PwC Logistics United States

Southwest Airlines

Application Refactoring

Southwest Airlines needed to modernize a legacy crew attendance and leave system whose undocumented logic and aging stack made maintenance, planning, and future change slow and risky.

Read the original story Explore all use cases

200+ hours saved across engineering, technology and business specialists during the planning and design project phases

50% reduction of backlog creation time to 5 weeks from 10 weeks compared to traditional methods

90% of AI-generated user stories accepted as high-quality requirements, totaling over 600 stories

Reported impact

Business outcome

Southwest halved backlog-creation time, created a high-confidence modernization plan with more than 600 accepted user stories, and established a faster, more accurate way to prepare legacy systems for redevelopment.

Solution

Southwest Airlines used generative AI as the core engine for modernizing a legacy crew leave and attendance application before any rewrite work began. PwC built a Microsoft Azure-based approach that reverse-engineered complex source code into functional requirements and a prioritized modernization backlog. GenAI capabilities automated code analysis, dependency mapping, and user-story generation, while Southwest’s knowledge specialists and PwC teams iteratively reviewed outputs in workshops to align them with operational needs. Instead of spending months reconstructing undocumented business logic by hand, the teams condensed planning and design into a five-week milestone with a high-confidence delivery plan. The resulting backlog covered more than 600 high-quality user stories and created a repeatable method for translating legacy applications into actionable modernization programs that save engineering time, reduce risk, and accelerate future development.

Data flow

Legacy crew-management source code flows through PwC’s Azure-based GenAI pipeline, which extracts requirements, maps dependencies, and generates user stories. Southwest specialists then review and refine the outputs in workshops, turning undocumented application logic into a prioritized backlog and delivery plan for the modernization program.

Solution architecture

3 components · 2 layers

Compute
- Microsoft Azure Provides the cloud environment for the GenAI-assisted reverse-engineering and planning workflow.
- GenAI capabilities Analyze legacy source code, extract requirements, and map dependencies for modernization planning.
Serving
- AI-generated user stories Translate the analyzed system behavior into a prioritized backlog for implementation teams.

Architecture clues

Source-code analysis and dependency mapping were automated with GenAI on Azure.
The generated backlog became a high-confidence delivery plan before redevelopment started.
User stories were refined through workshops with Southwest knowledge specialists.

Evidence from the source

90% of AI-generated user stories accepted as high-quality requirements, totaling over 600 stories

GenAI capabilities were used to pull unique insights and requirements directly from the source code, reducing project planning time by half.

PwC brought an innovative engineering approach along with GenAI, built on Microsoft Azure, to reverse-engineer the legacy system’s complex source code into holistic functional requirements.

The PwC team gave us a new way to modernize legacy applications, which is faster and more accurate than traditional planning approaches.

While GenAI tools automated labor-intensive tasks like scalable code analysis and dependency mapping, PwC facilitated workshops and iterative reviews that helped align the outputs with our operational needs — blending leading-edge technology with strategic human insights.

Transparency Evidence & methodology 95/100 reference value · 85% confidence · 2 sources

Review how this reference was scored and trace each normalized claim back to its documented source.

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value95/100

Problem clarity20/20
Measures whether the customer's operational problem is specific enough to compare.
Implementation depth25/25
Rewards named components, data flow, integrations, and architecture detail.
Outcome specificity20/20
Measures whether the reported benefit is concrete rather than a generic claim.
Quantified impact25/25
3 metrics describe measurable impact.
Deployment scale5/10
Rewards evidence of a live or scaled deployment and meaningful integration scope.

Evidence confidence85%

Source authority20/25
The main evidence is an official vendor-published customer story.
Claim traceability25/25
12 of 12 key fields link to a named source.
Direct evidence20/20
5 direct source quotes retained.
Date provenance0/10
The publication date has no documented provenance.
Source transparency10/10
2 source references document publisher, URL, authority, retrieval, and supported fields.
Implementation specificity10/10
Rewards source-backed components, data flow, quantified impact, and a specific outcome.

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

PwC
Southwest uses AI to modernize management software: PwC

First-party
https://www.pwc.com/us/en/library/case-studies/southwest-ai-software-update.html

Source type
Vendor-published customer story
Supports
- Customer
- Region
- Business problem
- Solution
- Products
- Solution components
- Data flow
- Integrations
- Business outcome
- Metrics
- Architecture
- evidence quotes
Southwest Airlines
People Data Table 2025

First-party
https://www.southwest.com/swa-resources/pdfs/about-southwest/People-Data-Table-2025.pdf
The 2025 People Data Table lists Total Employees at 78,723 as of December 31, 2025.

Source type
Official fact sheet
Supports
- Company size

Date evidence

First archived Apr 14, 2025 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
Open date source
Sitemap last modified Mar 10, 2026 · PwC · Publisher metadata Publisher-reported modification timestamp; not a publication date.
Open date source

Not separately sourced Industry. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Similar use cases

See all like this

Google Cloud Modified · Oct 9, 2026 Porter Logistics India Porter (Smartshift Logistics Private Limited), a leading logistics platform based in India, orchestrates on-demand mini-trucks, tempos, and two-wheelers across 50+ major cities. When order volumes doubled, Porter’s… Achieved 30% zero-touch driver verification automation on Gemini platform Application RefactoringDocument Processing BigQuery · Cloud Composer · Cloud Pub/Sub

MongoDB Archived · Sep 30, 2026 Amadeus IT Group Logistics Global The shift to New Distribution Capability (NDC) bypassed traditional GDS buffers, sending massive search traffic directly to airlines’ systems. Furthermore, MongoDB's distributed architecture and sharding capabilities enable Amadeus to scale horizontally,… Application RefactoringReal-time Analytics MongoDB Atlas · MongoDB Enterprise Advanced

Google Cloud Archived · Sep 26, 2026 Delivery Hero Logistics Germany Delivery Hero needed a standardized AI engineering platform that could support autonomous software delivery, let teams use the strongest coding model for each task, and still preserve centralized governance, review, and… Application RefactoringIT Operations Automation Claude · Gemini · Gemini CLI