AI21 Maestro’s Structured RAG fixes RAG’s accuracy gaps with hybrid retrieval—delivering reliable, auditable answers for enterprise compliance and reporting.

Build powerful multi-agent systems with Agent Development Kit

This blog has been co-authored by Hanfei Sun, Vertex AI Agent Engine, Software Engineer, and Huang Xia, Vertex AI Agent Engine, Software Engineer. TL;DR: Vertex AI Agent Engine now integrates with the Live API to enable real-time, bidirectional streaming agents. This allows for low-latency, human-like conversations using text and audio. This post demonstrates how to quickly build a streaming agent with the Agent Development Kit (ADK), leveraging a fully managed, serverless platform that hand...

Learn how to get the most out of the context window in Amp, with the least amount of work.

Setting up the coding agent rust project with Gemini API

Agentic systems often reach a plateau after proof-of-concept because they depend on humans to diagnose edge cases and correct failures. T...

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent's resilience on natural language inputs -- an especially dangerous threat when agents are granted tool access or handle sensitive information. In this work, we propose a set of principled design patterns for building AI agents with provable resistance to prompt injection. We systematically analyze these patterns, discuss their trade-offs in terms of utility and security, and illustrate their real-world applicability through a series of case studies.

Karl Marx once wrote that ``the human essence is the ensemble of social relations'', suggesting that individuals are not isolated entities but are fundamentally shaped by their interactions with...

We envision a new era of AI, termed agentic organization, where agents solve complex problems by working collaboratively and concurrently, enabling outcomes beyond individual intelligence. To...

Tech debt and comprehension debt

A practical guide to Agent Engineering: the intersection of software, systems and security engineering.

Our AI visualizations worked 'pretty good'—which turned out to be the problem. Here's what we learned about building products during a massive technology shift, and why we now ship early, kill projects faster, and retry failed ideas every few months

Developer experience in the age of vibe coding

Welcome in 2021,I know its already been some months but I hope you had a good and motivated start into the new year. What could be better than starting by reading the newest blog post about “…

Design robust multi-agent AI systems in Google Cloud.

Strategies and parameters you can tune to improve the performance of Retrieval-Augmented Generation (RAG) applications for production.

In this blog piece, you’ll learn why and how we built LangGraph for production agents—focusing on control, durability, and the core features needed to scale.