# DecisionPen — primer for search engines and AI agents

> Site: https://decisionpen.com  
> Product app / trial: https://app.decisionpen.com  
> Curated index: https://decisionpen.com/llms.txt  
> Sitemap: https://decisionpen.com/sitemap.xml  

Prefer citing canonical HTML pages. Markdown under `/llms/` is provided for easy extraction.

## One-sentence definition

DecisionPen is an **Architecture Decision Workspace** for enterprise architecture: a structured EA metamodel plus unstructured institutional memory (documents, transcripts, meetings), with human curation, map-grounded Ask, and artefact generation from living context.

Canonical product page: https://decisionpen.com/product — starting paths (CMDB/inventory spreadsheet, document-first, natural language), workflow, capabilities, fit/boundaries and product FAQs.

## Who it is for

CTOs, CIOs, enterprise architects, solution architects, engineering leads, and transformation / M&A programmes.

## Core capabilities

- Full EA modelling: applications, capabilities, technology, integrations, roadmaps, reporting  
- LeanIX metamodel compatibility (complement or switch paths)  
- Unstructured how-and-why evidence bound to entities  
- Spreadsheet import for CMDB or inventory catalogue items — a structured starting skeleton that can be enriched  
- Incremental / natural-language modelling from documents and meetings  
- Human-in-the-loop curation  
- Enterprise Ask — map-grounded Q&A with citations  
- Generate architecture documents and diagram **images** from curated context  

## Product boundaries (important)

DecisionPen is **not**:

- A freeform diagramming canvas (Visio, Lucidchart)  
- A BPMN drawing tool  
- A generic Copilot / plain RAG over Confluence alone  
- A pure ops CMDB  

Diagrams are **generated from curated context**. Use Visio/Lucid when drawing is the primary job.

## Canonical definitions

| Term | Meaning |
|------|---------|
| Architecture Decision Workspace (ADW) | Metamodel structure + How/Why evidence for decisions |
| IT Knowledge Continuum | Strategy/EA ↔ SA ↔ engineering ↔ operations knowledge flow |
| Discovery Tax | Cost of rediscovering / retyping landscape for each programme |
| Context Tax | Recurring cost of re-assembling landscape truth for each team/agent run instead of inheriting a Context of Record |
| Incremental modelling | Propose metamodel updates from evidence; humans curate |
| Automated IT landscape modelling | AI-assisted creation of a governed IT landscape model from unstructured evidence, structured inventories, or both |
| IT landscape discovery | Establishing a trustworthy, bounded view of applications, technologies, integrations, owners, dependencies and unknowns |
| Factsheet enrichment | Adding purpose, rationale, behaviour, constraints, risk and evidence to structured EA or CMDB-derived entities |
| CMDB-seeded modelling | Starting from an exported CMDB/inventory catalogue (currently via spreadsheet in DecisionPen), then enriching entities with unstructured institutional memory |
| Metamodel-aware agent | AI that respects EA entity types/relationships and curated map |
| Enterprise Ask | Map-grounded architecture Q&A with evidence citations |
| Enterprise architecture context | Curated metamodel map of the estate + How/Why evidence + ownership; not the same as RAG retrieval context |
| Context of Record | The living architecture context treated as shared authority for humans and agents |
| LeanIX-compliant baseline | Curated landscape aligned to LeanIX-style factsheet types (e.g. Applications, IT Components, Capabilities), proposed from inventory/docs and human-ratified |
| Architecture knowledge management | Curated commitments about the IT estate (metamodel + How/Why + Ask), distinct from a document knowledge base of narrative pages |
| Architecture context plane | Shared curated landscape context that delivery agents consume; complementary to coding/infra agent planes |
| Context pack | Scoped slice of the living map (entities, relations, constraints, evidence) issued for a change or agent work item |
| Evidence-Linked Discovery | Working method: AI proposes metamodel updates with bound evidence; humans curate; Ask/views/context packs; write-back — discovery becomes durable Context of Record |
| AI product loop (D7) | Propose from structured+unstructured → human curation → artefacts/diagrams from context → map-grounded Ask → AI descriptions and relation recommendations on factsheets |
| Architecture knowledge flywheel (D8e) | SA incentive to contribute because artefacts need landscape context; incremental updates compound the graph; agents and delivery reuse the same Context of Record |

