterprise AI customer-service products list at USD 0.99 per resolved conversation — built for the Fortune 500. For a Malaysian D2C brand doing 1,000 tickets a month, that is RM 4,500/month minimum, billed in USD, with English-first defaults and no native FPX/GrabPay support.

Generic chatbots hallucinate refund commitments, return windows, and stock numbers. For a small brand, one over-promised refund is a chargeback and a 1-star review — recent public industry incidents have shown those commitments can be enforceable against the operator.

DuoCode is the agent built for the SME that wants AI without losing sleep. Multilingual on day one. Guardrailed at five layers. Priced like a SME tool, not an enterprise contract.

The Moat

A 5-layer guardrail pipeline

Every other AI customer-service product is a single LLM call wrapped in a prompt. DuoCode is a pipeline of five enforcement layers, each catching a different class of failure — already running end-to-end in our operator cockpit.

L1 · Prompt-level filtering

Catches prompt-injection patterns and forbidden language ("ignore previous instructions", unauthorized guarantees) before any LLM round-trip — saving tokens and blocking the attack at the cheapest layer.

L2 · Grounding verification

Every factual claim in the agent's draft must trace back to a tool result or a cited policy chunk. Unsourced claims are blocked or regenerated.

L3 · Schema validation

Every tool call (refund, exchange, address change, ticket) is validated against a strict Zod schema and a cross-call identity check before execution.

L4 · Self-critique

A second LLM pass audits the draft for unauthorized commitments, guarantee language, and tonal misalignment — catching subtle hallucinations the regex layer misses.

L5 · Human-in-the-loop thresholds

Actions above merchant-defined limits (refund above RM200, ≥3 refunds in 30 days, address change after shipment) are queued for the merchant to approve in one click. The tool call never auto-executes.

L5 human approval dialog with full audit trail

L5 — Human approval dialog with refund_id + audit_id receipt

Approved refund with full guardrail trace and citations

Final response — every claim cites a policy chunk or tool result

Evidence

It's already running

Numbers from our internal evaluation harness — 30 YAML test cases (10 happy · 8 guardrail · 7 adversarial · 5 policy QA) against 3 configurations.

100%

Safety rate (full guardrail stack)

+73 ms

p95 latency cost of guardrails

30 / 30

Eval cases passed

5

Independent enforcement layers

Why us

How DuoCode compares

CapabilityEnterprise AI CSLocal rule-based botsDuoCode
Pricing for SMEOut of reachAffordableAffordable
Hallucination guardrailsPartialRule-based only5-layer pipeline
Native Malay / Chinese
FPX / GrabPay / J&TPartial
Human-in-the-loop UXLimitedCore to product
Setup time for SMEWeeksDaysHours
Pricing

Built for SMEs, not enterprises

Hybrid base + per-resolution model. You pay more only when the agent is actually working for you — a quiet month is a quiet bill.

Starter

RM 299/ month

Up to 200 AI-resolved conversations · RM 1.50 per additional · single language · single store

Most popular

Growth

RM 799/ month

Up to 800 resolutions · RM 1.20 per additional · multi-language · up to 3 stores · custom policies · full guardrail cockpit

Scale

RM 1,899/ month

Up to 2,500 resolutions · RM 0.90 per additional · unlimited stores · priority support · custom integrations

Final pricing calibrated against feedback from the first 10 design partners. We'd rather get this right than push a number.

For Investors

Pre-seed · RM 500,000 angel round

We are raising RM 500,000 to take DuoCode from prototype to first 30–50 paying Malaysian SME customers over an 18-month runway.

We are looking for investors who understand SME SaaS economics, have a network in the Malaysian/SEA D2C ecosystem, and are comfortable with a technical, product-led team and a deliberately narrow Malaysian beachhead. In return: exposure to the localized AI agent layer for one of the fastest-growing e-commerce regions in the world.

duocodetechu@duocodetech.com · +60 14-739-8281 · Klang, Selangor, Malaysia