> For the complete documentation index, see [llms.txt](https://docs.eitherway.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.eitherway.ai/documentation/ai-companion/memory-and-scheduled-runs.md).

# Memory & Scheduled Runs

Most AI products still begin each session from zero.

Users explain the project, explain the conventions, explain what was tried last time, and then repeat the same setup in the next session.

The Eitherway AI Companion is being built with memory across sessions so that project context, style, and user preferences carry forward over time. Older or outdated context can fade, reducing the risk of the system getting stuck on stale assumptions.

Users will also be able to clear memory when they want a clean start, such as when beginning a new project.

Scheduled runs are already working internally.

The aim is to let users assign work to the companion, step away, and return to a finished plan, a summary of what was done, and a set of changes laid out for review.

This is the shift from an assistant that needs to be actively driven to a system that can be delegated to.

That capability is not yet fully released to users, but it is a core part of where the product is heading.

As this workflow develops further, users will not need to stay inside the product and manually supervise every step. The companion is being built to handle work asynchronously, with updates and progress flowing back through the relevant interface, including Telegram-based workflows that are already central to the Eitherway experience. The intention is to make delegation feel practical, not theoretical.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.eitherway.ai/documentation/ai-companion/memory-and-scheduled-runs.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.