> For the complete documentation index, see [llms.txt](https://docs.aisera.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aisera.com/aisera-platform/what-can-my-bot-do/ai-automation-optimize-flow/hyperflow-studio/structured-hyperflow-prompt-editor/structured-hyperflow-prompt-editor-reference.md).

# Structured Hyperflow Prompt Editor Reference

Reference information for the Structured Hyperflow Prompt Editor, including section descriptions, action behaviors, and content format details.

### Prompt sections

Each Hyperflow prompt configuration is divided into five sections. Together, they define the agent's behavior, scope, and expected outputs.

| Section                    | Purpose                                                                              |
| -------------------------- | ------------------------------------------------------------------------------------ |
| **Agent Persona**          | Defines who the agent is and how it communicates with users.                         |
| **Agent Responsibilities** | Specifies the agent's objectives, capabilities, and boundaries.                      |
| **Execution Plan**         | Describes the reasoning process and approach the agent uses to complete tasks.       |
| **Completion Criteria**    | Defines what constitutes a successful outcome or response.                           |
| **Example Interactions**   | Provides representative scenarios and expected behaviors to guide agent performance. |

### Generate vs. Optimize

The Structured Prompt Editor includes two AI-assisted actions. They serve different purposes and behave differently.

|                         | Generate                                   | Optimize                                                           |
| ----------------------- | ------------------------------------------ | ------------------------------------------------------------------ |
| **Scope**               | Entire prompt configuration (all sections) | Entire prompt configuration (all sections)                         |
| **Input required**      | Plain-language behavior description        | Existing section content                                           |
| **Effect on content**   | Replaces all section content               | Refines and improves existing content                              |
| **Saves automatically** | Yes                                        | No. Requires review and manual save.                               |
| **Can be reverted**     | No                                         | Yes. The revert arrow is available immediately after optimization. |
| **When to use**         | Complete refresh of agent configuration    | Incremental improvement of the full prompt                         |

### Content format

Hyperflows that use the Structured Prompt Editor use Markdown for section content. The rich text editor supports:

* Headings
* Bold and emphasis formatting
* Bulleted and numbered lists

Hyperflows that use the standard editor use HTML-based prompt content. The Hyperflow's schema determines its content format, and this does not change after creation.

When you copy the full prompt from the **Full Prompt** view, you receive the content in Markdown format.

### Editor behavior by Hyperflow type

The editor that opens when you select a Hyperflow depends on the Hyperflow's schema.

| Hyperflow type                                            | Editor                             |
| --------------------------------------------------------- | ---------------------------------- |
| Created with the Structured Prompt Editor feature enabled | Structured Hyperflow Prompt Editor |
| Created with the standard editor                          | Standard prompt editor             |

There is no migration path between editor types. Each Hyperflow always opens in the editor that matches its schema.

### Variable Editor

The variable picker includes these built-in variables:

* `${flowUser}`
* `${conversationContext.channelType}`