CodeWhiz: My AI Assistant for Backend Developers

I recently built Knowledge Agent, an AI-powered assistant designed to help backend developers with questions about Java, Spring Boot, Node.js, Python, Go, and related frameworks. It’s live on Telex and ready to assist anyone exploring backend development.

What Knowledge Agent Does

Knowledge Agent is a real-time AI assistant. Developers can ask questions through a webhook or directly in the Telex platform. It answers with clear, concise explanations, often including code examples. For example, you can ask it how dependency injection works in Spring Boot or request best practices for API design.

Check it out here: https://telex.im/telex-ai-intergration/home/colleagues/019a4ea1-f657-73b3-8499-57b769c9ce51/019a4ea1-b942-73af-823c-1aa0c72c8edb

My agent provides instant backend development guidance for learning or troubleshooting.

Using Telex as a Platform

Telex is an AI agent platform, similar to Slack but optimized for communities, bootcamps, and educational settings. It allows agents like mine to receive messages, process them, and respond programmatically in real time. Learn more about Telex here: Telex homepage.

How I Built Knowledge Agent

I leveraged several Mastra features to build my agent:

Webhook Integration – I set up a webhook in Spring Boot that receives developer questions from Telex and sends them to my AI engine.

@PostMapping("/hook")

public ResponseEntity<Map<String,Object>> handle(@RequestBody Map<String,Object> payload) {

    String text = service.extractUserText(payload);

    String answer = service.generateResponse(text);

    return ResponseEntity.ok(Map.of("result", answer));

}

Google ADK – This Java client allowed me to send prompts to Google Gemini AI and receive structured responses.

String prompt = "You are a backend dev assistant. Question: " + query;

GenerateContentResponse resp = client.models.generateContent("gemini-2.0-flash", prompt, null);

return resp.text();

Real-Time Response Handling – Using Spring Boot and the webhook, my agent responds in real time to messages from developers on Telex.

Environment Management & Security – API keys and credentials are managed safely using environment variables, keeping my system secure while connecting to Gemini.

Why This Project Matters

This agent demonstrates how AI can assist developers in real time. It’s perfect for bootcamps, communities, or educational platforms where learners need instant support. By combining Mastra features, Telex as a platform, and Google Gemini AI, I created a tool that helps developers learn and troubleshoot efficiently.

Explore my agent here: https://telex.im/telex-ai-intergration/home/colleagues/019a4ea1-f657-73b3-8499-57b769c9ce51/019a4ea1-b942-73af-823c-1aa0c72c8edb

Learn more about Telex here: Telex.im

Java #SpringBoot #AI #GoogleGemini #BackendDev #Webhooks