Agents

An agent can be thought of as a logical wrapper around an LLM, allowing us to add several features to our AI systems, primarily:

Tool usage, such as calling APIs for info, executing code,

Internal thoughts over multiple generation steps

Ability to use various tools and reasoning steps to answer more complex queries.

Parallel agents can go and complete

James Briggs • LLMs Are Not All You Need | Pinecone

@HamelHusain Well, agents do have a specific definition that I feel like got lost somewhere in the hype - but yes, they're essentially just workflows with extra capacity for dynamic decision making (ie selecting the correct next function based on the environment) and backtracking on errors

Shannon Sands twitter.com

Agents Definition

Ideas related to this collection