Agent Development on danicat.dev

Build Rich Agentic Interfaces with ADK and A2UI

daniela@danicat.dev (Daniela Petruzalek) — Wed, 17 Jun 2026 00:00:00 +0000

In this codelab you are going to explore how to enhance your agent using A2UI to build dynamic interfaces beyond simple text and markdown.

Create Your Own Executive Assistant with Agent Development Kit

daniela@danicat.dev (Daniela Petruzalek) — Wed, 11 Mar 2026 00:00:00 +0000

In this codelab you are going to learn how to create your own AI Executive Assistant using Agent Development Kit (ADK) and Gemini.

Build an MCP Server with Go and Gemini CLI

daniela@danicat.dev (Daniela Petruzalek) — Wed, 04 Feb 2026 00:00:00 +0000

Learn how to extend the Gemini CLI with custom tools using the Model Context Protocol (MCP) in Go.

How to Build an Offline Agent with ADK, Ollama and SQLite

daniela@danicat.dev (Daniela Petruzalek) — Mon, 03 Nov 2025 09:00:00 +0000

Learn how to make your AI agent completely offline. We walk through swapping the cloud model for a local Qwen 2.5 via Ollama, and building a local RAG knowledge base using SQLite and sqlite-rag to query Osquery schemas and packs.

Beyond Dev-UI: Building a Custom Interface for ADK Agents

daniela@danicat.dev (Daniela Petruzalek) — Fri, 31 Oct 2025 11:43:35 +0000

Elevate your Google ADK agent with a custom, retro-style interface. This step-by-step guide shows you how to replace the standard Dev-UI using FastAPI and vanilla JavaScript, adding personality with a real-time streaming, AI-generated avatar.

How to Create a Diagnostic Agent with Agent Development Kit

daniela@danicat.dev (Daniela Petruzalek) — Tue, 21 Oct 2025 15:44:03 +0100

This article is a guide to creating a diagnostic agent with the Agent Development Kit (ADK). It covers the development process and explains how to use Vertex AI RAG to improve the agent’s response quality.

Hello, MCP World: Model Context Protocol Architecture with Go

daniela@danicat.dev (Daniela Petruzalek) — Sun, 17 Aug 2025 15:00:00 +0000

Based on my keynote at Gophercon UK 2025, this article is an introduction to the Model Context Protocol (MCP), exploring its core concepts, architecture, and the building blocks — Tools, Prompts, and Resources — used to create AI-enabled applications with Go.

Building GoDoctor: How to Build an MCP Server with Gemini CLI and Go

daniela@danicat.dev (Daniela Petruzalek) — Tue, 29 Jul 2025 00:00:00 +0000

A step-by-step guide on how I built GoDoctor, an AI-powered Go development assistant, using the Model Context Protocol (MCP) and the Gemini CLI.

Boldly Prompting: A Practical Guide to System Instructions and Agent Tools

daniela@danicat.dev (Daniela Petruzalek) — Wed, 11 Jun 2025 00:00:00 +0100

This article explores the concepts of system instruction, session history and agent tools to create a smarter diagnostic assistant.

Digging Deeper into the Vertex AI SDK for Python

daniela@danicat.dev (Daniela Petruzalek) — Thu, 05 Jun 2025 00:00:00 +0100

This article explores the communication model between the client code and the Gemini API using the Vertex AI SDK for Python

How I turned my computer into "USS Enterprise" using AI Agents

daniela@danicat.dev (Daniela Petruzalek) — Sat, 31 May 2025 01:00:00 +0100

How to create a diagnostic agent that speaks natural language using Gemini and Vertex AI Agent Engine