GenAI

If you’ve built an agent, you know that the delta between “it works on my machine” and “it works in production” can be huge. Traditional software assumes you mostly know the inputs and can define the outputs. Agents give you neither: users can say literally anything, and the space

Notes on applied AI engineering, machine learning, and data science.

Over the past month at LangChain, we shipped four applications on top of the Deep Agents harness: * DeepAgents CLI: a coding agent * LangSmith Assist: an in-app agent to help with various things in LangSmith * Personal Email Assistant: an email assistant that learns from interactions with each user * Agent Builder: a no-code agent building platform powered by meta deep agents Building and shipping these agents meant adding evals for each of them, and we learned a lot along the way! In this

Why does EDA fit so well with DDD principles?

Learn about our hierarchical Bayesian model for A/B testing AI agents. It combines deterministic binary metrics and LLM-judge scores into a single framework that accounts for variation across different groups

A walkthrough of using the bootstrap fewshot and GEPA optimizers in DSPy

The best agent products aren't the most flexible, they're the most opinionated. Learn why agents need fewer knobs, not more, and how to design around model intelligence spikes.

Most software doesn’t break because of syntax errors or flawed if-else logic.

Let's buy the fridge next month, honey.

We're excited to introduce langchain-azure-storage, the first official Azure Storage integration package built by Microsoft for LangChain 1.0. As part...

Anthropic economic research on productivity gains

Learn how to make stateless LLM agents remember conversations, manage context, and implement memory banks.

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 brain dump of all the ways I've been using Claude Code.

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

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.