Jesal.AI

Inventory Efficiency Report: Turning Supply Chain Chaos into Confident Decisions

How I designed a command-center interface that reduced issue detection time by 60% and prevented $2.1M in stockout losses for 3,000+ Walmart planners

Overview

Retail supply chain planners at Walmart were drowning in data but starving for insights. Managing billions in inventory across 150+ distribution centers and 4,000+ stores, they faced a critical problem: they couldn't see the risks until it was too late.

I led the design of the Inventory Efficiency Report—a command-center interface that transformed fragmented legacy systems into an intelligent, exception-based decision platform. The solution unified 6 data streams, surfaced only what mattered, and explained the "why" behind every flag.

TL;DR

The Problem

Fragmented inventory data made it impossible for planners to detect stockouts before they impacted revenue.

The Insight

Planners didn’t need more raw tables. They needed prioritized risk signals they could act on immediately.

The Solution

I designed a unified command center that highlighted critical anomalies using predictive thresholds, explainable scoring, and drill-down diagnostics.

The Impact

The redesign reduced issue-detection time by 60% and helped prevent roughly $2.1M in stockout losses.

TL;DR

The Problem

Fragmented inventory data made it impossible for planners to detect stockouts before they impacted revenue.

The Insight

Planners didn’t need more raw tables. They needed prioritized risk signals they could act on immediately.

The Solution

I designed a unified command center that highlighted critical anomalies using predictive thresholds, explainable scoring, and drill-down diagnostics.

The Impact

The redesign reduced issue-detection time by 60% and helped prevent roughly $2.1M in stockout losses.

60%
Reduction in time to detect critical issues
(4 hours → 90 minutes)
$2.1M
Stockout losses
prevented
in Q1 post-launch
6 → 1
Data streams unified
into single dashboard
Within 3 Months
40%
Increase in
tool adoption
(45% → 85%)

60%
Reduction in time to detect critical issues
(4 hours → 90 minutes)
$2.1M
Stockout losses
prevented
in Q1 post-launch
6 → 1
Data streams unified
into single dashboard
Within 3 Months
40%
Increase in
tool adoption
(45% → 85%)

Duration

3 months

My Role

Lead Product Designer

Team Role

2 Product Managers
2 BI Developers
2 Data Scientists
3 Engineers

Target Audience

Inventory Planners,
Retail Operations Teams

Scope

Research, UX, UI, Prototyping, Testing

Tools

Figma
Excel
Highcharts
Jira

Industry

Inventory planners
Retail operations teams

Platform

Web (Desktop-first)

Users Impacted

300+ daily active planners

Inventory Managed

$2B+ across 150+ DCs

The Challenge

Fragmented Systems, Hidden Risks

Retail supply chain planners at Walmart managed billions in inventory across 150+ distribution centers and 4,000+ stores.

Yet they struggled with a critical problem: they couldn't see the risks until it was too late.

I spend 4 hours a day just trying to find which SKUs need attention. By the time I figure it out, it's often too late. I need the system to tell me what matters and why it matters—not show me 10,000 rows of data.

Lisa M

— Category Manager, Walmart (User Research Interview, Week 2)

The Core Problem

Fragmented

Reactive

Opaque

Overwhelming

The Stakes Were High

Stockouts

Empty shelves = Lost sales

A single out-of-stock event could cost $50K-$200K depending on the category. Disappointed customers lead to lasting brand damage.

$50K-$200K cost

Stockouts

Empty shelves = Lost sales

A single out-of-stock event could cost $50K-$200K depending on the category. Disappointed customers lead to lasting brand damage.

$50K-$200K cost

Overstock

Capital tied up and operational waste

Excess inventory consumed warehouse space, tied up working capital, and increased markdown risk. Overstock also reduced flexibility when new shipments arrived.

Warehouse Gridlock

Delays

Supply chain disruptions

One missed delivery creates ripple effects—impacting downstream distribution, store replenishment, and ultimately customer experience.

