---
title: How It Runs
description: Part 2 of the Build an Agent tutorial. Session, turn, and durable steps, and why a turn survives a crash.
url: "https://eve.dev/docs/tutorial/how-it-runs"
docs_index: /llms.txt
---

> For an index of all documentation, see [/llms.txt](/llms.txt).

The analytics assistant sent one message and got one answer. Three terms describe the model behind that.

| Term        | Meaning                                        |
| ----------- | ---------------------------------------------- |
| **session** | Your whole conversation. It can span days.     |
| **turn**    | One message you send and the work it triggers. |
| **step**    | A saved checkpoint within the turn.            |

A session survives restarts and redeploys, because eve saves each turn's progress at every step. A completed step never runs again; eve reuses its saved result. A step that is interrupted runs again from its start. Make side effects such as charges or emails idempotent, or gate them with approval. A turn that's waiting on you (an approval, a question) resumes whenever you answer, even if that's much later.

That's why the features in the rest of this tutorial work the way they do:

- The metric glossary in Step 5 survives across turns, because eve saves state at each step.
- The spend approval in Step 7 pauses the turn on your yes/no, then picks up exactly where it left off.

You write the tools, instructions, channels, and skills. eve drives the model-to-tool loop and decides when a turn continues, waits, or ends.

→ Next: [Step 3: Query sample data](./query-sample-data)

Depth: [Execution model & durability](../concepts/execution-model-and-durability)

---

For a semantic overview of all documentation, see [/sitemap.md](/sitemap.md)

For an index of all available documentation, see [/llms.txt](/llms.txt)

For agent-facing discovery, including API and MCP surfaces, see [/agents.md](/agents.md)