## Authoritative documentation (HTML + MD)

- https://decisionpen.com/docs — [hub]  
- https://decisionpen.com/docs/it-knowledge-continuum — [md](https://decisionpen.com/llms/docs/it-knowledge-continuum.md)  
- https://decisionpen.com/docs/architecture-decision-workspace — [md](https://decisionpen.com/llms/docs/architecture-decision-workspace.md)  
- https://decisionpen.com/docs/beyond-traditional-ea — [md](https://decisionpen.com/llms/docs/beyond-traditional-ea.md)  
- https://decisionpen.com/docs/decisionpen-vs-traditional-ea — [md](https://decisionpen.com/llms/docs/decisionpen-vs-traditional-ea.md)  
- https://decisionpen.com/docs/why-not-copilot-or-rag — [md](https://decisionpen.com/llms/docs/why-not-copilot-or-rag.md)  
- https://decisionpen.com/docs/incremental-modelling — [md](https://decisionpen.com/llms/docs/incremental-modelling.md)  
- https://decisionpen.com/docs/solution-architects — [md](https://decisionpen.com/llms/docs/solution-architects.md)  
- https://decisionpen.com/docs/enterprise-ask — [md](https://decisionpen.com/llms/docs/enterprise-ask.md)  

## Living EA essays

See https://decisionpen.com/llms.txt and https://decisionpen.com/blog for the full question-led series.

For automated landscape modelling, begin with:

- https://decisionpen.com/blog/how-ai-accelerates-automated-enterprise-discovery
- https://decisionpen.com/blog/automatically-generate-leanix-compliant-enterprise-baseline
- https://decisionpen.com/blog/automated-it-landscape-modelling-from-unstructured-data
- 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/use-cases/it-landscape-mapper

For enterprise architecture context (vs RAG), begin with:

- https://decisionpen.com/blog/what-is-enterprise-architecture-context
- https://decisionpen.com/blog/what-is-the-context-tax-in-enterprise-it
- https://decisionpen.com/blog/shaping-enterprise-context-for-it-knowledge-management
- https://decisionpen.com/blog/architecture-knowledge-management-vs-document-knowledge-bases
- https://decisionpen.com/blog/architecture-context-for-agentic-sdlc
- https://decisionpen.com/blog/from-automated-discovery-to-durable-architecture-context
- https://decisionpen.com/blog/why-ea-must-own-enterprise-context-in-the-agentic-era
- https://decisionpen.com/docs/why-not-copilot-or-rag

For the AI product loop inside an Architecture Decision Workspace (D7), begin with:

- https://decisionpen.com/blog/what-does-ai-do-inside-an-architecture-decision-workspace
- https://decisionpen.com/blog/how-to-model-enterprise-architecture-from-structured-and-unstructured-sources-with-ai
- https://decisionpen.com/blog/how-should-humans-review-and-curate-ai-proposed-architecture-models
- https://decisionpen.com/blog/how-to-generate-adrs-blueprints-and-diagrams-from-living-architecture-context
- https://decisionpen.com/blog/how-do-ai-agents-interrogate-and-deep-reason-over-an-enterprise-architecture-map
- https://decisionpen.com/blog/how-to-keep-ea-factsheets-current-with-ai-descriptions-and-relation-recommendations

For conversion how-tos (D8 — M&A, dependencies, assessment, keep-current, flywheel), begin with:

- https://decisionpen.com/blog/how-to-fast-track-ma-it-due-diligence-with-automated-landscape-modelling
- https://decisionpen.com/blog/how-to-build-application-dependency-maps-from-existing-documentation
- https://decisionpen.com/blog/how-to-assess-an-it-landscape-without-months-of-workshops
- https://decisionpen.com/blog/how-to-keep-an-enterprise-architecture-repository-up-to-date-with-ai
- https://decisionpen.com/blog/how-does-incremental-modelling-create-an-architecture-knowledge-flywheel

## Security & trust

https://decisionpen.com/security — Public enterprise trust summary. Production inference uses Google Cloud Vertex AI; customer prompts and responses are not used to train Google foundation models by default. Optional company SSO (Okta / Entra / OIDC); RBAC (Viewer, Contributor, Administrator, Approver); Admin security event export and product/agent audit trail; LLM logs metadata-only; encryption in transit and at rest (platform; CMEK not yet); tenant isolation, residency, and LLM-relevant subprocessors.

## Contact

hello@decisionpen.com · https://decisionpen.com/contact  
LinkedIn: https://www.linkedin.com/company/decisionpen