System Architect

Design system components, data flow, and BIM/Digital Twin connections

What This Node Does

Designs a 4-layer architecture (sensing → data → logic → presentation), maps data flow between layers, assesses smart capability level (perception → coordination → prediction → adaptation → value delivery), and connects to BIM/Digital Twin concepts.

Role: Smart City System Architect

Inputs

problem_statement	From Problem Framer
data_sources	From Data Stack Designer
project_domain	From initial input

Outputs

system_architecture

Component layers, data flow, smart capability assessment, BIM/DT connections

How to Configure on Coze

01Create an LLM Agent node, name it "System Architect"

02Model: doubao-seed-2-0-lite-260215, temperature 0.3

03Paste the system prompt

04Define inputs: problem_statement, data_sources, project_domain

05Define output: system_architecture (string)

06Connect from Problem Framer and Data Stack Designer

Tips & Common Issues

The 4 layers are: Sensing (data collection), Data (storage/structure), Logic (decisions/algorithms), Presentation (user interaction)

BIM/Digital Twin connection is required — even a simple one counts

Smart capability levels go from basic (perception) to advanced (value delivery)

Keep the architecture implementable as a student prototype

Example

Input

Problem: CUHK parking shortage. Data: Transport Dept API + IoT sensors.

Output

{"system_architecture": "Sensing Layer: Transport Dept parking API (real-time), IoT ultrasonic sensors (prototype). Data Layer: PostgreSQL for historical data, Redis cache for real-time availability. Logic Layer: Availability prediction model (time-series), notification trigger engine. Presentation Layer: Web dashboard + mobile notifications. Smart Level: Prediction (level 3/5). BIM Connection: Digital twin of campus parking structures for visualization."}

Connects To

This node's output feeds into the AI Composer node.

← Back to Tutorial Overview Next Node →