LangChain Inc., a startup designed to assist developers in building artificial intelligence agents, has successfully raised $125 million in funding at a valuation of $1.25 billion.
According to Fortune magazine, IVP led this Series B funding round. Additional participants included Alphabet Inc.'s growth-stage fund CapitalG, ServiceNow Ventures, Workday Ventures, Cisco Investments, Datadog, Databricks, and several other companies.
LangChain has developed an open-source AI agent development tool of the same name. The software enables engineers to implement agents with as few as 10 lines of code. By providing pre-packaged building blocks, LangChain accelerates development and eliminates the need to build everything from scratch.
Another advantage of the tool is its unified application programming interface. OpenAI, Anthropic PBC, and other AI providers distribute their language models via different APIs. As a result, switching a model typically involves changing APIs, which requires code modifications. LangChain's unified API makes it possible to switch AI models without changing the code.
Software teams requiring advanced capabilities can use LangGraph, another open-source tool developed by LangChain. It facilitates the creation of AI agents that can run for extended periods and automatically recover from errors. LangGraph also supports the implementation of human supervision features.
Companies working on more complex projects can pair LangGraph with Deep Agents, an open-source tool released by LangChain in July. The latter's technology enables applications to be equipped with reasoning capabilities.
According to LangChain, Deep Agents includes a tool that allows AI agents to break down complex tasks into multiple steps. The tool tracks progress at each step and adjusts its plan when encountering difficulties. A second component of Deep Agents creates dedicated sub-agents for each processing step to accelerate output generation.
Certain tasks require AI agents to process large volumes of new data. In some cases, the amount of data might exceed the capacity of the agent's context window. Deep Agents includes a file system that increases the amount of information AI agents can utilize during processing.
LangChain generates revenue through a paid product called LangSmith. It provides a code editor optimized for AI agent development. After engineers create new agents, they can use LangSmith's built-in testing features to determine whether the agents meet project requirements.
The tool also simplifies other development tasks. It includes a feature that allows one-click deployment of AI agents. Once deployed, the tool tracks metrics such as inference costs and latency.
LangSmith's observability features also monitor how users interact with AI applications. The tool can automatically identify requests that agents struggle to handle. Developers can use this information to make improvements.
