Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents

TL;DR

Reversa is a framework that converts legacy software into operational specifications for AI agents, enhancing traceability, confidence marking, and human validation in software migration tasks.

Contribution

It introduces a multi-agent pipeline for reverse documentation engineering, integrating traceability, confidence, and gap preservation in legacy system modernization.

Findings

Produced 517 claims with confidence indices in a case study

Identified 10 gaps and generated 53 Gherkin scenarios

Reconstructed a migration plan with 9 of 11 tasks completed

Abstract

Legacy systems concentrate business rules, architectural decisions, and operational exceptions that often remain implicit in code, data, configuration, and maintenance practices. At the same time, language-model-based coding agents depend on reliable context, correctness criteria, and behavioral contracts to modify real systems with lower risk. This paper presents Reversa, a reverse documentation engineering framework for converting legacy software into traceable operational specifications for AI agents. Reversa organizes this process as a multi-agent pipeline: specialized agents map the project surface, analyze modules, extract implicit rules, synthesize architecture, write unit-level specifications, and review generated claims. The proposal emphasizes three mechanisms: traceability between code and specification, explicit confidence marking, and preservation of gaps for human validation. The framework is distributed as a Node.js CLI, installs skills across multiple agent engines, and uses a SHA-256 manifest to preserve modified files during update or uninstall operations. In addition to the architectural description, we report an exploratory case study on migrating an ATM from COBOL to Go, in which the pipeline produced 517 claims classified by an internal confidence index, 10 registered gaps, 53 Gherkin parity scenarios, and a reconstruction plan with 9 of 11 tasks completed at inventory time. Final parity validation and cutover were not completed in this study. We do not claim broad empirical superiority; we position the contribution with respect to the literature on reverse engineering, LLM-based documentation, and software agents, and propose an evaluation protocol with metrics for coverage, traceability, confidence, utility, and cost.