Skip to main content

AI Engines

diffray is built on a powerful foundation of AI engines that work together to deliver comprehensive code reviews. This architecture enables a true multi-agent system where specialized agents collaborate effectively.

Core Engine​

The core engine provides the foundation for the entire multi-agent system:

Advanced Language Models​

We use the latest frontier models from Anthropic — Haiku 4.5, Sonnet 4.5, and Opus 4.5 — currently the most capable AI models for understanding and analyzing code. Each task within the review pipeline is matched with the optimal model:

  • Complex analysis tasks — largest models for deep reasoning and understanding
  • Pattern matching — faster models for quick checks
  • Validation passes — specialized models for verification

This model selection approach ensures both high-quality analysis and efficient processing.

The core includes an advanced file search system that quickly navigates codebases of any size:

  • Smart pattern matching — finds relevant files instantly across thousands of files
  • Context-aware search — understands code structure, not just text
  • Efficient exploration — minimizes API calls while maximizing coverage
  • Parallel search — multiple search strategies run simultaneously

This means agents can quickly locate dependencies, related code, and project context to validate their findings.

Task Management System​

A built-in task tracking system ensures thorough, consistent reviews:

  • Structured checklists — every review follows a comprehensive process
  • No missed steps — the system tracks what's been analyzed and what remains
  • Rule adherence — custom rules are never forgotten during analysis
  • Progress visibility — clear tracking of what each agent has completed

This prevents agents from overlooking issues or skipping important checks.

Tooling Engine​

The tooling engine provides agents with the ability to verify their hypotheses using real code analysis tools:

Static Analyzers​

Agents can invoke static analysis tools to validate their findings. This means agents don't just guess — they can run actual analyzers to confirm issues exist.

Hypothesis Verification​

When an agent suspects a problem, it can run targeted analysis to execute specific checks on suspicious code. This dramatically reduces false positives by grounding AI analysis in concrete tool output.

Multi-Agent Architecture​

These engines enable a sophisticated multi-agent system:

Agent Collaboration​

  • Parallel execution — multiple specialized agents work simultaneously
  • Shared context — agents access the same codebase understanding
  • Finding deduplication — overlapping discoveries are merged intelligently
  • Cross-validation — agents can verify each other's findings

Specialized Agents​

Each review agent leverages the full power of both engines:

  • Security agent uses static analyzers to verify vulnerability patterns
  • Performance agent runs profiling tools to confirm bottlenecks
  • Bug hunter uses type checkers to validate error scenarios
  • Quality guardian leverages linters to enforce standards

Phased Review Pipeline​

Reviews run through a multi-phase pipeline, each phase optimized for its purpose:

Clone → Data Prep → Guidelines → Review → Deduplication → Validation → Report
  • Data Preparation — gathers relevant context about your codebase
  • Guidelines — applies project-specific rules and standards
  • Review — specialized agents analyze different aspects in parallel
  • Deduplication — removes redundant findings across agents
  • Validation — filters out low-confidence issues using tooling

Continuous Evolution​

The engines evolve with the latest advances:

  • New models — latest AI capabilities integrated as they become available
  • Tool updates — static analyzers kept current with language evolution
  • Rule refinement — review rules continuously improved based on feedback
  • Performance optimization — faster reviews without sacrificing quality

The result? A multi-agent system that combines AI reasoning with concrete code analysis — delivering accurate, verified findings instead of speculation.