Large legacy applications are too vast — and too constantly changing — for AI to parse from source alone. That approach is expensive, incomplete, and prone to hallucination.
MDiQ builds a complete Knowledge Graph (node-edge map) of application code, objects and data using native parsing tools, directly on the IBM i server. CI/CD triggers granular updates so the repository stays current.
Browse, analyse and navigate every program component from the MDOpen extension in Visual Studio Code — bridging source-level detail and enterprise-level understanding for modernization, maintenance and documentation.
Native node-edge repositories of code, objects and data — updated granularly by CI/CD.
MoreCall charts, object dashboards, where-used tracing and ILE procedure-level mapping.
MoreGoverned access for IDEs and third-party tools via MCP, REST APIs and SQL stored procedures.
MoreBringing AI to your enterprise knowledge
Most AI development tools rely on analysing source code, documentation and prompts — an approach that becomes slow, expensive and difficult to govern at scale.
MDiQ changes the model. It gives AI structured knowledge of your application, so agents work with the right context, not the entire codebase — reducing AI cost and unnecessary source exposure, while MDChange brings every AI-driven change within proven DevOps governance.
The Midrange Dynamics AI Platform combines two complementary capabilities:
Using Model Context Protocol (MCP) and complemented by AI-Ready Knowledge Services, they allow any AI client to understand enterprise applications and safely participate in software delivery without bypassing governance.
MDiQ builds the cross-reference you always wished you had: a comprehensive node-edge knowledge graph of your IBM i application that maps not just source code, but the complete application structure and the relationships between its assets.
Programs, service programs, modules, procedures, database tables, files, fields, variables, parameters, subroutines, displays and other application entities are represented as interconnected nodes — creating a precise structural map of what exists, how it is related and how the application works as a whole.
This gives developers — and AI agents — a reliable way to navigate the application from any starting point, follow dependencies and understand impact across the system.
Instead of asking AI to guess how a legacy application works from isolated pieces of source code, MDiQ gives it the map of the application first.
Explore your IBM i application through purpose-built MDiQ views — or query the same Knowledge Graph directly through REST APIs as structured JSON.
One source of application knowledge. Built for developers, tools and AI.
Built on IBM i expertise
MDiQ builds its knowledge graph using native IBM i parsing developed by experienced IBM i experts — including contributors to IBM Redbooks and authors of commercial legacy analysis products.
Instead of asking AI to discover and infer application structure from millions of lines of source code, MDiQ provides that structure already parsed, mapped and connected.
Accurate and comprehensive
MDiQ uses IBM i-native parsing to extract and understand your application’s real structure — not just text, but meaning.
What MDiQ captures
Real application context
Parsers analyse source code and object metadata to map variable relationships across IBM i applications.
Not just where variables exist
True execution insight
Visibility into the actual logical execution elements inside service programs and modular applications — not only the object that contains them.
Examples of relationships captured
When a file is updated by a specific ILE procedure inside a service program, MDiQ identifies the precise procedure responsible — not merely the containing service program object.
Get to the answer, faster
No need to analyse millions of lines of source
Deterministic, trusted knowledge
Accurate, connected, actionable
Turn application knowledge into insight, documentation and governed change.
Remove guesswork from planning and scoping projects.
Get detailed metrics on your application — including object counts, complexity, dependencies and code distribution — to make better decisions, estimate effort and identify modernization priorities.
Export to a web-based documentation platform for creating and managing Markdown-based technical documentation.
Generate structured documentation directly from your application knowledge graph and edit it in a modern web interface. Keep your documentation current, searchable and linked to real application objects.
Visualise objects and their components.
Explore interactive diagrams that show how programs, files, procedures and other objects are connected. Quickly understand relationships, trace dependencies and see the bigger picture.
Extend analysis into governed change with MDChange integration.
Go from insight to action. Use the knowledge graph to check out related objects, manage changes, compile, implement and deploy — all within proven DevOps governance.
Complete node-edge mapping with native parsers on the IBM i server — not an off-platform reconstruction of the application.
CI/CD triggers granular repository updates so the knowledge graph stays aligned with the live application.
Trace calls and file usage to the exact ILE procedure — not only the service program that contains it.
Intelligent variable mapping, multi-level dependency chains and where-used tracing across even the largest IBM i systems.
Structured knowledge for MCP, REST and SQL clients — reducing hallucination by giving AI the graph, not the entire source tree.
MDDocs associates Markdown documentation with programs, procedures and database elements — and exports to PDF and Word.
For more info, a live demonstration, or to discuss your business and technical needs with the Midrange Dynamics team.
Request Info
