Arjun Prabhulal - Blog

Most agent bugs get blamed on the model.

30 AI and ML terms every developer should know.

Connect ADK agents to PostgreSQL databases using MCP Toolbox for enterprise-grade data access.

Understand the event system for real-time streaming and debugging.

Store and manage files, images, and data produced by agents.

Intercept and customize agent behavior at various execution points.

Manage conversation history, state, and memory for multi-turn interactions.

Optimize agent performance with context caching and compression techniques.

Understanding the Model Context Protocol - architecture, connection types, and production patterns.

Connect your agents to external services for version control and web content extraction.

Build agents that leverage multiple tools together to accomplish complex tasks.

Transform OpenAPI-defined APIs into agent tools and configure authentication for secure access.

Build custom functions that add specialized capabilities to your agents beyond built-in tools.

Build agents that can search across your enterprise data using the Vertex AI Search built-in tool.

Learn how to use the Vertex AI RAG Engine built-in tool to create grounded agents with your own data.

Explore the Google Search and Code Executor built-in tools.

Compose multiple agents into hierarchical systems for complex applications using agent composition patterns.

Create dynamic task flows with sequential, loop, and parallel workflows in Google ADK.

Build intelligent, model-powered agents with Google ADK.

Learn how to set up and run ADK agents using three different methods: command-line interface, web interface, and programmatic Python approach.

Introduction to ADK – Overview, environment setup, and your first agent.

Build and manage AI agents without coding using Google ADK Visual Agent Builder

RAG implementation using Gemini API's File Search Tool