Agent Bricks: Domain-Specific High-Quality AI Agent Systems
Who this is for:
Architecture / Concept Overview: Agent Bricks: Domain-Specific High-Quality AI Agent Systems
Agent Bricks provide a structured starting point that teams customise with their own data, tools, and guardrails.
%%{init: {"theme":"base","themeVariables":{"background":"#0B0E14","primaryTextColor":"#E0E6ED","lineColor":"#5D6470","darkMode":true,"primaryColor":"#2E4A4A","secondaryColor":"#374151","secondaryTextColor":"#E0E6ED","tertiaryColor":"#111827","tertiaryTextColor":"#E0E6ED","edgeLabelBackground":"#1f2937"}}}%%
flowchart LR
classDef source fill:#3F4B59,stroke:#9CA3AF,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef ingestion fill:#5A4B36,stroke:#C9A86B,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef processing fill:#535072,stroke:#8E82B4,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef storage fill:#2E4A4A,stroke:#5FAFA8,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef serving fill:#3D5550,stroke:#6BB7AA,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef governance fill:#5A3F52,stroke:#C28BB0,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
TEMPLATE[Agent Brick Template] -->|Configure| DATA[Your Data Sources]
TEMPLATE -->|Configure| TOOLS_C[Your Tools]
TEMPLATE -->|Configure| PROMPTS[Your Prompts]
DATA -->|Build| AGENT[Customised Agent]
TOOLS_C -->|Build| AGENT
PROMPTS -->|Build| AGENT
AGENT -->|Evaluate| EVAL[Agent Evaluation]
EVAL -->|Deploy| EP[Serving Endpoint]
EP -->|Monitor| MON[Production Monitoring]
TEMPLATE:::governance
DATA:::source
TOOLS_C:::ingestion
PROMPTS:::processing
AGENT:::serving
EVAL:::storage
EP:::serving
MON:::governance
*Agent Bricks workflow: select a template, customise with your data and tools, evaluate, and deploy.*
%%{init: {"theme":"base","themeVariables":{"background":"#0B0E14","primaryTextColor":"#E0E6ED","lineColor":"#5D6470","darkMode":true,"primaryColor":"#2E4A4A","secondaryColor":"#374151","secondaryTextColor":"#E0E6ED","tertiaryColor":"#111827","tertiaryTextColor":"#E0E6ED","edgeLabelBackground":"#1f2937"}}}%%
graph TD
classDef source fill:#3F4B59,stroke:#9CA3AF,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef ingestion fill:#5A4B36,stroke:#C9A86B,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef processing fill:#535072,stroke:#8E82B4,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef storage fill:#2E4A4A,stroke:#5FAFA8,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef serving fill:#3D5550,stroke:#6BB7AA,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef governance fill:#5A3F52,stroke:#C28BB0,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
BRICKS[Agent Bricks] --> RAG_BRICK[RAG Agent Brick]
BRICKS --> SQL_BRICK[SQL Agent Brick]
BRICKS --> SUPPORT_BRICK[Support Agent Brick]
BRICKS --> CUSTOM[Custom Agent Brick]
RAG_BRICK --> RAG_VS[Vector Search Retriever]
RAG_BRICK --> RAG_LLM[LLM Generator]
SQL_BRICK --> SQL_TOOL[SQL Execution Tool]
SQL_BRICK --> SCHEMA_AWARE[Schema-Aware Prompting]
SUPPORT_BRICK --> KB[Knowledge Base]
SUPPORT_BRICK --> ESCALATION[Escalation Logic]
BRICKS:::governance
RAG_BRICK:::processing
SQL_BRICK:::storage
SUPPORT_BRICK:::serving
CUSTOM:::ingestion
RAG_VS:::source
RAG_LLM:::source
SQL_TOOL:::source
SCHEMA_AWARE:::source
KB:::source
ESCALATION:::source
*Available Agent Brick templates for common enterprise use cases.*
Key Terms
Prerequisites and Setup
- Databricks workspace with Unity Catalog, Model Serving, and Vector Search.
databricks-agentspackage installed.- A Vector Search index (for RAG bricks) or SQL tables (for SQL bricks).
Step-by-Step Implementation
Configuration Reference
| Parameter | Default | Description |
|---|---|---|
vector_search_index | — | Unity Catalog name of the vector index |
vector_search_endpoint | — | Vector Search endpoint name |
llm_endpoint | — | Foundation model serving endpoint |
system_prompt | — | System message defining agent behaviour |
top_k | 5 | Number of documents to retrieve |
max_tokens | 500 | Maximum response length |
temperature | 0.1 | Sampling temperature |