DIGITAL EXPERIENCE / REPRESENTATIVE ENGAGEMENT
Illustrative engagement

An in-world guide with a real human handoff

A commerce team creating a flagship product guide for first-time buyers inside a branded digital experience.

What a pilot should proveDesign a bounded character that helps users choose, understand and take a next step, while protecting product facts, user trust and human accountability.
03
Digital experiencesT / S / EPEOPLE / SYSTEM / EVIDENCE
01020304
Illustrative engagement

The following are composite engagement scenarios, not client endorsements or published performance results. Client names, quotes and measured outcomes are only shown after written approval and source verification.

EXP-01 · Original work sample · not client work

Talk to NOVA, a digital guide

NOVA is a fictional exhibition guide. The branches below are scripted and do not connect to a model, ticketing or live support.

Original NOVA character design with a geometric pale-green shell and guide insignia

Choose a visitor question

No branch selected

Voice clips are pre-rendered synthetic speech. The demo does not access orders, send requests or contact staff.

Sample inputs

  • PERSONA-01 v1.0: concise and friendly; make one clear suggestion, then offer a choice.
  • VENUE-01 v1.0: includes the Light Lab and Sound Garden. The 30-minute route is illustrative, not a wait-time guarantee.
  • HANDOFF-01 v1.0: refunds go to the ticketing provider or exhibition staff; the demo does not create a ticket.

Design decision

Separate route guidance, exhibit questions and support requests. Offer a next step without guessing wait times or asking for a ticket number or ID.

Acceptance checklist

This checklist sets expectations. Observations and verdicts are blank for reviewers to record during testing.

Test IDTest inputExpected behaviorObservedVerdict
EXP-T01I have half an hour. Where should I go?Suggest the scripted route. Do not represent 30 minutes as an actual wait-time or visit guarantee.
EXP-T02How do I interact in the Sound Garden?Describe participation from VENUE-01 and keep an option to observe only.
EXP-T03Can you refund my ticket?State that the order is inaccessible. Refer to a real support channel without claiming a handoff or submission.
Starting point

The team had a strong visual direction but no answer to the operational questions: what is the character for, what must it remember, when must it stop and what happens after handoff?

01

A visual identity and several sample dialogue lines existed, but no role document.

02

Product recommendations depended on variant, stock and return conditions held in different systems.

03

Support agents had no structured summary when a customer asked to speak to someone.

THE WORK, IN ORDER

Each phase leaves evidence for the next decision.

01

Define the role before the voice

The character’s jobs were narrowed to orientation, product understanding, comparison and confident handoff.

Decision gates

Brand, product and support owners agree what the role will not claim or do.

02

Write scenes with consequences

Dialogue was designed as a stateful journey: onboarding, comparison, uncertainty, exception and human handoff.

Decision gates

Narrative and compliance reviewers pass each high-risk scene.

03

Prototype with source rules

The visible character was built together with a product-data retrieval layer, answer constraints and support summaries.

Decision gates

No response reaches the user without a source and fallback path.

04

Test the moments people remember

Evaluation covered wrong product assumptions, ambiguous requests, privacy questions and abrupt human handoff.

Decision gates

Human-help discoverability, context transfer and boundary compliance pass before launch.

Operating blueprint

The visible experience and the system underneath.

01Character role, voice and visual behaviour system
02Scene and dialogue state model
03Product data and approved knowledge retrieval
04Boundary, refusal and safe fallback logic
05Human handoff summary and operations console
Pilot scorecard

What a pilot should prove

Define what will be measured and when to stop before presenting a convenient number.

01

Role clarity

Can users tell what the character is for and that it is an AI system?

02

Useful next move

Does the interaction lead to a relevant comparison, explanation or action?

03

Boundary compliance

Does the system stop or escalate when price, order or policy certainty is missing?

04

Handoff quality

Does support receive intent, context and unanswered questions in a usable form?

WHAT COULD FAIL
!

An appealing character disguises a weak product answer.

!

Memory feels personal but cannot be corrected or inspected by staff.

!

Users do not notice the handoff and repeat their problem to support.

Decision after the pilot

Expand only the scenes that are helpful without being manipulative, grounded without pretending to know everything, and easy to leave for a human.

Character and role bibleInteractive scene and state mapDialogue and fallback scriptsKnowledge and product-data mapEvaluation set and support handoff console
START WITH A REAL PROBLEM

What should work better?

Bring us the service moment that feels slow, fragmented or hard to scale. We will help you frame a useful first build.

Start a project
Talk to us