"Thoughtworks consultants recently described an experiment that applied generative AI to a legacy system with no available source code. The article, shared on Martin Fowler's blog, highlighted a pilot where a five-person team analyzed the system's database, UI, and binaries in parallel. InfoQ reached out to the authors, Thiyagu Palanisamy and Chandirasekar Thiagarajan, who explained that during the two-week pilot the team used Gemini 2.5 Pro to analyse a thin slice of what was an enormous legacy system."
"The output of that analysis was a functional specification - a "blueprint" of the black-box system that domain experts were able to validate. AI proved most effective in decoding code, summarizing binaries, and mapping database changes, while also easing schema discovery. AI made a significant difference in reverse engineering the ASM code. Traditional approaches would have taken months to decode the logic specified ASM and also to identify the system functions vs business functionality."
A five-person team ran a two-week pilot using Gemini 2.5 Pro to analyze a thin slice of a large legacy system lacking source code. The team examined database schema, UI behavior, runtime traces, and binaries in parallel to correlate observable behaviors and trace how user actions mutated the database. The pilot produced a functional specification — a validated blueprint of the black-box system — that captured functional intent rather than regenerated code. AI proved especially effective at decoding assembly, summarizing binaries, mapping database changes, and easing schema discovery, accelerating insight compared to months of manual work.
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]