AITOPAI热报
How-toSelected

LangChain's agent evaluation tools

官方账号LangChain@LangChainAI
Post
View the post
Why we picked it

For developers using LangChain agents, this shows how to scale evaluation beyond manual checks.

LangChain's manual review process fails at high scale, so the company uses LangSmith's online evaluators and tests its insights product to understand agent behavior. This is for millions of agent runs per month.

Image · LangChain
Original · LangChain

Manual review works at small scale. At millions of agent runs a month, it falls apart, so @Clay relies on LangSmith's online evaluators and is testing its insights product to understand agent behavior. @jeffbarg explains. Your browser does not support the video tag. 🔗 View on Twitter 💬 2 🔄 1 ❤️ 7 👀 1996 📊 3 ⚡

#LangChain#agent evaluation#LangSmith#prompt engineering

Keep reading

Recent stories with the same tag or section
How-toBuildersSelected03:52
LangChain's Harrison Chase Shares Agent Building Lessons on Twenty Minute VC

The model-plus-context-plus-harness decomposition gives teams a concrete decision framework for where to invest effort first, rather than defaulting to fine-tuning. Practitioners building or budgeting for agents get a tested sequence for cutting spend and a candid view that memory distillation is still the hardest unsolved piece. The claim that horizontal agents will call vertical agents also hints at where agent infrastructure investment is heading.

#LangChain#agents#coding assistants#open-source models
官方账号LangChain@LangChainAISource
How-toBuildersSelected03:52
LangChain: run agent evals through the same graph

Testing evals against the production agent graph removes the gap between what benchmarks measure and what users actually experience. Builders of conversational or multi-turn agents can reuse this pattern: simulate personas through the same entry point as live traffic, then trust the same scores in CI. It pairs well with LangSmith-style tracing workflows for regressions.

#LangChain#agents#evals#LLM personas
官方账号LangChain@LangChainAISource