# Eliza Concepts

Providers, actions, and evaluators extend the functionality of the agent.

## Character Files

[Characters](https://hackmd.io/AEni5Dd6QgWtZskFXL-lJw)

## Agents

## Providers

Provide information into the context. This is how you get information from the outside. Providers are the inputs into the agent.

## Actions

Actions are the things the agent can do. They can call an action in the response.

## Evaluators

This is the agent reflecting on the current scenario and extracting information from that.
This abstraction is for goal-oriented behavior.

---

## Embeddings

- [Embedding Projector](https://projector.tensorflow.org/)
- [What are embeddings in machine learning? | Cloudflare](https://www.cloudflare.com/learning/ai/what-are-embeddings/)
- [Embeddings | Machine Learning | Google for Developers](https://developers.google.com/machine-learning/crash-course/embeddings)
- [Neural Networks: Zero to Hero](https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ)
- [Andrej Karpathy: Tesla AI, Self-Driving, Optimus, Aliens, and AGI | Lex Fridman Podcast #333](https://www.youtube.com/watch?v=cdiD-9MMpb0)