Ripple Effects

User Pain Points Quantified

User Snapshot:
The Inventory Planner

Meet Sarah, an inventory planner responsible for $40M in inventory across three regions. She spends much of her day reconciling data from multiple systems and reacting to emerging problems.

Her biggest challenge isn’t making decisions — it’s finding the right problems to solve first.

Responsibilities

Maintain optimal stock levels (95% fill rate)

Minimize excess inventory costs

Coordinate with logistics on transfers

Metrics Tracked

Stockout Rate

Risk Monitor

Weeks of Supply

Efficiency

Forecast Accuracy

Reliability

Forecast Accuracy

Reliability

A Typical Day

8:00 AM

Check Emails

Scanning for urgent stockouts

10:00 AM

Data Consolidation

Pulling reports from 3 systems

10:00 AM

Data Consolidation

Pulling reports from 3 systems

2:00 PM

Analysis

Pivot tables in Excel

4:00 PM

PO Creation

Place rush orders and adjust replenishment plans

4:00 PM

PO Creation

Place rush orders and adjust replenishment plans

Key Insight

“I spend 80% of my time finding the problem and only 20% fixing it. If I could see risk immediately, I could prevent half these issues.”

Responsibilities

Maintain optimal stock levels (95% fill rate)

Minimize excess inventory costs

Coordinate with logistics on transfers

Metrics Tracked

Stockout Rate

Risk Monitor

Weeks of Supply

Efficiency

Forecast Accuracy

Reliability

A Typical Day

8:00 AM

Check Emails

Scanning for urgent stockouts

10:00 AM

Data Consolidation

Pulling reports from 3 systems

2:00 PM

Analysis

Pivot tables in Excel

4:00 PM

PO Creation

Pulling reports from 3 systems

Key Insight

"I spend 80% of my time finding the problem and only 20% fixing it. If I knew where to look immediately, I could prevent half these issues."

Success Criteria

To solve this problem, the design needed to shift the tool from reporting data to directing decisions.

We defined three success criteria.

Speed to Insight

Reduce the time it takes to identify a critical stock risk from hours to minutes.

Time-to-Detect

< 5 mins

Decision Confidence

Enable planners to trust system insights without needing to manually validate raw data.

Trust Score

4.5/5

Workflow Adoption

Make the tool the planner’s primary workspace, replacing the daily spreadsheet ritual.

Daily Active Usage

> 85%

Process Overview

The design process focused on understanding how planners actually worked before proposing new solutions.

01
Understand System
02
Define Truth
03
Make Exceptions Visible
04
Design Intelligence
05
Build Decision Paths
06
Validate
07
Iterate

01
Understand System
02
Define Truth
03
Make Exceptions Visible
04
Design Intelligence
05
Build Decision Paths
06
Validate
07
Iterate

Understand the System

Systems Thinking in Action

Philosophy

Before designing interfaces, we mapped the entire supply-chain ecosystem.

What I did:

Stakeholder Mapping

Planners, Category Managers, Procurement, Warehouse Ops

4 User Groups

Stakeholder Mapping

Planners, Category Managers, Procurement, Warehouse Ops

4 User Groups

Data Dependency

Traced technical pipelines through the entire ecosystem

6 Data Sources

Data Dependency

Traced technical pipelines through the entire ecosystem

6 Data Sources

User Shadowing

Observed 8 planners in real distribution centers

40+ Hours

User Shadowing

Observed 8 planners in real distribution centers

40+ Hours

Log Analysis

Revealed actual usage patterns vs. intended workflows

Audit Logs

Log Analysis

Revealed actual usage patterns vs. intended workflows

Audit Logs

Key Insight

Planners didn’t need more data. They needed to know what to act on first — and why.

Define the Workflow Truth

Goal: Map the real decision flow, not the idealized one

The Current State

The Manual Workflow

Planners moved between multiple systems and spreadsheets before reaching a decision.

