Open

Linkedin

Medium

Instagram

Let's be friends

pranjal.designxvation@gmail.com

Switch to Verizon

faster and easier than ever

Down Arrow

Product Overview


Problem

Verizon wanted more people to switch from other carriers in 2026. But switching took 14 to 16 steps, and people never saw if Verizon was better than what they had. The chatbot just copied the website, so it didn’t help.

The chatbot was scripted (deterministic): it replayed the website journey in chat. Research showed customers expected it to work like the AI tools they already use, so Verizon started experimenting with agentic AI that does the work for the customer.

Challenge

How might we use agentic AI to make switching faster and easier than ever, like a guided, consultative sale?

Solution

Bring your bill. The assistant reads it, matches it to a better Verizon bundle and takes the customer to a ready cart, with 60% fewer decisions.

My role

Senior Experience Designer, one of three, on the Verizon chatbot

I owned the overall journey structure and experience from upper to lower funnel, the new UX and UI patterns, and steering the generative UI. Timeline: 2 months for the switch journey, within a wider chatbot programme.

Leadership

Leading as a design and product leader

  • Set AI design best practices
  • Divided work across 3 designers
  • Led product vision workshops with PMs
Result

10 decisions to 4

per line, to build an order.

40% fewer drop offs

across the switch journey.

8 of 10 customers

found it easier to switch.

The Verizon assistant: screens from the switch journey

Research & Insights


Task analysis

I ran task analysis on UserTesting.com to understand how many steps a switcher goes through, and how they feel at each one. They felt overwhelmed by the choices and unsure whether switching would save them money.

Upper funnelLower funnel
Step 1 of 10: Phone

Switchers only want to know if Verizon beats what they have. Instead they built an order from scratch, faced hundreds of options, and took too long to see if they would save.

The brief

For the PMs the ask was simple: take what is on the web, make it conversational and add widgets. I pushed back: the same steps and legal copy in chat would only make switching longer. I showed the team a journey with fewer choices and manual decisions instead, and asked a harder question.

Scrutinised design problem

If it is already on the web, why would someone use a bot for the same experience?

Faster and Easier


Faster

Start from what they already have

Customers should not be the ones working out the best plan, phone and offer. We looked at starting with questions, a plan comparison or the phone, but each still left the work to the customer. The bill already holds their lines, plan and spend. So the assistant takes their bill and matches it algorithmically to what Verizon offers. That answers the brief: a bot can start from what you have, the website can’t.

→ Bring your bill: from the first message to a placed order, in one conversation.

Upload the bill
1. Upload the bill
What the bill showed
2. What the bill showed
Tell us what you want
3. Tell us what you want
The best recommended bundle
4. The best recommended bundle
Cart
5. Cart
Profile, filled from the bill
6. Profile, filled from the bill
Soft credit check
7. Soft credit check
Delivery
8. Delivery
Agreements
9. Agreements
Order summary and payment
10. Order summary and payment
Order placed
11. Order placed

→ Try it: I built this working prototype with AI, with real LLM replies and the bot and website in sync. Open the assistant and switch to Verizon.

Key Design Decisions


01

Bring the bot back to the core conversation

Early versions saw huge deflection and less conversion as conversations drifted elsewhere. I set a rule: any side question gets a short answer that ends by pointing to the next step, so a detour never becomes an exit.

→ Side question: answered, then straight back to checkout.

AI rules

How the assistant behaves

  • Answer side questions briefly, then point to the next step
  • Keep replies short, one idea per paragraph
  • Never ask for what the bill already shows
  • Recommend first, then let the customer change anything
02

What goes in chat, a widget, a suggestion or the FAQ

Every team asked where content belongs. I set a simple rule that the three designers and PMs used on every screen, backed by research showing content plus a widget beats either alone.

Conversation
Short answers and guidance

“When will my phones arrive?”

Widget
Choices with many options

Colour, storage and plan for each line.

Suggestion
The likely next step

“Continue to checkout”, one tap away.

FAQ
Fixed facts and policies

Trade in rules and broadband facts.

03

Suggestions inside the widget, or outside it

I wanted suggestions inside the widget, next to the choice. But each one needs a backend call, so the widget would load slower. After exploring the options below, we kept them outside.

Suggestions inside the bill upload widget
What we wanted
Inside the widget

Closest to the choice, but the whole widget waits on the backend call.

Suggestions inside the widget, shown as a skeleton while they load
Explored
Inside, behind a loader

The widget shows, with a skeleton where suggestions will arrive. Adds motion while the customer decides.

The widget with no suggestions until they load
Explored
Inside, hidden until ready

Nothing shows until they load, so the widget shifts once they appear.

Suggestions below the widget
Shipped
Outside the widget

The widget loads at full speed, and suggestions follow below it on their own call.

04

Every line in one widget

Setting up phones line by line in chat added a turn for every choice, and an order can have up to 12 lines. Users also preferred a widget to pure conversation when configuring a phone. A widget per line was ruled out too, since each one is a new turn and a new load. So I put every line in one widget, set in place and confirmed together.

05

Designed for empowerment

The assistant recommends the best bundle, but the customer stays in control. They can change any choice, by tapping or by typing. A fixed recommendation was simpler, but switchers need to feel the deal is theirs.

→ myPlan: customers can see every plan and step a line up or down. The assistant shows what they gain or lose and how the bill changes.

06

Bot and web, in sync both ways

The website lagged behind the bot, showing stale steps. I designed them to stay in sync: a change in the bot updates the web, and after an order the web shows next steps. A page refresh after each step was ruled out, because it loses the customer’s place.

→ Phone discovery: the phone the assistant recommends opens on the site’s product page.

→ Cart: a change made in chat or on the site updates both, without a refresh.

→ Order placed: the site moves on to the next steps.

60%

Fewer decisions to build an order

40%

Fewer drop offs across the switch journey

8/10

Customers found it easier to switch

Reflections


Organisational challenges

Two teams, one assistant

Two teams built it in parallel on different stacks, each proving theirs.

Separate revenue counts

Bot and web teams tracked revenue apart, which made cohesion hard.

Rules for legal copy

FCC broadband facts and legal copy needed set formats in chat.

Design challenges

No A2UI standard

Components differed across sales, service and Verizon Business, so we built a design system MCP with guardrails.

Widget, suggestion or chat

Research showed content plus a widget beats either alone.

Limitation

A2UI was experimental

We avoided complex nested components.

What were my learnings?

Fit the format to the decision

Chat for short answers, widgets for real work.

Widgets should not add turns

Actions inside a widget must keep the flow moving.

What we did well?

Started from the bill

Removed the comparing and choosing that lost people on the web.

Built the tooling

Our A2UI tool and the MCP kept screens consistent.

Agreed the voice

Content guidelines made the assistant sound like Verizon.

What is next?

Voice

The same guided journey, spoken.

Let's talk about the next big thing.

design@pranjal-choudhary.com

Linkedin

Medium

Instagram


Copyright ©2026 - Designed and developed by Pranjal Choudhary