# Stateless

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: statelessness, no memory, doesn't remember, stateless model

Describes something that keeps nothing between uses. A model is stateless: it does not remember earlier requests, so the product around it sends the [conversation](https://ecosystem.samcarlton.com/session) again each time. This is why long chats cost more and why [agents](https://ecosystem.samcarlton.com/ai-agent) need saved notes to pick up old work.

**For example:** A user believes the [chatbot](https://ecosystem.samcarlton.com/chatbot) remembers last week's [conversation](https://ecosystem.samcarlton.com/session). In fact the app saved the chat and sent it back with the new question; the model itself remembered nothing.

## Connects to (7)

- [Stateful](https://ecosystem.samcarlton.com/stateful): Describes something that carries information forward from one moment to the next.
- [Model](https://ecosystem.samcarlton.com/model): The trained system at the center of an AI product.
- [Session](https://ecosystem.samcarlton.com/session): One stretch of work with an AI agent, from a blank start until it is cleared, closed or compacted.
- [Model provider request](https://ecosystem.samcarlton.com/model-provider-request): One trip from an AI product to the model provider and back.
- [Input tokens](https://ecosystem.samcarlton.com/input-tokens): The tokens an AI product sends to the model on each request: the instructions, the conversation so far, files and tool results.
- [Memory system](https://ecosystem.samcarlton.com/memory-system): A setup that tries to give an agent memory across sessions by saving notes to files or a database and loading them back when a new session…
- [Clearing](https://ecosystem.samcarlton.com/clearing): Ending a session and starting a completely empty one.

Map view: https://ecosystem.samcarlton.com/stateless