Tool A

Sales data

Tool B

Inventory levels

Tool C

OTIF reports

Export Excel

The Bottleneck

Manual consolidation of disparate data sources into a static spreadsheet.

Complex Calculation

Calculate WOS and turn rates

Time Consuming

Manual Reconciliation

Cross-reference SKU IDs manually

High Error Risk

Prioritization

Create top 10 priority list

Static Snapshot

Finally Take Action

Total Estimated Time: 2-3 Hours / Cycle

The Current State

The Manual Workflow

Planners moved between multiple systems and spreadsheets before reaching a decision.

Tool A

Sales data

Tool B

Inventory levels

Tool C

OTIF reports

Export Excel

The Bottleneck

Manual consolidation of disparate data sources into a static spreadsheet.

Complex Calculation

Calculate WOS and turn rates

Time Consuming

Manual Reconciliation

Cross-reference SKU IDs manually

High Error Risk

Prioritization

Create top 10 priority list

Static Snapshot

Finally Take Action

Total Estimated Time: 2-3 Hours / Cycle

The Current State

The Manual Workflow

Planners moved between multiple systems and spreadsheets before reaching a decision.

Tool A

Sales data

Tool B

Inventory levels

Tool C

OTIF reports

Export Excel

The Bottleneck

Manual consolidation of multiple data sources

Complex Calculation

Calculate WOS and turn rates

Time Consuming

Manual Reconciliation

Cross-reference SKU IDs manually

High Error Risk

Prioritization

Create top 10 priority list

Static Snapshot

Finally Take Action

Total Estimated Time:
2-3 Hours / Cycle

Friction Points

A unified decision platform with built-in prioritization, automatic calculations, and transparent reasoning.

The Future State

The Real Decision Workflow

User
(Planner)
Planner logs in
Is this urgent?
“Threshold-based alert
(stockout risk, SLA breach)”
YES
NO (Snooze)
Cause of issue?
Vendor delay
/ forecast error
/ demand spike
Action
Execution
Adjust next order
Redistribute inventory
Flag forecast model
Problem Resolved
~8 minutes total
was 4+ hours

System (NIQ)

Command Center
Entry via Alert
Northeast Region
3 Critical Issues
Reports Catalog
Inventory • Vendor • Dist.
Inventory Efficiency
Heatmap View
!
DC-04: Low unit turns
Item Opportunity
SKU Drill-down
SKU B
High on-hand,
Low sales
Root Cause Panel
AI Recommendation
Action Plan
Reduce order 40%
Redistribute to DC-07
Vendor Compliance
Supplier C
87%
OTIF Score
Issue is forecasting,
not vendor failure

Alternative Workflows

Path A
No Issues
Dashboard
Efficiency
All Green
2m

Path B
Vendor Issue
Alert
Scorecard
Escalate
5m

Design Principles

Entry via Alerts

Users don't hunt for problems. The system pushes 3 Critical Issues directly to the dashboard.

Explainable AI

System explains "why" (Low turns) and suggests "what" (Reduce order), building trust.

Progressive Disclosure

High-level Heatmaps → SKU Details → Root Cause. Information only when needed.

Action-Oriented

Every screen is designed to move the planner towards a decision, not just display data.

User
(Planner)
Planner logs in
Is this urgent?
“Threshold-based alert
(stockout risk, SLA breach)”
YES
NO (Snooze)
Cause of issue?
Vendor delay /
forecast error
/ demand spike
Action
Execution
Adjust next order
Redistribute inventory
Flag forecast model
Problem Resolved
~8 minutes total
was 4+ hours

System (NIQ)

Command Center
Entry via Alert
Northeast Region
3 Critical Issues
Reports Catalog
Inventory • Vendor • Dist.
Inventory Efficiency
Heatmap View
!
DC-04: Low unit turns
Item Opportunity
SKU Drill-down
SKU B
High on-hand,
Low sales
Root Cause Panel
AI Recommendation
Action Plan
Reduce order 40%
Redistribute to DC-07
Vendor Compliance
Supplier C
87%
OTIF Score
Issue is forecasting,
not vendor failure

Alternative Workflows

Path A
No Issues
Dashboard
Efficiency
All Green
2m

Path B
Vendor Issue
Alert
Scorecard
Escalate
5m

Design Principles

Entry via Alerts

Users don't hunt for problems. The system pushes 3 Critical Issues directly to the dashboard.

