BundleBox Survey

Turning a home walkthrough video into a move-ready inventory with AI

Turning a home walkthrough video into a move-ready inventory with AI

AI surveys that turn home walkthrough videos into a priced-ready inventory, whichever of four ways the home is surveyed.

BundleBox Survey dashboard behind the generated inventory for a surveyed home

Four ways to survey a home, one inventory at the end

Role

Product Designer

Skills

AI Product Design · Interaction Design · Systems Design

Timeline

2 Weeks

Team

2 Designers

BundleBox Survey is an AI-powered virtual survey product for moving companies. Instead of sending an estimator to every home, movers can survey a move four ways: a self-recorded video, a live assisted video call, an on-site visit, or an uploaded video. In every case, AI turns the footage into a room-by-room inventory with volume and weight.

We designed the product end to end. The work covered survey creation, AI transcript and inventory review, the inventory workspace, customer-facing inventory review, automated customer communication, and the dashboards teams use to run surveys at scale.

Problem

Surveys were slow to schedule, easy to abandon, and ended in retyped data

Surveys were slow to schedule, easy to abandon, and ended in retyped data

Accurate moving quotes depend on knowing what’s in the home. Traditionally, that meant a surveyor driving to every address, walking each room and counting items by hand. Early virtual surveys removed the drive, but they produced unstructured video that someone still had to watch and transcribe into an inventory.

Every survey type followed a different process, and customer follow-up was manual. Surveys stalled when customers didn’t record, links expired unnoticed, and the inventory that finally came out lacked the details crews and estimators actually needed, such as packing, fragility, disassembly and crew instructions.

Time sink

A single in-home survey cost an estimator approximately 2 hours between travel, the walkthrough and retyping the inventory.

Dead-end data

Video surveys captured the home but not the data. The footage still had to be manually converted into items, volume and weight before anyone could price the move.

Target Users

Surveyors who turn homes into data, and the customers on the other side of the camera

Surveyors who turn homes into data, and the customers on the other side of the camera

The primary users are surveyors and estimators at moving companies. They schedule and run surveys, review AI-generated inventory, and hand accurate data to sales and dispatch. Office admins oversee survey volume and follow-ups across the whole team. Customers are secondary users: they record their homes, join video calls, and review their inventory before signing.

Role

Surveyor at a 20 truck mover, running 40 surveys a week.

Goals

Survey more homes without driving to them, and trust the inventory enough to price from it.

Frustrations

Customers who never record, scrubbing through long videos, and inventory that misses packing and fragile items.

Tools today

Phone, video calls, spreadsheets, manual texts and emails.

Problem Statement

How might we let movers survey any home remotely, in whatever format the customer can manage, and turn that footage into an inventory accurate enough to price and dispatch from?

How might we let movers survey any home remotely, in whatever format the customer can manage, and turn that footage into an inventory accurate enough to price and dispatch from?

Discovery Insights

Where surveys stalled and where inventory broke down

Where surveys stalled and where inventory broke down

To understand why surveys stalled and why inventories weren’t trusted, we mapped every survey type from creation to confirmed inventory. We did this through interviews with surveyors and admins, and a review of real survey footage.

We spoke with 8 surveyors, estimators and admins across 3 moving companies and reviewed over 25 recorded surveys. The goal was to find where customers dropped off and what an inventory needed to be usable downstream.

Key Insights

No single format fits every customer

Some customers want to record on their own time, others need a live call, and some homes still need an in-person visit.

Surveys died between invite and submission

Customers rarely refused a survey. They forgot, ran out of time, or let the link expire.

An item list isn’t an inventory

Crews and estimators needed volume, weight, who packs each item, fragile, high-value and bulky flags, disassembly needs, and crew notes.

AI output needed a receipt

Surveyors only trusted a detected item when they could jump to the moment it appeared on video.

These insights shaped a core design principle:

Be flexible in how a survey is captured, consistent in what it produces, and make every AI-detected item traceable to the video.

Be flexible in how a survey is captured, consistent in what it produces, and make every AI-detected item traceable to the video.

Strategy & Key Decisions

Design decisions to scale surveys without losing accuracy

Design decisions to scale surveys without losing accuracy

Based on research into how surveys were run and where they broke, we made two structural decisions that shaped AI Survey.

Create survey panel with four capture modes: self virtual, assisted virtual, on-site and upload video

Decision 1: One survey, four capture modes

Decision 1: One survey, four capture modes

Survey creation became a single flow where the surveyor picks a capture mode (self virtual, assisted virtual, on-site or upload video). Customer details, move details and the outgoing SMS or email adapt to that mode. However the survey is captured, it ends in the same transcript and inventory.

Why: Customers get the format that works for them, while surveyors and downstream teams always receive the same structured output.

Inventory summary and room-grouped item rows with packing, flags and crew notes

Decision 2: Inventory as an operational document, not a list

Decision 2: Inventory as an operational document, not a list

The AI inventory was designed as a working document. Items are grouped by room, with quantity, volume, weight, packing responsibility, handling flags and crew notes. A live summary shows totals per room, and the inventory can be exported as CSV or PDF or sent to the customer to review.

Why: An inventory only saves time if estimators can price from it and crews can work from it without re-entering anything.

