Update ARCHITECTURE.md

ARCHITECTURE.md

@@ -1,17 +1,18 @@
 # AISA Architecture
 
-This document outlines the layered architectural model introduced in
-**AISA — Agentic AI Systems Architecture**.
 
-AISA models agentic AI systems as composed systems in which behavior
-emerges from the interaction between reasoning, execution,
-infrastructure, evaluation, and governance.
 
-![Agentic AI Systems Architecture (AISA)](https://cdn-uploads.huggingface.co/production/uploads/676bac31dd95830fd9adf3cf/N6mUf5D7FzV5PXOl2Bm3z.png)
+AISA models agentic AI systems as composed systems in which behavior emerges from the interaction between reasoning, execution, infrastructure, evaluation, and governance.
 
 ---
 
-## Layer Responsibilities (Summary)
+<img src="https://cdn-uploads.huggingface.co/production/uploads/676bac31dd95830fd9adf3cf/N6mUf5D7FzV5PXOl2Bm3z.png"
+     alt="Agentic AI Systems Architecture (AISA)"
+     width="800"/>
+
+---
+
+## Layer Responsibilities
 
 ### Governance, Ethics & Policy Layer
 - AI policies and transparency standards  
@@ -78,22 +79,20 @@ infrastructure, evaluation, and governance.
 
 ## Architectural Principles
 
-![AISA Architectural Principles](https://cdn-uploads.huggingface.co/production/uploads/676bac31dd95830fd9adf3cf/NZACvevXzxQR2dye4PNh_.png)
+<img src="https://cdn-uploads.huggingface.co/production/uploads/676bac31dd95830fd9adf3cf/NZACvevXzxQR2dye4PNh_.png"
+     alt="AISA Architectural Principles"
+     width="700"/>
+
+---
 
-**1. Separation of Concerns**  
-Clear separation between system responsibilities to prevent mixing reasoning, permissions, and orchestration logic.
+**1. Separation of Concerns**  :Clear separation between system responsibilities to prevent mixing reasoning, permissions, and orchestration logic.
 
-**2. Assurance-by-Design**  
-Evaluation, monitoring, and governance are built into the architecture from the start, not added after deployment.
+**2. Assurance-by-Design**  :Evaluation, monitoring, and governance are built into the architecture from the start, not added after deployment.
 
-**3. Dual-Plane Design**  
-A clear distinction between the data plane (runtime execution) and the control plane (policies, permissions, and budgets).
+**3. Dual-Plane Design**  :A clear distinction between the data plane (runtime execution) and the control plane (policies, permissions, and budgets).
 
-**4. Contract-Driven Interfaces**  
-Structured and machine-checkable interfaces reduce ambiguity and improve testing and auditability.
+**4. Contract-Driven Interfaces**  :Structured and machine-checkable interfaces reduce ambiguity and improve testing and auditability.
 
-**5. Continuous Improvement Loop**  
-Agent behavior evolves continuously through feedback-driven updates to prompts, tools, and policies.
+**5. Continuous Improvement Loop**  :Agent behavior evolves continuously through feedback-driven updates to prompts, tools, and policies.
 
-**6. Practical Deployability**  
-The architecture accounts for real-world constraints such as cost, latency, observability, access control, and versioning.
+**6. Practical Deployability**  :The architecture accounts for real-world constraints such as cost, latency, observability, access control, and versioning.