In the news
LangChain State of AI 2023
LangChain · Published · 3 min read
In 30 seconds
- What happened
- LangChain analyzed anonymized LangSmith data from mid-2023 showing how developers build LLM applications, revealing retrieval dominates, OpenAI leads, and evaluation remains challenging.
- Why it matters
- Engineers building LLM applications need this to understand current practices, popular tools, and common patterns for retrieval, model selection, and testing strategies.
- Watch out
- Data comes from LangSmith users only, a self-selected group; patterns may not represent all LLM development; rankings count users, not usage volume or production deployments.
Listen to this summary
- llm
- retrieval
- eval
Who else ran this
- LangChain State of AI 2024 ReportLangChain
The same event, reported by other publishers we follow.
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.