> For the complete documentation index, see [llms.txt](https://help.intangible.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.intangible.ai/chat-agents-intangible/status-and-steps.md).

# Status and steps

Read what Intangible agents are doing: the status line at the top of the panel and the step list as each part of the job lands.

The status line and the step list show what the agents are working on, and a choice card tells you when they are waiting on you.

## The status line

The status line is the title at the top of the open chat panel. It says what the agents are doing:

| Status                      | What it means                                                                                                                                                                                  |
| --------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| ready when you are          | Nothing is running. Type a request. A run you stopped with **Stop generating** (the square button that replaces Send while the agents work) comes back to this, and so does a turn that failed |
| building your scene         | They are working: references, models, layout, cameras                                                                                                                                          |
| waiting for your answer     | A choice card in the chat panel needs a click                                                                                                                                                  |
| All done! How does it look? | Their turn ended. Renders they started can still be generating on the canvas                                                                                                                   |

"All done! How does it look?" means the agents stopped replying, not that every step ran. Check the step list and the canvas before you move on. If you rename the chat, its name takes the place of the status line for good.

While they work without a plan, a single row marked **Running** shows a short line of flavour text, such as "Fingers crossed that we understood the assignment.", in place of the old loading bubble. It is there to show the run is alive; it does not report progress. Once there is a plan, the step rows take its place.

## When a turn fails

A failed turn does not change the status line. The thread says what happened, under your message:

| Line in the thread                                                                   | What it means                                                                                           | What to do                                                                                                        |
| ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------- |
| That didn't go through. Anything already on the canvas stays.                        | The request failed. Anything already on the canvas stays there                                          | Click **Try again** under the line. It sends the same message once, as you first sent it, and the turn carries on |
| Connection lost before I finished. Send "continue" and I'll pick up where I stopped. | The connection dropped mid-run: a network drop, a refresh or a closed tab. The work done so far is kept | Send `continue`. The agents read the thread and the canvas and do only what is left                               |

**Try again** shows only on the newest failed turn, and only in the session where it failed. It does not appear after a lost connection, where sending the request again would redo work already done, or when the request itself was refused. "continue" is an ordinary message and uses credits like one.

## The step list

When you confirm a plan, the step list appears in the thread: one full-width row per step, in order, with its status on the right. **Running** has a spinner, **Queued** an empty circle and is dimmed, **Ready** a check. A step only runs while the turn does: if the turn stops or is cut off before a step is marked ready, it goes back to **Queued**. The agents write the steps themselves. On a five-shot run the list read:

* Confirm brief
* Start 3 reference sheets (pod, rover, crater)
* Build the crater scene with pod and rover
* Animate drop, bounces, opening, drive-off
* Frame the five shots for your approval

A step that spends credits carries its cost in the step text. A step that ends "for your approval" is a point where the agents stop and wait for you. During a long build the thread can also show a link that reads **continue if you timed out**. When the turn ends, the list folds to **Show steps**; click it to open the list again, and **Hide steps** to fold it. A step still running never folds away.

What the steps make (the brief, references, models, scenes and shots) lands on the canvas as cards you can open, change or delete. See [What Intangible agents build](https://help.intangible.ai/canvas/what-intangible-agents-build.md).

## When it stalls

There is no time estimate, so watch the step list. If the status stops changing for a long time, see [Troubleshooting Intangible agents](https://help.intangible.ai/learn-more/faq/troubleshooting-the-agent.md).

## Related

* [Chat with Intangible](https://help.intangible.ai/chat-agents-intangible/chat-with-intangible.md)
* [Chat](https://help.intangible.ai/chat-agents-intangible/chat.md)


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.intangible.ai/chat-agents-intangible/status-and-steps.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
