From Black Field to Blueprint

Key Challenges

1. Lacking Supply Code: legacy understanding is already complicated once you
   have supply code and an SME (in some type) to place every little thing collectively. When the
   supply code is lacking and there are not any specialists it’s an excellent higher problem.
   What’s left are some compiled binaries. These should not the current binaries that
   are straightforward to decompile on account of wealthy metadata (like .NET assemblies or JARs), these
   are even older binaries: the type that you just may see in outdated home windows XP beneath
   C:Home windowssystem32. Even when the database is accessible, it doesn’t inform
   the entire story. Saved procedures and triggers encode many years of gathered
   enterprise guidelines. Schema displays compromises made based mostly on context unknown.
2. Outdated Infrastructure: OS and DB reached finish of life, gone its
   LTS. Utility has been in a frozen state within the type of VM resulting in
   vital threat to not solely enterprise continuity, additionally considerably growing
   safety vulnerability, non compliance and threat legal responsibility.
3. Institutional Information Misplaced: whereas 1000’s of finish customers are
   constantly utilizing the system, there’s hardly any enterprise information obtainable
   past the occasional help actions. The reside system is the most effective supply of
   information. The one dependable view of performance is what customers see on display.
   However the UI captures solely the “final mile” of execution. Behind every display lies a
   tangled net of logic deeply built-in to a number of different core techniques. It is a
   frequent problem, and this method was no exception, having a historical past of a number of
   failed makes an attempt to modernize.

Our Objective

The target is to create a wealthy, complete purposeful specification
of the legacy system while not having its authentic code, however with excessive
confidence. This specification then serves because the blueprint for constructing a
trendy substitute utility from a clear slate.

• Perceive total image of the system boundary and the mixing
  patterns
• Construct detailed understanding of every purposeful space
• Establish the frequent and distinctive eventualities

To make sense of a black-box system, we would have liked a structured method to pull
collectively fragments from completely different sources. Our precept was easy: don’t
attempt to recuperate the code — reconstruct the purposeful intent.

Our Multi Lens Method

It was a 3 tier structure – Net Tier (ASP), App Tier (DLL) and
Persistence (SQL). This structure sample gave us a leap begin even with out
supply repo. We extracted ASP information and DB schema, saved procedures from the
manufacturing system. For App Tier we solely have the native binaries. With all
this data obtainable, we deliberate to create a semi-structured
description of utility habits in pure language for the enterprise
customers to validate their understanding and expectations and use the validated
purposeful spec to do accelerated ahead engineering. For the semi-structured
description, our method had broadly two components

1. Utilizing AI to attach dots throughout completely different information sources
2. AI assisted binary Archaeology to uncover the hidden performance from
   the native DLL information

UI Layer Reconstruction

Searching the prevailing reside utility and screenshots, we recognized the
UI components. Utilizing the ASP and JS content material the dynamic behaviour related
with the UI aspect could possibly be added. This gave us a UI spec like under:

What we seemed for: validation guidelines, navigation paths, hidden fields. One
of the important thing challenges we confronted from the early stage was hallucination, each
step we added an in depth lineage to make sure that we cross test and make sure. In
the above instance we had the lineage of the place it comes from. Following this
sample, for each key data we added the lineage together with the
context. Right here the LLM actually sped up the summarizing of enormous numbers of
display definitions and consolidating logic from ASP and JS sources with the
already recognized UI layouts and subject descriptions that will in any other case take
weeks to create and consolidate.

Discovery with Change Knowledge Seize (CDC)

We deliberate to make use of Change Knowledge Seize (CDC) to hint how UI actions mapped
to database exercise, retrieving change logs from MCP servers to trace the
workflows. Atmosphere constraints meant CDC might solely be enabled partially,
limiting the breadth of captured information.

Different potential sources—resembling front-end/back-end community site visitors,
filesystem modifications, extra persistence layers, and even debugging
breakpoints—stay viable choices for finer-grained discovery. Even with
partial CDC, the insights proved invaluable in linking UI habits to underlying
information modifications and enriching the system blueprint.

Server Logic Inferance

We then added extra context by supplying
typelibs that have been extracted from the native binaries, and saved procedures,
and schema extracted from the database. At this level with details about
structure, presentation logic, and DB modifications, the server logic may be inferred,
which saved procedures are probably known as, and which tables are concerned for
most strategies and interfaces outlined within the native binaries. This course of leads
to an Inferred Server Logic Spec. LLM helped in proposing probably relationships
between App tier code and procedures / tables, which we then validated by
noticed information flows.

