Tag
LangChain announces new products to be unveiled at the Interrupt keynote livestream, with CEO Harrison Chase discussing the future of AI agents in production.
LangChain announces an event on September 30th focused on online evaluations, demonstrating how to use Tuned Evaluators in LangSmith to automatically analyze AI agent interactions and provide feedback in production.
An aspiring AI engineer seeks advice from senior professionals on which portfolio project best demonstrates production skills, proposing ideas like LLM routing services, agent systems with guardrails, and local inference microservices, while asking for feedback on common gaps in portfolios.
AWS, NVIDIA, and LangChain are hosting an in-person session focused on building flexible infrastructure for developing and scaling agentic AI workloads using Amazon EKS and related technologies.
LangChain and Typesafe AI are hosting a live session on building an agent harness with Jev, scheduled for today at 11am PT / 2pm ET.
A developer built a tool to compare different AI agent frameworks side-by-side, aiming to evaluate architectural differences and seeking feedback from experienced practitioners.
This article introduces TypeSafeClassifier, a LangChain Runnable that provides typed decisions with calibrated probabilities for model routing and tool-risk gating in agent workflows.
LangChain announces that SemIf, an open-source decision model, is available for free for one week in the LangSmith LLM Gateway, compatible with the TypeSafe SDK.
LangChain is hosting a livestream to discuss TypeSafe AI's new model Jev, which promises up to 200x faster inference and 400x lower cost for classification tasks, aiming to improve agent loops.
LangChain is hosting a live demo of their Paid Media Agent on September 23rd, covering its architecture, functionality, production learnings, and Q&A.
This article provides 10 steps to optimize AI agent decision-making by using the langchain-typesafe tool, reducing LLM call costs to $0.042 per million tokens and latency to 70-500ms while preventing hallucinations.
TypeSafe AI releases Jev, a System One model for fast, structured decisions in agent loops, offering up to 200x faster inference and 400x lower cost for classification tasks compared to traditional LLMs.
Deep Life Sci is an open source agentic assistant built for clinical and lab scientists, providing access to vast databases like ClinicalTrials.gov and PubMed with sub-agents for efficient document review.
LangChain's Paid Media Agent is an AI-powered tool with 200+ tools and a company wiki, designed to assist marketing teams in campaign analysis, code writing, and report generation.
LangChain shares a guide on how Schneider Electric, Vodafone, and monday.com are scaling AI agents in production with improved observability, evaluation, and governance.
Podcast episode featuring LangChain's Harrison Chase and Browserbase's Paul Klene discussing the evolution of AI agents, LangChain's development from open-source to commercial platform, and key insights on AI infrastructure and developer tools.
This post highlights context engineering as a major challenge for AI agent harnesses and introduces Deep Agents, which includes built-in features like filesystems and subagents for effective context management.
LangChain demonstrates how LangGraph and LangSmith have accelerated support agent development at Lyft, reducing shipping time from six months to 1-2 weeks with enhanced visibility.
LangChain's Managed Deep Agents now function as MCP servers, allowing coding assistants and other agents to delegate tasks like research and analysis via a standard protocol endpoint.
LangChain has added a capstone project to their LangSmith Essentials course, providing more opportunities to practice debugging and tracing skills in AI agent engineering.