RSS feed for my blog www.philschmid.de
Use Gemini 3.7 Flash Computer Use with about 150 lines of Python to control an Android emulator. The model plays Wordle from screenshots: opens Chrome, clears popups, reads tile colors, and solves in two guesses.
Use Google Maps and Google Search in the same Gemini API call with Gemini 3.6 Flash, then add custom functions or MCP servers for actions like booking a table.
EvoCode-Bench tests coding agents across 227 sequential rounds in a persistent workspace. Single-turn scores overstate reliability — regressions, not missing features, are the real bottleneck.
Build Gemini Managed Agents that use the GitHub CLI without exposing your PAT. The egress proxy injects your real token into outbound requests while the sandbox only sees a dummy token.
Control an Android emulator using Gemini 3.5 Flash Computer Use. Connect the Google GenAI SDK interactions loop with ADB to control a virtual device from your terminal.
A developer guide to the Gemini Interactions API, text generation, streaming, multi-turn chat, multimodal inputs, structured output, tool use, managed agents, and background execution from a single endpoint.
A single API call boots a sandbox, loads skills, and lets the model loop until the task is done. Here is what happens at each step.
Build, customize, and deploy production agents that reason, execute code, and manage files inside secure Linux sandboxes as a single API call.
Subagents solve context pollution, but how the main agent manages them matters more than whether they run in sync or async. Four orchestration patterns, from a simple tool call to an autonomous agent team, each with different requirements for model capability and result collection.
The Gemini Deep Research Agent autonomously plans, searches, and synthesizes long-horizon research tasks into detailed, cited reports.
MCP servers are not dead. Blindly enabling them bloats your context, which leads to higher cost and worse performance. Here are two proven patterns on how to correctly use MCP servers and avoid the bloat.
8 Tips for Writing Agent Skills. Know What a Skill Is, Nail the Description, Write Instructions, Keep It Lean, Set the Right Level of Freedom, Don't Skip Negative Cases, Test It Before You Ship It, Know When to Retire a Skill.
Learn how to use Gemma 4 with the Gemini API and Google AI Studio.
Learn the unique ways how Kimi, Cursor, and Chroma train agentic models with RL.
Learn how to combine built-in tools and function calling in the Gemini Interactions API.
Learn how to use the Gemini Interactions API to build a personalized Japan travel brochure with Nano Banana 2.
Autoresearch lets an AI agent run hundreds of model training experiments overnight. Learn how it works, early results from Karpathy and Shopify, and how to apply it.
Learn how to systematically test and improve agent skills using deterministic checks and a real-world Gemini API example.
Learn what to include, what to skip, and how to structure your AGENTS.md for best results.
Most agent frameworks share the same hardcoded tool loop; what differs is how the model uses it. This post explains the inner loop—an agent verifying its own work within a task—and the outer loop—an agent carrying lessons across tasks via persistent memory, skills, and rules files—and why both are needed for agents that feel reliable and get smarter over time.
What makes some AI agents feel like collaborators while others need constant babysitting? Two capabilities matter: self-awareness — does the agent understand what it is and how to use its tools — and closing the loop — can it verify its own work before responding. This post breaks down where agents stand today, how production systems like Spotify scaffold verification, and what needs to improve…
Multimodal function calling allows tools to return images the model can process natively, similar to how you pass images in prompts. Instead of describing what's in a file, your tool returns the actual image and Gemini 3 processes it natively.
Learn how to use the new Gemini Deep Research agent via the Interactions API to perform complex research tasks, generate images based on the findings, and translate the results.
The Agent Client Protocol (ACP) is an open standard abstracts the events and outputs of AI agents and provides a common interface for editors to interact with them. Similar to MCP but for agent to client (UI) communication.
The Interactions API is a unified interface for building with Gemini models and agents. It simplifies the development of agentic applications by handling server-side state management, tool orchestration, and long-running tasks.
The Model Context Protocol (MCP) has exploded roughly 1 year ago, everyone rushed to build MCP servers. The hype was real. Yet, most MCP servers disappoint. Most developers blame the protocol. The protocol feels like it's dying on social media.
Learn how to generate transparent PNG stickers using Nano Banana Pro and the Gemini Interactions API, featuring chromakey green background removal with HSV detection.
Learn how to build AI agents using the new Gemini Interactions API, featuring server-side state management and simplified tool orchestration.
Mcp-cli is a lightweight CLI that allows dynamic discovery of MCP, reducing token consumption while making tool interactions more efficient for AI coding agents.
In 2026, Agent Harnesses will become essential for building reliable AI systems that can handle complex, multi-day tasks.
8 Predictions for 2026, exploring the future of AI, personal agents, smart homes, and more.
Building on the foundations of Context Engineering, this post explores advanced strategies to manage context rot, multi-agent coordination, and action space optimization for AI agents.
Traditional software engineering is deterministic, while AI agents operate probabilistically. This fundamental difference creates challenges for engineers accustomed to strict interfaces and predictable outcomes.
A step-by-step practical guide on building AI agents using Gemini 3 Pro, covering tool integration, context management, and best practices for creating effective and reliable agents.
A comprehensive guide on best practices for prompting Gemini 3, focusing on clarity, structure, reasoning, and agentic tool use to maximize model performance across various domains.
Learn how to use the Gemini API File Search tool with JavaScript/TypeScript to build a Retrieval-Augmented Generation (RAG) system.
Learn how to deploy n8n on Google Cloud Run with PostgreSQL and create an AI Agent using Google Gemini 2.5.
An extensive compendium of over 50 benchmarks for evaluating AI agents, categorized into Function Calling and Tool Use, General Assistant and Reasoning, Coding and Software Engineering, and Computer Interaction.
An overview of the architectural shift from Shallow Agents (Agent 1.0) to Deep Agents (Agent 2.0) and how to build complex AI agents that can handle multi-step tasks over extended periods.
The rise of subagents is a trend in the AI community. We are seeing more and more use of subagents to reliably handle specific user goals.
Learn how to use Gemini 2.5 Flash for product image generation.
Learn how to engineer long-term memory into stateless AI agents to overcome their biggest limitation and unlock true personalization.
A comprehensive cheatsheet on using Google's Gemini CLI, covering installation, authentication, configuration, and core commands.
Code Sandbox MCP is a simple, self-hosted code interpreter for your AI agents. It allows you to execute code snippets in containerized environments.
This guide shows you how to add long-term memory to your Gemini 2.5 chatbot using the Gemini API and Mem0.
Context Engineering is the new skill in AI. It is about providing the right information and tools, in the right format, at the right time.
Single vs. multi-agent? The real secret to building AI agents is 'read vs. write'. Learn which to use for your task and build reliable systems.
Learn common agentic design patterns and workflows for building robust, scalable AI applications, understanding when to use each.
A comprehensive cheatsheet on using Google's Gemini within the LangChain, covering chat functionalities with multimodal inputs, tool usage, structured data generation, and text embedding techniques.
I used Gemini 2.5 Pro to better understand the OpenAI Codex CLI, a tool that allows you to interact with an AI model directly in your terminal to perform coding tasks.