Building a Data Analyst Agent with Google ADK.

A developer built a Data Analyst Agent using Google's open-source Agent Development Kit (ADK) and the Gemini 2.5 Flash model, demonstrating agentic workflows over single-prompt chat completion. The build hit two configuration errors — a 404 NOT_FOUND from an outdated model name and a 400 INVALID_ARGUMENT from a malformed model string — which were resolved by correcting the .env and agent.py files and refreshing credentials via gcloud auth. The agent then returned a clean 200 OK and successfully processed data requests and generated summaries.

At the recent Build with Google AI event in Kisumu, the core focus centered around a fundamental shift: moving from single-prompt chat completion to Agentic Workflows . Instead of asking one LLM to solve a complex problem in a single turn, agentic patterns split tasks across specialized, autonomous units coordinated by an orchestrator. To explore this hands-on, I built a Data Analyst Agent using the Google Agent Development Kit ADK . Here's a quick look at the build, the bugs I bumped into, and the concepts behind them. Google's Agent Development Kit ADK is an open-source, code-first Python framework for building and testing AI agents. It gives you: adk web to monitor API calls, inspect payloads, and debug agent reasoning in real time. A key concept when building agentic systems is the Model Context Protocol MCP . MCP serves as a standardized bridge between AI models and external data sources or execution environments. Rather than hardcoding custom integrations for every database or API, MCP gives agents a uniform interface to securely read context, access files, and call tools across different systems. I instantiated the agent in agent.py using standard ADK imports: python from google.adk import Agent data agent = Agent name="data analyst", model="gemini-2.5-flash", instruction="You are an expert Data Analyst AI...", During local testing in the ADK web UI, I hit two quick configuration bumps: 404 NOT FOUND gemini-1.5-flash , causing the platform to reject the request. gemini-2.5-flash . 400 INVALID ARGUMENT "gemini-2.5 flash" instead of a hyphen , breaking the API URL parser. .env and agent.py . After fixing the config files, I refreshed my local session using gcloud auth application-default login . Re-running adk web gave a clean 200 OK status, allowing the agent to successfully process data requests and generate summaries.