Prior Makes an attempt

Earlier than we arrived at this method, we tried

• brute-force methodology: Added all meeting features right into a workspace, and used
  the LLM agent to make it humanly readable pseudocode. Confronted a number of challenges
  with this. Ran out of the 1 million context window as LLM tried to ultimately
  load all features on account of dependencies (references it encountered e.g. perform
  calls, and different features referencing present one)
• Break up the set of features into a number of batches, a file every with 100s of
  features, after which use LLM to research every batch in isolation. We confronted quite a bit
  of hallucination points, and file dimension points whereas streaming to mannequin. A couple of
  features have been transformed meaningfully however a whole lot of different features did not make
  any-sense in any respect, all seemed like related capabilities, on cross checking we
  realised the hallucination impact.
• The following try was to transform the features separately, to
  guarantee LLM is supplied with a contemporary slender window of context to restrict
  hallucination. We confronted a number of challenges (API utilization restrict, charge
  limits) – We could not confirm what LLM translation of enterprise logic
  was proper or improper. Then we could not join the dots between these
  features. Fascinating word, we even discovered some C++ STDLIB features
  like
  std::vector::insert
  on this method. We discovered quite a bit have been truly unwind features purely
  used to name destructors when exception occurs (stack
  unwinding)
  destructors, catch block features. Clearly we would have liked to concentrate on
  enterprise logic and ignore the compiled library features, additionally combined
  into the binary

After these makes an attempt we determined to vary our method to slice the DLL based mostly
on purposeful space/workflow moderately than think about the entire meeting code.

Discovering the related perform

The primary problem within the purposeful space / workflow method is to discover a
hyperlink or entry level among the many 1000s of features.

One of many obtainable choices was to rigorously have a look at the constants and
strings within the DLL. We used the historic context: late Nineties or early 2000
frequent architectural sample adopted in that interval was to insert information into
the DB: was to both “choose for insert” or “insert/replace dealt with by saved
process” or through ADO (which is an ORM). Curiously we discovered all of the
patterns in numerous components of the system.

Our performance was about inserting or updating the DB on the finish of the
course of however we could not discover any insert or replace queries within the strings, no
saved process to carry out the operation both. For the performance we
have been on the lookout for, it occurred to really use a SELECT by SQL after which
up to date through ADO (activex information object microsoft library).

We obtained our break based mostly on the desk title talked about within the
strings/constants, and this led to discovering the perform which is utilizing that
SQL assertion. Preliminary have a look at that perform did not reveal a lot, it could possibly be
in the identical purposeful space however a part of a unique workflow.

Constructing the related subtree

ASM code, and our disassembly software, gave us the perform name reference
information, utilizing it we walked up the tree, assuming the assertion execution is one
of the leaf features, we navigated to the mother or father which known as this to
perceive its context. At every step we transformed ASM into pseudo code to
construct context.

Earlier after we transformed ASM to pseudocode utilizing brute-force we could not
cross confirm whether it is true. This time we’re higher ready as a result of we all know
to anticipate what could possibly be the potential issues that would occur earlier than a
sql execution. And use the context that we gathered from earlier steps.

We mapped out related features utilizing this name tree navigation, generally
we’ve to keep away from improper paths. We realized about context poisoning in a tough
manner, in-advertely we handed what we have been on the lookout for into LLM. From that
second LLM began colouring its output focused in the direction of what we have been wanting
for, main into improper paths and eroding belief. We needed to recreate a clear
room for AI to work in throughout this stage.

We obtained a excessive stage define of what the completely different features have been, and what
they could possibly be doing. For a given work circulation, we narrowed down from 4000+
features to 40+ features to cope with.

Multi-Go Enrichment

AI accelerated the meeting archaeology layer by layer, go by go: We
utilized multi go enrichment. In every go, we both navigated from leaf
node to prime of the tree or reverse, in every step we enriched the context of
the perform both utilizing its mother and father context or its little one context. This
helped us to vary the technical conversion of pseudocode right into a purposeful
specification. We adopted easy strategies like asking LLM to provide
significant methodology names based mostly on recognized context. After a number of passes we construct
out the whole purposeful context.

Validating the entry level

The final and demanding problem was to substantiate the entry perform. Typical
to C++, digital features made it tougher to hyperlink entry features at school
definition. Whereas performance seemed full beginning with the foundation node,
we weren’t certain if there’s some other extra operation taking place in a
mother or father perform or a wrapper. Life would have been simpler if we had debugger
enabled, a easy break level and evaluate of the decision stack would have
confirmed it.

Nonetheless with triangulation strategies, like:

1. Name stack evaluation
2. Validating argument signatures and the the return signature within the
   stack
3. Cross-checking with UI layer calls (e.g., associating methodology signature
   with the “submit” name from Net tier, checking parameter sorts and utilization, and
   validating in opposition to that context)