LangChain

What do Ramp, Perplexity, Superhuman, and Replit have in common? They've built breakout agentic apps that are live in production and pushing the boundaries of what AI agents can do ????? In our new "Breakout Agents" series, we've teamed up with Ramp, Perplexity, Superhuman, and Replit to take you behind-the-scenes of how they built their AI agents. ?? Explore how their engineering teams: ??Designed UXs for human-agent interactions ??Built unique cognitive architectures ??Leveraged prompt engineering ??Evaluated app performance to stay ahead ?? Read their stories and get inspired: https://lnkd.in/g246xsH8

Built on LangChain and LangGraph, check out how Elastic's AI Assistant can leverage custom knowledge sources to improve threat detection. In this blog post, walk through how to add a threat intelligence report PDF as custom knowledge and reference relevant information during an incident. Read the blog: https://lnkd.in/gXftDBqe

??Promptim: an experimental library for prompt optimization Promptim is an experimental prompt optimization library to help you systematically improve your AI systems. Promptim automates the process of improving prompts on specific tasks. You provide initial prompt, a dataset, and custom evaluators (and optional human feedback), and promptim runs an optimization loop to produce a refined prompt that aims to outperform the original. Blog: https://lnkd.in/gjENqmNN Video: https://lnkd.in/gU__JMPG

We’re excited to announce a new module in "Introduction to LangGraph" – our course on LangChain Academy – dedicated to mastering long-term memory ?? In this module, you’ll: ? Save and retrieve memory with the LangGraph Memory Store ?? Build a chatbot that uses both short- and long-term memory ?? Create an agent with memory to manage tasks Enroll now to earn your course certificate, and start designing LLM agents with long-term memory ?? https://lnkd.in/eAvWgJ83

?? Introducing Prompt Canvas — a novel UX for prompt engineering Building LLM applications requires new and dedicated tools for prompt engineering. With Prompt Canvas in LangSmith, you can: ? Collaborate with an AI agent to draft, refine, and edit your prompts ? Define custom quick actions to standardize prompting strategies used across the org ?? Learn more: https://lnkd.in/g4pJB2NH ?? Try it out: https://lnkd.in/gQqGyH33

??Composio’s SWE agent advances open-source on SweBench with a 48.6% score using LangGraph and LangSmith Coding is the first frontier for agents, and SWE Bench is a common benchmark Check out this top open source example using LangGraph/LangSmith https://lnkd.in/gYjKeNkM

??Chunking Data for RAG Applications Learn about how to transform your data for retrieval-augmented generation (RAG) applications using different chunking strategies. Covers: recursive splitting, document-specific splitting, and semantic splitting https://lnkd.in/gXubkP6d

SCIPE - a new tool to identify where your agent is failing Identifying failures in agents can be tricky because of the many steps they take. A new tool from Ankush Garg out of Berkeley makes it easy to identify where the agent fails. Try it out now with your LangGraph agents! https://lnkd.in/g_e6_2Z4

??Using Atlas Vector Search for RAG Applications In this unit, you'll build a?RAG?application with LangChain and MongoDB First, you'll learn what RAG is, and you'll build up to creating a custom prompt and a full RAG application. https://lnkd.in/gwDKCKtq

?? Document GPT ??? Features PDF Upload: Upload PDF files to be processed Q&A System: Users can ask questions based on the content of the uploaded PDF API Documentation: Automatic API documentation available through Swagger at /docs. https://lnkd.in/gRZVwThG