> For the complete documentation index, see [llms.txt](https://help.metaforms.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.metaforms.ai/survey-programming-dimensions/programming-page-walkthrough.md).
# Programming Page Walkthrough
Once your Dimensions project is set up, you'll land in the **Programming** tab — the central workspace for scripting, reviewing, and managing your survey. This guide introduces the key panels and features you'll use day-to-day.
***
### Script Panel
The left side of the screen displays your survey script, split into two tabs:
* **Metadata** — defines your questions, answer lists, and variable types.
* **Routing** — controls survey flow and logic.
You can use the **split screen** feature to view or edit metadata and routing scripts side-by-side — either vertically or horizontally.
***
### Quotas Panel
At the top, you'll find the **Quotas** panel. It starts empty and populates once quotas are generated through the AI agent.
***
### Design Files & Agent
The right side of the screen gives you access to two key panels:
* **Design File** — displays your uploaded questionnaire as a constant reference while you work.
* **AI Assistant** — chat-based agent that helps you program questions, quotas, and logic.
***
### Edit History
View a timeline of all file changes and versions, so you can track what was modified and when.
#### Saving Checkpoints
You can manually save a checkpoint at any point to bookmark your progress. Give it a descriptive name and click **Save Checkpoint**.
***
### Save, Sync & Test
When you're ready to push your work back to your Dimensions project directory:
1. Click **Save and Sync** at the top to write your code changes back to the project directory.
2. Click **Test** to launch the Unicorn app and preview your survey build directly.
---
# 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, and the optional `goal` query parameter:
```
GET https://help.metaforms.ai/survey-programming-dimensions/programming-page-walkthrough.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.