Build an AI-Powered Tech Radar Advisor with SQL DB, RAG, and Routing Agents

Go to Workflow
12,453 views
Built by Sean Lon Sean Lon
Created on June 05, 2026

Description

AI-Powered Tech Radar Advisor

This project is built on top of the famous open source ThoughtWorks Tech Radar.

You can use this template to build your own AI-Powered Tech Radar Advisor for your company or group of companies.

Target Audience

This template is perfect for:
Tech Audit & Governance Leaders:** Those seeking to build a tech landscape AI platform portal.
Tech Leaders & Architects:** Those aiming to provide modern AI platforms that help others understand the rationale behind strategic technology adoption.
Product Managers:** Professionals looking to align product innovation with the company's current tech trends.
IT & Engineering Teams:** Teams that need to aggregate, analyze, and visualize technology data from multiple sources efficiently.
Digital Transformation Experts:** Innovators aiming to leverage AI for actionable insights and strategic recommendations.
Data Analysts & Scientists:** Individuals who want to combine structured SQL analysis with advanced semantic search using vector databases.
Developers:** Those interested in integrating RAG chatbot functionality with conversation storage.

1. Description

Tech Constellation is an AI-powered Tech Radar solution designed to help organizations visualize and steer their technology adoption strategy.
It seamlessly ingests data from a Tech Radar Google Sheet—converting it into both a MySQL database and a vector index—to consolidate your tech landscape in one place.

The platform integrates an interactive AI chat interface powered by four specialized agents:
AI Agent Router:** Analyzes and routes user queries to the most suitable processing agent.
SQL Agent:** Executes precise SQL queries on structured data.
RAG Agent:** Leverages semantic, vector-based search for in-depth insights.
Output Guardrail Agent:** Validates responses to ensure they remain on-topic and accurate.

This powerful template is perfect for technology leaders, product managers, engineering teams, and digital transformation experts looking to make data-driven decisions aligned with strategic initiatives across groups of parent-child companies.

2. Features
Data Ingestion
A Google Sheet containing tech radar data is used as the primary source.
The data is ingested and converted into a MySQL database.
Simultaneously, the data is indexed into a vector database for semantic (vector-based) search.
Interactive AI Chat
Chat Integration:** An AI-powered chat interface allows users to ask questions about the tech radar.
Customizable AI Agents:**
AI Agent Router: Determines the query type and routes it to the appropriate agent.
SQL Agent: Processes queries using SQL on structured data.
RAG Agent: Performs vector-based searches on document-like data.
Output Guardrail Agent: Validates queries and ensures that the responses remain on-topic and accurate.

Usage Examples
Tell me, is TechnologyABC adopted or on hold, and why?
List all the tools that are considered part of the strategic direction for company3 but are not adopted.

Project Links & Additional Details

GitHub Repository (Frontend Interface Source Code):** github.com/dragonjump/techconstellation
Try It:** https://scaler.my

Nodes Used (16)

AI Agent
@n8n/n8n-nodes-langchain.agent
Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic
Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm
Code
n8n-nodes-base.code
Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader
Embeddings Google Gemini
@n8n/n8n-nodes-langchain.embeddingsGoogleGemini
Google Docs
n8n-nodes-base.googleDocs
Google Drive
n8n-nodes-base.googleDrive
Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini
Google Sheets
n8n-nodes-base.googleSheets
Groq Chat Model
@n8n/n8n-nodes-langchain.lmChatGroq
MySQL
n8n-nodes-base.mySql
Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone
Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow
Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore