Legacy System & Specialized Use Cases

Weight: 0%

Sources verified Dec 22

Why It Matters

Legacy systems remain critical enterprise infrastructure. AI tools like GitHub Copilot and Claude Code are increasingly used for legacy code comprehension, documentation, and modernization—enabling organizations to reduce modernization timelines significantly.

✓ GitHub/Accenture: Airbnb migrated 3,500 test files in 6 weeks vs estimated 1.5 years (Accenture 2025) ⓘ

×

Research: Quantifying GitHub Copilot's impact in the enterprise with Accenture

GitHub/Accenture

This is the primary source for the 30% acceptance rate benchmark and the 88% code retention statistic. The 95% enjoyment and 90% fulfillment stats are powerful for adoption justification. The 84% increase in successful builds directly supports the claim that AI doesn't sacrifice quality for speed. Published May 2024, so represents mature Copilot usage patterns.

Key Findings:

• 95% of developers said they enjoyed coding more with GitHub Copilot
• 90% of developers felt more fulfilled with their jobs when using GitHub Copilot
• Developers accepted around 30% of GitHub Copilot's suggestions

Credibility: high

View Source ↗

✓ GitHub/Accenture: Google reported 80% of code modifications AI-authored with 50% reduction in migration time ⓘ

×

Research: Quantifying GitHub Copilot's impact in the enterprise with Accenture

GitHub/Accenture

This is the primary source for the 30% acceptance rate benchmark and the 88% code retention statistic. The 95% enjoyment and 90% fulfillment stats are powerful for adoption justification. The 84% increase in successful builds directly supports the claim that AI doesn't sacrifice quality for speed. Published May 2024, so represents mature Copilot usage patterns.

Key Findings:

• 95% of developers said they enjoyed coding more with GitHub Copilot
• 90% of developers felt more fulfilled with their jobs when using GitHub Copilot
• Developers accepted around 30% of GitHub Copilot's suggestions

Credibility: high

View Source ↗

Learn More

• ConceptUnderstand how long-context models enable codebase-wide analysis
• ConceptLearn retrieval patterns for large legacy codebases
• ExerciseEvaluate modernization strategies systematically

2025 Context

Legacy modernization is a major 2025 enterprise use case. Organizations like Airbnb and Google are demonstrating significant time savings. However, human oversight remains essential for business logic validation.

Assessment Questions (4)

Maximum possible score: 17 points

○ Q1 single choice 3 pts

Do you work with legacy codebases (COBOL, older Java, mainframe systems)?

[0] No - N/A

[1] Occasionally - some older code

[2] Regularly - significant legacy codebase

[3] Primarily - legacy modernization is my focus

✓ Google DORA: AI adoption varies significantly by codebase age and technology ⓘ

×

State of AI-Assisted Software Development 2025

Google DORA

The 2025 DORA report introduces the 'AI Capabilities Model' identifying seven practices that amplify AI benefits. The core insight is that AI is an 'amplifier' - it magnifies existing organizational strengths AND weaknesses. Key stats: 89% of orgs prioritizing AI, 76% of devs using daily, but 39% have low trust. The trust research is critical: developers who trust AI more are more productive, but trust must be earned through organizational support (policies, training time, addressing concerns). The 451% adoption increase from acceptable-use policies is remarkable - clarity enables adoption.

Key Findings:

• 89% of organizations prioritizing AI integration into applications
• 76% of technologists rely on AI for parts of their daily work
• 75% of developers report positive productivity impact from AI

Credibility: high

View Source ↗

○ Q2 multi select 5 pts

How do you use AI tools for legacy code?

[1] Understanding/documenting legacy code

[1] Refactoring within the same language

[2] Migrating to modern languages (COBOL→Java)

[1] Generating tests for legacy code

[0] I don't use AI for legacy code

✓ Google DORA: Legacy modernization is an emerging AI use case ⓘ

×

State of AI-Assisted Software Development 2025

Google DORA

The 2025 DORA report introduces the 'AI Capabilities Model' identifying seven practices that amplify AI benefits. The core insight is that AI is an 'amplifier' - it magnifies existing organizational strengths AND weaknesses. Key stats: 89% of orgs prioritizing AI, 76% of devs using daily, but 39% have low trust. The trust research is critical: developers who trust AI more are more productive, but trust must be earned through organizational support (policies, training time, addressing concerns). The 451% adoption increase from acceptable-use policies is remarkable - clarity enables adoption.

