# context-engineering-domain-understanding-johnson-2025-07-23

## Veille

Context Engineering - Domain Understanding - DICE - Rod Johnson - LLM - Domain Model - Embabel

## Titre Article

Context Engineering Needs Domain Understanding

## Date

2025-07-23

## URL

https://medium.com/@springrod/context-engineering-needs-domain-understanding-b4387e8e4bf8

## Keywords

Context Engineering, Domain Understanding, LLM, Gen AI, Domain-Integrated Context Engineering (DICE), AI Agents, Business Value, Domain Model, Embabel, Prompt Engineering, bidirectional communication, structured context, testability

## Authors

Rod Johnson

## Ton

**Profile:** Professional-technical | First-person thought leader | Analytical-prescriptive | Expert

Johnson (creator of the Spring framework) adopts an authoritative technical voice combining software architecture expertise and Gen AI insight. The introduction of the new DICE (Domain-Integrated Context Engineering) concept reveals a framework-builder mindset. Assured technical language (domain objects, bidirectional communication, structured persistence, Cypher queries) aimed at enterprise architects. The critique → proposal → benefits structure reflects systematic thinking. The emphasis on integration with existing systems rather than isolated capabilities shows a pragmatic enterprise focus. Measured, authoritative tone, avoiding both dismissive skepticism and naive enthusiasm. Typical of technical thought leadership (Martin Fowler, Kent Beck style) proposing architectural patterns grounded in practical experience.

## Pense-betes

- **"Context engineering"** more precise than "prompt engineering" for LLM applications
- **Traditional context engineering** neglects the bidirectional nature (inputs AND outputs) and the relationship with existing business applications
- **DICE (Domain-Integrated Context Engineering)** proposed: emphasize the domain model to structure context and consider LLM outputs
- **Domain objects** define targeted behaviors exposable to manual code AND to LLMs as tools
- **DICE benefits**: code to structure context, simpler/safer integration with existing systems, faster delivery through reuse, structured persistence, improved testability, better debugging/tracing, stronger context handling in multi-step flows
- **LLMs excel at natural language, but adding structure** makes them safer and more reliable
- **Gen AI's real business value** requires bridging the gap between LLM capabilities and proven existing systems
- **Domain integration is critical** to unlocking full business value; existing business applications = key adjacency for Gen AI

## RésuméDe400mots

The article "Context Engineering Needs Domain Understanding" by Rod Johnson introduces **Domain-Integrated Context Engineering (DICE)** as an evolution of context engineering for building more effective and robust LLM applications. Johnson begins by acknowledging "context engineering" as a valuable advance over "prompt engineering," defining it as the art and science of filling the LLM's context window with relevant information. He argues, however, that this definition is incomplete, as it neglects two crucial aspects: the bidirectional nature of communication with LLMs (what is sent *and* what is received) and the integration of LLM applications with business understanding and existing systems.

**DICE: Conceptual Extension**

To address these gaps, Johnson proposes DICE, which extends context engineering by emphasizing the use of a domain model to structure context and by considering LLM outputs in addition to inputs. The central idea: although LLMs excel at natural language, **adding structure to inputs and outputs** makes them safer and more reliable. DICE allows LLMs to "converse" using a business's established terminology and concepts, fostering better integration with existing applications. In this context, domain objects are not merely data structures but define targeted behaviors that can be exposed both to manually written code AND to LLMs as tools.

**Compelling Benefits of DICE**

The article highlights several compelling benefits of adopting DICE. First, it allows code to be used to structure context, turning a "delicate art" into a more scientific process where context can be refined, reasoned about, and tested. This also enables precise content filtering, improving results and saving tokens. Second, DICE facilitates simpler and safer integration with existing systems, moving beyond "demo" Gen AI applications toward real-world scenarios where agents need access to existing functionality. By working with domain objects, businesses can reuse their existing domain models and capitalize on hard-won business understanding.

**Additional Advantages**

Other advantages include faster delivery and improved quality through the reuse of domain models across applications and agents. DICE also offers structured persistence options, enabling more precise retrieval via existing technologies such as SQL or Cypher, a potential complement to vector search. The structure and encapsulation added by the domain model strengthen testability, debugging, and tracing, since information appears in observability tools in a structured, understandable format. Finally, domain integration helps manage context in multi-step flows, preventing quality degradation and controlling token costs.

**Strategic Positioning**

Johnson concludes that domain integration is paramount to unlocking the full business value of generative AI, positioning existing business applications as the key adjacency for Gen AI, rather than data science or LLMs alone. **The central argument**: domain model structure moves LLM capabilities from powerful-but-chaotic to controlled-and-reliable, an essential condition for enterprise adoption. By conceptualizing domain objects as entities carrying behaviors that can be exposed as tools, DICE bridges the conceptual gap between LLM potential and enterprise reality, offering a framework for systematic, reliable, value-creating Gen AI integration into existing business workflows. This pragmatic perspective recognizes that **Gen AI's value does not lie in isolation**, but in harmonious integration with the proven systems where domain knowledge resides.

## GrapheDeConnaissance

- Rod Johnson —a_créé→ DICE (METHODOLOGIE, 0.99)
- Rod Johnson —a_créé→ Spring (TECHNOLOGIE, 0.99)
- Rod Johnson —a_créé→ Embabel (ORGANISATION, 0.99)
- DICE —est_basé_sur→ context engineering (METHODOLOGIE, 0.98)
- DICE —améliore→ context engineering (METHODOLOGIE, 0.97)
- context engineering —améliore→ prompt engineering (METHODOLOGIE, 0.95)
- Andrej Karpathy —a_créé→ context engineering (METHODOLOGIE, 0.97)
- DICE —utilise→ modèle de domaine (CONCEPT, 0.97)
- modèle de domaine —améliore→ intégration systèmes existants (CONCEPT, 0.93)
- Embabel —utilise→ DICE (METHODOLOGIE, 0.9)
- MCP —s_oppose_à→ DICE (METHODOLOGIE, 0.75)
- Martin Fowler —a_créé→ bounded contexts (CONCEPT, 0.92)
- bounded contexts —fait_partie_de→ modèle de domaine (CONCEPT, 0.9)

---
Canonical: https://www.thekb.eu/en/fiches/context-engineering-domain-understanding-johnson-2025-07-23/