Create a prompt - AgentMark Docs

Cloud
Local

1. Create a prompt

Open the create menu in the Dashboard to start a new prompt.

The Create menu in the top bar lets you add a new prompt, dataset, or component to the current app.

2. Name your prompt

Give your prompt a descriptive name and choose the generation type (Text, Object, Image, or Speech).

Prompt name and generation-type selection dialog

The new-prompt dialog takes a name (used as the filename under agentmark/) and a generation type (Text, Object, Image, or Speech), which determines the frontmatter config key and supported message tags.

3. Write your prompt

Select your model and write your prompt using message tags.

The editor has a model selector, frontmatter for config (model, temperature, etc.), and a message-tag editor for the prompt body (<System>, <User>, <Assistant>). Syntax highlighting and inline validation help catch frontmatter or tag errors as you type.

4. Run your prompt

Add your input variables and run the prompt to see results.

Fill the input-variable fields (any {props.foo} references in your prompt), then click Run to execute the prompt. The output streams into the right panel in real time.

5. Publish

Publish to save your changes and make them available to your application.

The Publish button commits your edits to the app’s default Git branch and makes the new version available to your application via the SDK or CLI.Every change is automatically versioned. You can view the full version history, compare changes between versions, and rollback to any previous version from the Dashboard. See Version control for details.

1. Create a `.prompt.mdx` file

Add a new file in your project’s agentmark/ directory:

agentmark/greeting.prompt.mdx

---
name: greeting
text_config:
  model_name: openai/gpt-5-mini
  temperature: 0.7
---

<System>
You are a friendly assistant.
</System>

<User>
Say hello to {props.name} and tell them something interesting.
</User>

2. Choose a generation type

The frontmatter key determines the output type:

Key	Output	Tags
`text_config`	Text response	`<System>`, `<User>`, `<Assistant>`
`object_config`	Structured JSON	`<System>`, `<User>`, `<Assistant>`
`image_config`	Image	`<ImagePrompt>`
`speech_config`	Audio	`<SpeechPrompt>`, `<System>`

Learn more about generation types →

3. Run your prompt

agentmark run-prompt agentmark/greeting.prompt.mdx

Requires the development server running (agentmark dev).

Or run it from your application code. See Running prompts.

4. Iterate

Edit the file, save, and run again. With the dev server running, changes are picked up automatically.Your prompts are version-controlled in git alongside your code. When synced to Cloud, every change is tracked with full history and rollback. See Version control for details.

Next steps

Running prompts

Execute prompts from your application via SDK

Playground

Compare models and prompts side-by-side

Generation types

Text, object, image, and speech output

TemplateDX syntax

Variables, conditionals, loops, and components

Have questions?

Reach out any time:

Email the team at hello@agentmark.co for support
Schedule an Enterprise Demo to learn about AgentMark’s business solutions

​1. Create a prompt

​2. Name your prompt

​3. Write your prompt

​4. Run your prompt

​5. Publish

​1. Create a .prompt.mdx file

​2. Choose a generation type

​3. Run your prompt

​4. Iterate

​Next steps

Running prompts

Playground

Generation types

TemplateDX syntax

​Have questions?

1. Create a prompt

2. Name your prompt

3. Write your prompt

4. Run your prompt

5. Publish

1. Create a `.prompt.mdx` file

2. Choose a generation type

3. Run your prompt

4. Iterate

Next steps

Have questions?