Explainable AI

System explains "why" (Low turns) and suggests "what" (Reduce order), building trust.

Progressive Disclosure

High-level Heatmaps → SKU Details → Root Cause. Information only when needed.

Action-Oriented

Every screen is designed to move the planner towards a decision, not just display data.

The Future State

The Real Decision Workflow

Imrovements

Single source of truth, automatic calculations, built-in prioritization, transparent reasoning builds trust

Report Architecture: Mapping Decision Modules

Design principle: Surface what matters, reduce noise

CORE DECISIONS

Default view = Exceptions only:

Show only SKUs at risk (High/Medium), not all 10,000+ SKUs. Advanced users can toggle "Show All" if needed.

Risk scoring:

Automated classification based on Sales Velocity × Inventory Depth matrix. Red = Critical (stockout imminent), Amber = Watch (trending negative), Green = Healthy.

Top 10 prioritization:

Surface highest revenue-impact items first. One planner said: "I don't have time to fix everything—just tell me which 10 will cost us the most."

Progressive disclosure:

Start with heatmap overview (scan), allow drill-down to SKU detail (understand), then quick actions (act).

CORE DECISIONS

Default view = Exceptions only:

Show only SKUs at risk (High/Medium), not all 10,000+ SKUs. Advanced users can toggle "Show All" if needed.

Risk scoring:

Automated classification based on Sales Velocity × Inventory Depth matrix. Red = Critical (stockout imminent), Amber = Watch (trending negative), Green = Healthy.

Top 10 prioritization:

Surface highest revenue-impact items first. One planner said: "I don't have time to fix everything—just tell me which 10 will cost us the most."

Progressive disclosure:

Start with heatmap overview (scan), allow drill-down to SKU detail (understand), then quick actions (act).

Concept Exploration

We explored three main paradigms for the report before
converging on a hybrid approach.

We explored three main paradigms
for the dashboard before
converging on a hybrid approach.

Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).

Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).

Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Report Page with Geo Map
Report Page with Heatmap
2
Concept B: The Geographic
Map-first view emphasizing warehouse locations.
Why it failed: Spatial view hid non-geo logic (e.g. expiration).
Supply Chain / Reports / Catlogue
Report Page
1
Concept A: The Analyst
Dense data tables with advanced filtering.
Why it failed: Too overwhelming for quick scanning.
Supply Chain / Reports / Catlogue
Report Page
3
Concept C: The Feed
KPI-first layout
Why it failed: Spatial view hid non-geo logic (e.g. expiration).

Convergence

We combined the high-level scannability of the Heatmap
with the drill-down power of the Table.

Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table

Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table

Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table

Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table
Supply Chain / Reports / Catlogue
Pipeline Drive + Geomap
Pipeline Drive + Heatmap
Item Opportunities
Listing Efficiency
EoP Distribution Table

Concept D: Map vs Heatmap

We combined the high-level scannability of a heatmap with the analytical power of detailed investigation views. Inventory issues are rarely spatial.

They are temporal, behavioral, and threshold-based, making abstract visualizations more effective than geographic maps.

Key Decision

Selected: Hybrid MODEL

Concept D: Map vs Heatmap

We chose abstract heatmaps over geo-maps because inventory issues often aren't spatial—they are temporal.

Key Decision

Selected: Hybrid MODEL

Top layer: Visual heatmap for instant "health check"

Middle layer: Prioritized list of "At Risk" items

Bottom layer: Detailed SKU table on demand

The 3 Core Pillars (3CP Framework)

We used this framework to evaluate every feature decision.

We explored three main paradigms
for the dashboard before
converging on a hybrid approach.

PROBABILITY

How likely is a stockout or overstock event?

Metrics: Sales velocity, Weeks of Supply (WOS), Unit turn rate

Implementation: The scoring formula is visible in the interface so planners understand how risk is calculated.

EXPLAINABILITY

Why is this SKU being flagged?

Breakdown: OTIF delays + Forecast variance + Inbound gaps + Historical trend

Implementation: Drill-down panel shows root cause analysis. Users can trace the issue back to its source (e.g., "DC-03 missed 3 deliveries last week").

ADAPTABILITY

How should the system adjust as conditions change?

Customization: Override thresholds based on seasonal patterns, product lifecycle, regional differences

Implementation: System learns from planner actions—if they consistently dismiss a flag type, the model adjusts.

This framework became the north star for all design decisions.
Every feature had to serve at least one pillar.

Intelligence Layer Design

The interface was designed as a decision workflow, not just a reporting dashboard.

Planners move through three stages: scan risk signals, understand the drivers behind them, and take action directly within the system — without losing context.

The experience is structured around an exception-first heatmap, supported by explainability and action layers that help planners move from signal detection to operational decisions.

We explored three main paradigms
for the dashboard before
converging on a hybrid approach.

Input: DC/Store network + weekly signals
Core mechanic: Exception-first heatmap + explainability
Output: Prioritized actions + audit-ready validation

The workflow begins with an exception-first heatmap that surfaces inventory anomalies across distribution centers and time periods.

Instead of scanning dense tables, planners can quickly identify unusual patterns, inspect individual cells via hover, and move directly into deeper investigation when something looks off.

This allows users to shift from manual data hunting to rapid anomaly detection.

01
Scan
Heatmap
02
Investigate
Tooltip + Drilldown
03
Explain
Root Cause
04
Act
Alerts + Actions
05
Validate
Table

Understand Why It’s Happening

Once an anomaly is identified, planners can open the root-cause panel without leaving the view.

The panel aggregates multiple signals — including OTIF performance, forecast variance, sales velocity, and inventory levels — to explain the drivers behind the risk.

This removes the need to switch between multiple reporting tools and allows planners to diagnose problems directly within the workflow.

1.1

1.2

Root Cause Panel

Consolidates signals across inventory, forecast, and logistics.

Root Cause Panel

Consolidates signals across inventory, forecast, and logistics.

Multi-signal breakdown

Shows which metrics are contributing most to the issue.

Temporal context

Allows planners to see how the signal evolved over time.

Temporal context

Allows planners to see how the signal evolved over time.

Take Action Without Losing Context

Once the planner understands the problem, the system supports action directly within the same workflow.

Rather than exporting data or switching tools, planners can evaluate item performance, adjust decisions, and prioritize corrective actions while maintaining the full analytical context.

This reduces workflow fragmentation and allows planners to move from analysis to action more quickly.

1.1

1.2

Inline adjustments

Planners can modify decisions or initiate corrective actions directly from the interface.

Suggested Actions

The system highlights high-impact opportunities that require attention.

Suggested Actions

The system highlights high-impact opportunities that require attention.

Feedback loop

Planner actions feed back into the workflow, improving prioritization over time.

Feedback loop

Planner actions feed back into the workflow, improving prioritization over time.

