Liang Yue
← All work

01AI · Insurtech · Conversational commerce

AI Sales Co-Pilot

WhatsApp-native conversational commerce for Indonesian insurance agents

Period2025 — present

RoleLead Product Strategy & Design

MarketIndonesia

AI Sales Co-Pilot — WhatsApp / AI
WhatsApp / AI
2025 — present
01

Overview

Agents sell on private WhatsApp; the product had to meet them there. I led research, product definition, and design for a WhatsApp Business Co-Pilot that amplifies — not replaces — that habit.

The problem

Quoting lived in Ignite app; trust lived in private chat. AI only inside the app added another switch when momentum was already fragile.

My approach

One agent-initiated journey, a four-layer architecture, and a phased MVP — hand-off, quote, close, signals — aligned through prototypes before build.

02

Contribution

Research · Product · Design

One accountable thread from field insight to a shippable WhatsApp Business Account (WABA) experience — the value it creates for agents, and the three roles behind it.

Value to agents

An always-on sales co-pilot, embedded where agents already sell.

Agents run the full quote-to-close inside WhatsApp — the app their customers already trust — backed by a 24/7 AI assistant. No switching to Ignite, no leaving the chat.

  • 24/7 assistant
  • Native to WhatsApp
  • Zero context-switch

Three roles, one accountable thread

01

Research lead

Built the case remotely — the product is blocked on the mainland — validating the thesis through Meta documentation and a live WABA sandbox.

02

Product strategist

Owned the agent-initiated journey and four-phase MVP, balancing Meta’s messaging rules against agent trust.

03

Experience designer

Turned strategy into WhatsApp Flows, conversational UX, and prototypes the team could ship against.

03

Research

End-to-end WhatsApp sales

WhatsApp is not usable day-to-day on the mainland. I could not shadow Indonesian agents in situ — so I built the case study through evidence I could access remotely. The product thesis: embed quote-to-issue by pairing unstructured NLP/LLM with WhatsApp Flow’s structured UI — not one mode alone.

Why are we doing this — chat-first market reality, the WhatsApp Flow opportunity, and the unstructured vs. structured interaction modes.
Scroll to read →
Market validation — Lifepal and Meta WhatsApp Flows precedents, plus Redbus, JioMart, and HDFC Bank industry benchmarks.
Scroll to read →
04

Product

Scope & phases

North star: empowerment without displacement. Phases breakdown, User flow, and WABA screens below — aligned to the WhatsApp MVP programme for Indonesia.

Phases breakdown across four phases, and the user flow from lead acquisition to policy issued.
Scroll to read →

Live demos · test phase

In-chat performance inquiry
Marketing assets generation
Conversational quoting flow
05

System design

Four-layer architecture

From omni-channel gateway to MCP capabilities.

Four-layer system architecture — omni-channel integration, hybrid orchestration & runtime, smart MCP routing, and MCP servers.
Scroll to read →
06

Outcome

A coherent WhatsApp Co-Pilot for Indonesia — culturally grounded, architecturally explicit, ready for phased ship.

Next case

02 · Ignite - Insurance Sales Platform

Reimagining an end-to-end insurance platform for Southeast Asia