Key Findings:

• 89% of organizations prioritizing AI integration into applications
• 76% of technologists rely on AI for parts of their daily work
• 75% of developers report positive productivity impact from AI

Credibility: high

View Source ↗

✓ GitHub: Copilot can assist with code translation and modernization ⓘ

×

GitHub Copilot Documentation - Supported AI Models

GitHub

GitHub Copilot now supports multiple AI models including Claude 3.5 Sonnet, GPT-4o, and Gemini 1.5 Pro, allowing developers to switch models per conversation based on task requirements. This multi-model capability is foundational for model routing maturity - understanding that different models excel at different tasks enables cost-effective and capability-optimized AI development workflows.

Key Findings:

• Multi-model support (Claude, GPT, Gemini)
• Model selection per conversation

Credibility: high

View Source ↗

○ Q3 single choice 5 pts

For AI-assisted legacy migration, what verification do you apply?

[0] N/A - don't do migration

[1] Trust AI output if tests pass

[2] Code review + test verification

[4] Expert review of business logic + comprehensive testing

[5] Parallel running of old and new systems + expert validation

Note: Legacy migration requires highest verification—business logic is often undocumented

✓ GitHub/Accenture: Enterprise case studies show significant accuracy improvements with AI-assisted migration ⓘ

×

Research: Quantifying GitHub Copilot's impact in the enterprise with Accenture

GitHub/Accenture

This is the primary source for the 30% acceptance rate benchmark and the 88% code retention statistic. The 95% enjoyment and 90% fulfillment stats are powerful for adoption justification. The 84% increase in successful builds directly supports the claim that AI doesn't sacrifice quality for speed. Published May 2024, so represents mature Copilot usage patterns.

Key Findings:

• 95% of developers said they enjoyed coding more with GitHub Copilot
• 90% of developers felt more fulfilled with their jobs when using GitHub Copilot
• Developers accepted around 30% of GitHub Copilot's suggestions

Credibility: high

View Source ↗

○ Q4 single choice 4 pts

How do you use AI to document legacy code?

[0] I don't use AI for documentation

[1] Generate basic inline comments

[2] Generate function/module documentation and flow diagrams

[3] Use long-context models to understand and document entire systems

[4] Generate comprehensive documentation including business logic, dependencies, and modernization recommendations

✓ Google: Long-context models (1M tokens) enable whole-codebase understanding ⓘ

×

Long context | Gemini API Documentation

Google

Gemini's 1M token context window is among the largest available, enabling whole-codebase understanding. Key for context_curation and model_routing dimensions.

Key Findings:

• Gemini models support up to 1M token context window (1,048,576 tokens)
• Can process hours of video, audio, and 60,000+ lines of code in single context
• Gemini 2.5 Pro, 2.5 Flash, 3.0 Pro, 3.0 Flash all support 1M tokens

Credibility: high

View Source ↗

✓ GitHub/Accenture: AI-generated documentation accelerates legacy modernization ⓘ

×

Research: Quantifying GitHub Copilot's impact in the enterprise with Accenture

GitHub/Accenture

This is the primary source for the 30% acceptance rate benchmark and the 88% code retention statistic. The 95% enjoyment and 90% fulfillment stats are powerful for adoption justification. The 84% increase in successful builds directly supports the claim that AI doesn't sacrifice quality for speed. Published May 2024, so represents mature Copilot usage patterns.

Key Findings:

• 95% of developers said they enjoyed coding more with GitHub Copilot
• 90% of developers felt more fulfilled with their jobs when using GitHub Copilot
• Developers accepted around 30% of GitHub Copilot's suggestions

Credibility: high

View Source ↗