Intelligence Principles

Across all views, the design follows four core principles:

Progressive disclosure

Explainable scoring

Exception-first workflow

Action-oriented states

Validation

Testing Approach

5 Moderated Usability Sessions

High-fidelity Prototype (Figma)

Task: "Identify & Fix 3 Risks"

Task Success Rate

100%

All users completed core workflow (vs 40% on legacy)

All users completed core workflow
(vs 40% on legacy)

Time on Task

-60%

Reduction from ~12 mins to ~4.5 mins

Finding

Evidence

Change Made

Terminology Confusion

3/5 users didn't understand 'Velocity Score'

Renamed to 'Sales Rate' and added tooltip

Filter Blindness

Users missed the global region filter in top right

Moved filters to left sidebar

Action Anxiety

Hesitation to click 'Transfer' without confirmation

Added summary modal before final execution

Iteration Changelog

Adjusted color thresholds

Simplified navigation

Added bulk actions

Improved empty states

Impact

The pilot launched in Q4 and immediately
transformed how the inventory team operated.

"I used to dread Monday mornings. Now I can clear my risk queue before my first coffee. It's not just faster; it's less stressful."

Sarah R.

— Sr. Inventory Planner, Walmart

Finding

Evidence

Change Made

Issue Detection

48 hours

< 1 hour

98% Faster

Stockout Losses (Q4)

$3.5M (proj)

$1.4M

$2.1M Saved

Tool Switching

4-5 tools

1 tool

Consolidated

Learnings &
What's Next

What Worked Well

Involving engineers early in feasibility checks

Testing with real data (not Lorem Ipsum)

Weekly 'office hours' with planners

What I'd Do Differently

Spent too long on 'Geographic View' concept

Should have defined metrics baseline earlier

Underestimated legacy data cleanup effort

Next Case Studies

Brand Swap initiative

Creating an advanced analytical and AI-infused solution, which can quickly and preemptively prevent supply chain disruptions, maintain on-shelf availability, and improve future forecasting, planning and management.

Inventory Efficiency Report: Turning Supply Chain Chaos into Confident Decisions

Overview

TL;DR

TL;DR

60%

$2.1M

6 → 1

40%

60%

$2.1M

6 → 1

40%

The Challenge

Fragmented Systems, Hidden Risks

Fragmented Systems, Hidden Risks

The Core Problem

Fragmented

Reactive

Opaque

Overwhelming

The Stakes Were High

Stockouts

Stockouts

Overstock

Delays

User Pain Points Quantified

45%

Adaption

6

Sources

24+

Hours

4+

Hours

45%

Adaption

6

Sources

24+

Hours

4+

Hours

4+

Hours

24+

Hours

6

Sources

45%

Adaption

User Snapshot: The Inventory Planner

Success Criteria

To solve this problem, the design needed to shift the tool from reporting data to directing decisions.We defined three success criteria.

To solve this problem, the design needed to shift the tool from reporting data to directing decisions.We defined three success criteria.

Process Overview

The design process focused on understanding how planners actually worked before proposing new solutions.

The design process focused on understanding how planners actually worked before proposing new solutions.

Understand the System

Systems Thinking in Action

Systems Thinking in Action

Before designing interfaces, we mapped the entire supply-chain ecosystem.

Define the Workflow Truth

Goal: Map the real decision flow, not the idealized one

Goal: Map the real decision flow, not the idealized one

The Manual Workflow

Complex Calculation

Manual Reconciliation

Prioritization

Finally Take Action

The Manual Workflow

Complex Calculation

Manual Reconciliation

Prioritization

Finally Take Action

The Manual Workflow

Complex Calculation

Manual Reconciliation

Prioritization

Finally Take Action

The Real Decision Workflow

User Snapshot:
The Inventory Planner

To solve this problem, the design needed to shift the tool from reporting data to directing decisions.

We defined three success criteria.

To solve this problem, the design needed to shift the tool from reporting data to directing decisions.

We defined three success criteria.

We explored three main paradigms for the report before
converging on a hybrid approach.

We explored three main paradigms
for the dashboard before
converging on a hybrid approach.

We combined the high-level scannability of the Heatmap
with the drill-down power of the Table.

We explored three main paradigms
for the dashboard before
converging on a hybrid approach.

We explored three main paradigms
for the dashboard before
converging on a hybrid approach.

The pilot launched in Q4 and immediately
transformed how the inventory team operated.

Learnings &
What's Next