April 1, 2026
12 curated links on AI agents, Python, security, Google Cloud, and engineering, selected by Médéric Hurier.
-
ADK Go 1.0 Arrives!
developers.googleblog.com
Google has launched version 1.0 of the Agent Development Kit (ADK) for Go, featuring OpenTelemetry integration for deep tracing, a new plugin system for self-healing logic, and human-in-the-loop safety guardrails.
-
Improve Coding Agents’ Performance with Gemini API Docs MCP and Agent Skills
blog.google
Google has launched the Gemini API Docs MCP and Developer Skills to provide coding agents with real-time access to up-to-date documentation and best practices, significantly increasing their accuracy and efficiency.
-
Build with Veo 3.1 Lite, Our Most Cost-Effective Video Generation Model
blog.google
Google DeepMind has released Veo 3.1 Lite, a cost-effective video generation model available in the Gemini API that allows developers to build high-volume video applications with professional capabilities.
-
Spanner's Multi-Model Advantage for the Era of Agentic AI
cloud.google.com
Google Cloud highlights how Spanner's interoperable multi-model database approach—combining relational, vector, and graph data—serves as an intelligent context hub for powering sophisticated agentic AI workflows.
-
Agent to UI Protocol (A2UI) with Agent Development Kit (ADK)
medium.com
This post introduces A2UI, a generative UI protocol from Google that enables AI agents to generate interactive user interfaces across web, mobile, and desktop platforms using the Agent Development Kit.
-
Create Expert Content: Architect a Personalized Multi-Agent System with Long-Term Memory
cloud.google.com
This article details building a multi-agent architecture using Google ADK and Vertex AI, focusing on integrating long-term memory to personalize agent responses and persist user preferences across sessions.
-
Reverse-Engineering Claude Code: A Deep Dive into Anthropic's AI-Powered CLI
sathwick.xyz
This technical analysis explores the architecture and engineering of Claude Code, Anthropic's developer CLI, detailing its terminal UI, permission system, and extensibility via MCP.
-
Building Better AI Benchmarks: How Many Raters Are Enough?
research.google
Google Research introduces an evaluation framework that optimizes the trade-off between the number of items and raters per item to create highly reproducible AI benchmarks that capture the nuance of human disagreement.
-
Anthropic Leaks Part of Claude Code's Internal Source Code
cnbc.com
Anthropic confirmed that part of the internal source code for its Claude Code assistant was accidentally leaked due to a packaging error, though no sensitive customer data was compromised.
-
Announcing ADK Go 1.0
youtube.com
Official announcement video from Google for Developers about the release of Agent Development Kit for Go version 1.0.
-
Hands-on AI workshop: Graph RAG, Memory & Multimodal Agents
youtube.com
A practical workshop by Google Cloud Tech covering Graph RAG, memory integration, and building multimodal AI agents.
-
Claude Code was just leaked... (WOAH)
youtube.com
Matthew Berman discusses the recent internal source code leak of Anthropic's Claude Code tool.