Ankush Gola

Few-shot prompting to improve tool-calling performance

We ran a few experiments, which show how few-shot prompting can significantly enhance model accuracy - especially for complex tasks. Read on for how we did it (and the results).

By LangChain 8 min read

How Athena Intelligence optimized research reports with LangSmith, LangChain, and LangGraph

See how an AI-powered employee for enterprise analytics used the LangSmith playground and debugging features to quickly identify LLM issues and to generate complex research reports.

Case Studies 4 min read

Rethinking Our Documentation

LangChain has seen some incredible growth in the last year and half. The Python open-source library is now downloaded over 7 million times per month,

4 min read

LangSmith: Production Monitoring & Automations

Key Links: * YouTube Walkthrough * Sign up for LangSmith here If 2023 was a breakthrough year for LLMs, then 2024 is shaping up to be the

6 min read

Using Feedback to Improve Your Application: Self Learning GPTs

We built and hosted a simple demo app to show how applications can learn and improve from feedback over time. The app is called "

4 min read

Multi Needle in a Haystack

Key Links * Video * Code Overview Interest in long context LLMs is surging as context windows expand to 1M tokens. One of the most popular and

6 min read

LangGraph for Code Generation

Key Links * LangGraph cookbook * Video Motivation Code generation and analysis are two of most important applications of LLMs, as shown by the ubiquity of products

4 min read

Reflection is a prompting strategy used to improve the quality and success rate of agents and similar AI systems. This post outlines how to build 3 reflection techniques using LangGraph, including implementations of Reflexion and Language Agent Tree Search.