AWS

A unified conversational system for faster, smarter cloud support

AWS chatbot redesign — two iPhone mockups showing the conversational support entry and an active triage flow

Role

Experience Designer

Team

1 Experience Designer

2 Engineers

1 Product Owner

My contribution

Discovery & Strategy

Conversational Design

Chatbot Experience Design

Timeline

24 Weeks

Overview

I co-led the redesign of the AWS chatbot with the AWS Product Manager, driving research, conversational design sprints, and end-to-end delivery. Together, we built a multi-modal support system that reduces customer frustration, surfaces real-time context for agents, cuts handling time by ~20%, and unifies customer journeys across chat, email, and callbacks.

Challenge

Customers hit a sprawling, fragmented support surface. Routing was unreliable, context was missing, and there was no scalable path to a real human when stakes spiked. The chatbot looked smart but rarely closed the loop.

Solution

A multi-modal support layer with a context-rich agent desk, ML-driven routing, and a unified entry point across chat, email, and voice callbacks; the chatbot becomes a triage surface, not a dead end.
AWS support persona portrait — a customer at sunrise next to the AWS chatbot triage screen

Research

Our starting point was to understand who we were designing for, and what pressure they were under when they reached for help.

Key questions guiding discovery

  • Who is using the system, and what pressures are they under?
  • What slows them down today?
  • What do they need to act confidently and quickly in high-stakes moments?

This clarity shaped every design decision and ensured the chatbot directly addressed real customer pain points instead of guesses.

Research artefacts — Quick triage, Personality, Onboarding flow and Speaking style breakdown for the AWS support assistant

Challenge

Where the experience was breaking down

  • Incorrect or irrelevant routing from Lex / Kendra led to user frustration
  • No visibility into a customer's history, past issues, or pages visited
  • No scalable callback or escalation flow
  • Support fragmented across chat, email, and phone with no shared state
Conversational journey audit — current-state map of the AWS chatbot routing, fallbacks and escalation gaps

Wireframes and Designs

Designing a conversational experience that works in the real world. Our sprint focused on two parallel flows running in lockstep.

1. Customer-facing chatbot flow

  • Streamlined onboarding for users in distress (e.g. identity lockouts)
  • Introduced quick actions for technical triage
  • Added a seamless path to Voice Callback
  • Tuned ML routing so it aligned with real user intent rather than keyword guesses

Wireframes 1.0 to 4.0 visualise how users move from first message to resolution.

2. Agent dashboard (parallel flow)

  • Context-rich agent interface surfacing recent errors, pages viewed, and past chats
  • Smart ML routing logic to classify and direct queries before they hit the queue
  • Unified support layer threading chat to callback to follow-up under one record

The result: a single source of truth for agents, and dramatically less back-and-forth questioning during live handling.

Customer-facing chatbot wireframes — onboarding, quick triage, and voice callback handoff screens on mobile
Agent dashboard wireframes — Salesforce-integrated case view, ML routing pane, and unified support timeline

Solution

Problem solved

Context switching and inefficient AWS resource management were eliminated by folding management capabilities directly into the chat interface.

Customer experience

The chatbot became a central hub for cloud operations, enabling users to access diagnostics, monitor resources, and execute commands in real time without jumping between consoles.

Agent efficiency

A context-rich agent interface integrated with Salesforce delivers instant history and signals (e.g. pages visited, recent errors), so agents can resolve issues faster and with less repeated questioning.

Core systems

Bespoke ML routing logic and a unified “support everywhere” entry point across channels, backed by a robust voice callback system.

Final AWS support flow — four iPhone mockups showing entry triage, voice callback handoff, agent context panel, and resolution summary

Next Project

bp