Ep 28: LangChain CEO Harrison Chase on the Current State of Eval and Agents and The LLM Apps that Will Define 2024
Unsupervised Learning
Embracing Multi-Agent Frameworks as State Machines
The evolution of AI has led to a shift towards using multi-agent frameworks as controlled state machines with specific prompts and tools. By viewing agents as state machines, there is more control over the transition probabilities between prompts, creating a more reliable and focused system. Frameworks like Langgraph are embracing this concept, allowing for a structured approach to agent development based on specific states and transitions.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
