{"slug": "building-a-data-analyst-agent-with-google-adk", "title": "Building a Data Analyst Agent with Google ADK.", "summary": "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 The build hit two configuration errors — a 404 NOT_FOUND from an outdated model name and a 400 INVALID_ARGUMENT from a malformed model string — which were resolved by correcting the .env and agent.py files and refreshing credentials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.", "body_md": "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**.\n\nInstead 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.\n\nTo 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.\n\nGoogle's Agent Development Kit (ADK) is an open-source, code-first Python framework for building and testing AI agents. It gives you:\n\n`adk web`) to monitor API calls, inspect payloads, and debug agent reasoning in real time.\nA 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.\n\nRather 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.\n\nI instantiated the agent in `agent.py` using standard ADK imports:\n\n``` python\nfrom google.adk import Agent\n\ndata_agent = Agent(\n    name=\"data_analyst\",\n    model=\"gemini-2.5-flash\",\n    instruction=\"You are an expert Data Analyst AI...\",\n)\n```\n\nDuring local testing in the ADK web UI, I hit two quick configuration bumps:\n\n`404 NOT_FOUND`)\n`gemini-1.5-flash`), causing the platform to reject the request.` gemini-2.5-flash`.` 400 INVALID_ARGUMENT`)\n`\"gemini-2.5 flash\"` instead of a hyphen), breaking the API URL parser.`.env` and `agent.py`.\nAfter 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.", "url": "https://wpnews.pro/news/building-a-data-analyst-agent-with-google-adk", "canonical_source": "https://dev.to/bwandere/building-a-data-analyst-agent-with-google-adk-5349", "published_at": "2026-09-21 08:50:39+00:00", "updated_at": "2026-09-21 08:54:21.967690+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "agent-protocols", "developer-tools", "large-language-models"], "entities": ["Google", "Google Agent Development Kit", "Gemini 2.5 Flash", "Model Context Protocol", "Gemini 1.5 Flash", "Build with Google AI"], "alternates": {"html": "https://wpnews.pro/news/building-a-data-analyst-agent-with-google-adk", "markdown": "https://wpnews.pro/news/building-a-data-analyst-agent-with-google-adk.md", "text": "https://wpnews.pro/news/building-a-data-analyst-agent-with-google-adk.txt", "jsonld": "https://wpnews.pro/news/building-a-data-analyst-agent-with-google-adk.jsonld"}}