Risks & Trade Offs

Balancing automation, accuracy and customer trust

Balancing automation, accuracy and customer trust

AI over-trust

Detected items could be wrong or assumed. Every item links to a video timestamp, inferred items are labelled (for example, “Not mentioned by customer, considered moving by default”), and surveyors can switch models and retry processing.

Automation vs noise

Automated reminders could quickly become spam. Each message is tied to a specific trigger with defined timing, such as 24 hours after invite or 24 hours before link expiry. Templates are editable and can be sent as a test first.

Team visibility vs focus

Admins needed an organisation-wide view while surveyors needed their own queue. The dashboard switches between organisation and personal scope, and every inventory edit is logged in Activity with who made it.

Solutions

An AI survey platform from first invite to confirmed inventory

An AI survey platform from first invite to confirmed inventory

Create a survey in any format

Create a survey in any format

One create flow covers all four survey types. Scheduling, customer details and the outgoing SMS or email adapt to the mode, and the message can be edited in place.

Create survey screen for a self virtual survey with customer, move and message details
Create survey form for a self virtual survey, filled in with customer, move and SMS details

Self virtual survey, filled in

Create survey form for an assisted virtual survey with a scheduled call

Assisted virtual survey

Create survey form for an on-site survey with a scheduled visit

On-site survey

Calendar overlay for picking a survey date and time

Calendar overlay

Create survey form with the outgoing message switched to email

Switching the message to email

From video to transcript to AI inventory

From video to transcript to AI inventory

AI transcribes each video by room and detects items with timestamps. Surveyors can review what was said, see what was detected, and jump to any moment in the footage.

Transcript and AI inventory side by side, with each item linked to the video
Survey tab showing several surveys for one customer

Survey tab with several surveys

Survey tab for an assisted virtual survey

Assisted virtual survey

Survey tab processing an uploaded video

Processing an uploaded video

Room-by-room transcript next to the AI-generated inventory with video timestamps

Transcript and AI inventory

Send reminder modal for a customer who has not recorded yet

Send reminder modal

Inventory workspace

Inventory workspace

A room-grouped inventory with volume, weight, packing responsibility, handling flags and crew notes. Totals update live and the inventory exports as CSV or PDF.

Inventory tab with summary, room breakdown and room-grouped items
Inventory tab with room-grouped items, quantities, volume, weight and flags

Inventory tab

Inventory summary expanded with breakdown by room

Summary expanded

Crew instructions and internal notes on an inventory item

Crew instructions and internal notes

Video modal jumping to the moment an item appears in the survey footage

Video modal

Inventory zero state before any video is processed

Zero state

Inventory filter dropdown

Filter dropdown

Customer inventory review

Customer inventory review

Customers review their room-by-room inventory on any device before signing the Bill of Lading, which catches disputes before moving day.

Customer inventory review on web and mobile
Customer-facing inventory review on web with stats, flag filters and room-by-room items

Customer inventory on web

Customer-facing inventory review on mobile

Customer inventory on mobile

Close-up of fragile, bulky, high value and disassembly flag filters on inventory rows

Flag filters close-up

Communication hub

Communication hub

Automated SMS and email for every survey stage, including invitations, reminders, expiring links, rescheduling and submission. Each message uses editable templates, variables and a branded sender identity.

Communication hub overview of automated email and SMS triggers per survey type
Communication hub overview of automated triggers for each survey type, with email and SMS toggles

Triggers overview

Communication hub message templates

Templates

Communication hub variables used inside message templates

Variables

Sender identity settings for outgoing email and SMS

Sender identity

Send a communication flow with a filled-in message

Send a communication

System foundations supporting scale and reliability

System foundations supporting scale and reliability

These screens cover the rest of the product: dashboards, survey and customer management, and an activity trail that keeps teams in sync.

Admin dashboard with organisation-wide survey metrics

Admin dashboard

Surveyor dashboard with a personal survey queue

User dashboard

Needs Attention table listing surveys that are stalled or expiring

Needs Attention table

Survey list with status, survey type, surveyor and created date columns

Survey list

Survey details with customer, move stops and Zillow property data

Survey details with Zillow property data

Activity log of survey and inventory changes with notes

Activity log

Customer list and card views

Customer list and card views

Impact

84%

Fewer in-person surveys

Or 26 hours of estimator drive time saved per week.

4.3 mins

From video upload to generated inventory

Time from a customer’s upload to a room-by-room inventory with volume and weight.

93%

Survey completion rate

Completion after automated invitations, reminders and expiring-link nudges.

4

Survey modes, one inventory

Self virtual, assisted virtual, on-site and uploaded video all produce the same room-by-room inventory.

Learnings

AI output needs a receipt

Surveyors adopted AI-detected inventory only when every item could be traced back to the video and edited with a visible history.

Flexible input, consistent output

Supporting four capture modes only worked because they all converged on one inventory model. The flexibility is upstream, and the structure is downstream.

Please reach out if you have any questions. Currently open to new opportunities.

© 2026 | Pranav Shinde.

Please reach out if you have any questions. Currently open to new opportunities.

© 2026 | Pranav Shinde.

Please reach out if you have any questions. Currently open to new opportunities.

© 2026 | Pranav Shinde.

Please reach out if you have any questions. Currently open to new opportunities.

© 2026 | Pranav Shinde.