AI Composer

Design AI capabilities, agent configuration, and workflow automation

What This Node Does

Identifies specific AI capabilities needed (RAG, prediction, anomaly detection, NLP, computer vision), recommends implementation path (no-code vs code), designs AI Agent configuration, and defines workflow automation with triggers and feedback loops.

Role: AI Workflow Designer

Inputs

system_architecture	From System Architect
data_sources	From Data Stack Designer
problem_statement	From Problem Framer

Outputs

ai_workflow_config

AI capabilities, implementation path, agent config, automation logic

How to Configure on Coze

01Create an LLM Agent node, name it "AI Composer"

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

03Paste the system prompt

04Define inputs: system_architecture, data_sources, problem_statement

05Define output: ai_workflow_config (string)

06Connect from System Architect, Data Stack Designer, and Problem Framer

Tips & Common Issues

AI must serve a clear purpose — don't add AI just because you can

Focus on 1-2 core AI capabilities that directly solve the problem

The node recommends no-code/low-code vs code implementation

Include specific system prompt and tool definitions for your Agent

Example

Input

Architecture: 4-layer parking system. Data: Transport API + IoT sensors.

Output

{"ai_workflow_config": "AI Capabilities: (1) Time-series prediction model for parking availability (30min forecast). (2) RAG retrieval for parking policy FAQ. (3) Anomaly detection for sensor failures. Implementation: No-code platform (Coze) for RAG + notification workflow; Python script for prediction model. Agent Config: System prompt focuses on parking guidance; tools include availability lookup and prediction. Automation: Trigger when availability < 20%, action: notify users; feedback loop: retrain prediction weekly."}

Connects To

This node's output feeds into the Value Canvas node.

← Back to Tutorial Overview Next Node →