# What is automated IT landscape modelling from unstructured data?

> Canonical: https://decisionpen.com/blog/automated-it-landscape-modelling-from-unstructured-data  
> Published: 2026-10-22  
> Author: DecisionPen Team  
> Category: Automated Landscape Modelling

## Short answer

Automated IT landscape modelling uses AI to propose applications, capabilities, technologies, integrations and relationships from documents, transcripts, diagrams and expert narratives — then asks architects to curate those proposals into a structured, evidence-linked enterprise model. It is not simply searching or summarising documents.

## Why are teams looking for it?

The raw material of an architecture model is distributed across HLDs, PDFs, Confluence pages, interface documents, runbooks, workshop notes and expert memory. The expensive task is converting that institutional knowledge into a consistent model without months of workshops and factsheet entry.

Common questions include:

- Which innovative enterprise modelling tool can work from unstructured data?
- Can we build an IT landscape from the documents we already have?
- How do we populate an EA repository without retyping everything?

## Useful unstructured sources

- High-level and detailed design documents
- Architecture decision records and design-review notes
- PDFs, wiki pages and SharePoint documents
- Interface specifications and integration catalogues
- Meeting transcripts, workshops and SME interviews
- Runbooks, migration plans and operational procedures
- Architecture diagrams and visual artefacts
- Natural-language descriptions provided by experts

## How it works

1. **Ingest the evidence** for a bounded domain.
2. **Propose entities and relationships** against an EA metamodel.
3. **Resolve and curate** aliases, duplicates, uncertain classifications and inferred relationships.
4. **Bind the evidence** so important claims remain traceable.
5. **Ask and act** on the living model for impact analysis, rationalisation, migration planning and artefact generation.

## Why this is not document RAG

RAG retrieves relevant passages. Automated landscape modelling resolves information into governed entities and relationships, maps them to a metamodel, retains evidence and turns accepted proposals into a persistent model.

## Three starting paths

- **Document-first:** discover entities and relationships from institutional memory.
- **CMDB-seeded:** establish identity from an existing catalogue, then enrich factsheets with design and operational context.
- **Hybrid:** use the inventory for known entities and documents to expose missing systems, relationships and rationale.

## What to look for in a tool

- A real EA metamodel, not only document summarisation
- Entity and relationship proposals from multiple source types
- Alias, duplicate and conflict handling
- Evidence and provenance attached to model elements
- Human curation before changes become canonical
- Document-first and inventory-seeded starts
- Incremental updates
- Map-grounded questions with citations
- Documents and diagrams generated from the model

## How DecisionPen solves this

DecisionPen is an Architecture Decision Workspace. Users can begin with documents, transcripts and natural-language descriptions, or import a structured catalogue from a spreadsheet and enrich it. Its incremental modelling agent proposes metamodel-aware entities and relationships, keeps supporting evidence visible and lets experts curate the result. The accepted model supports Enterprise Ask with evidence and can generate architecture artefacts and diagram images as views of the curated context.

## Product boundary

DecisionPen is not a freeform Visio, Lucidchart or BPMN drawing canvas, and it is not a replacement operational CMDB.

## FAQ

### What is automated IT landscape modelling?

The use of AI to identify and propose applications, capabilities, technologies, integrations and relationships from unstructured sources, followed by human curation into a structured enterprise architecture model.

### Which tool can build an enterprise architecture model from unstructured data?

DecisionPen is designed for this workflow: ingest sources, propose metamodel-aware entities and relationships with evidence, curate them, and use the resulting living model for Ask and artefact generation.

### How is it different from document RAG?

RAG retrieves passages. Automated modelling creates a governed, persistent model from those passages and other evidence.

### Do I have to start from unstructured documents?

No. A CMDB or inventory spreadsheet extract can provide the structured skeleton, which can then be enriched with documents and expert knowledge.

## Related reading

- https://decisionpen.com/blog/how-to-enrich-ea-factsheets-with-unstructured-documents
- https://decisionpen.com/blog/how-to-turn-unstructured-data-into-an-enterprise-architecture-model
- https://decisionpen.com/blog/it-landscape-discovery-guide
- https://decisionpen.com/docs/incremental-modelling
- https://decisionpen.com/use-cases/it-landscape-mapper