Skip to main content
AgentMark generates text with prompts that declare a text_config in frontmatter. Text prompts use message-role tags (<System>, <User>, <Assistant>) and return a string.

​
Example configuration

example.prompt.mdx
---
name: example
text_config:
  model_name: openai/gpt-5-mini
---

<System>You are a math tutor that can perform calculations.</System>
<User>What's 235 * 18?</User>
These docs write model_name in the provider-prefixed form, such as openai/gpt-5-mini. The value is a free-form string that AgentMark passes through to your call site unchanged, which is why the Running prompts examples strip the openai/ prefix before constructing the provider model.

​
Tags

TagDescription
<System>System-level instructions
<User>User message
<Assistant>Assistant message (optional; include for few-shot examples or prior-turn context)

​
Available configuration

PropertyTypeDescriptionRequired
model_namestringThe name of the model to use for text generation.Yes
max_tokensnumberMaximum number of tokens to generate.No
temperaturenumberControls the randomness of the output; higher values are more random.No
max_callsnumberMaximum number of LLM calls allowed (for agent workflows).No
top_pnumberCumulative probability for nucleus sampling.No
top_knumberLimits next-token selection to the top k tokens.No
presence_penaltynumberPenalizes tokens based on presence in the text so far, encouraging new topics.No
frequency_penaltynumberPenalizes tokens based on frequency in the text so far, reducing verbatim repetition.No
stop_sequencesstring[]Strings that, if encountered, stop generation.No
seednumberRandom-number seed for reproducibility.No
max_retriesnumberMaximum number of retries on failure.No
tool_choice"auto" | "none" | "required" | { type: "tool", tool_name: string }Controls how tools are used during generation.No
toolsstring[]List of tool names or MCP URIs available to the model. You resolve these names to implementations at your call site (see Tools and agents).No

​
Running a text prompt

See Running prompts → Text generation for the SDK code patterns: render the prompt with prompt.format(), then make your own model call (generateText in TypeScript, the OpenAI client in Python).

​
Have questions?

Reach out any time: