LangChain co-founder and CEO Harrison Chase argues that the unpredictable nature of large language models means enterprises cannot achieve reliable AI agents simply by dropping a model into fixed code — the real work lies in the surrounding system. In a talk titled "3 ingredients for building reliable enterprise agents" delivered at the AI Engineer World's Fair in San Francisco, Chase pressed a point that has become central to the current agent-building debate: because an LLM behaves probabilistically, you cannot know in advance exactly what it will do, and embedding that uncertainty directly into a deterministic workflow does not guarantee the outcome you want.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.