Writing Prompt Files

Version-controlled prompts with YAML configuration and XML message blocks

Prompts in Output live in .prompt files inside a prompts/ folder — version-controlled, reviewable, and deployed with your code. No more strings scattered across your codebase or prompts locked in external dashboards.

[e-mail]

---
provider: anthropic
model: claude-sonnet-4-20250514
temperature: 0.3
maxTokens: 2000
---

<system>
You are a sales research assistant. You help sales teams prepare for calls by summarizing company information.

Be factual and concise. Never make up information. If something is unclear from the provided data, say so.
</system>

<user>
Research this company and provide a brief summary for a sales call:

Company: {{ company_name }}
Website content: {{ website_content }}

Include: what they do, target market, recent news if available, and potential pain points we could address.
</user>

A prompt file has two parts: YAML frontmatter (configuration) and message blocks (the actual prompt content).

File Naming

Prompt files use the pattern [e-mail]:

• [e-mail]
• [e-mail]
• [e-mail]

The version lets you iterate on prompts while keeping old versions around. When you reference a prompt in code, use the name without the .prompt extension:

await generateText({
  prompt: 'generate_summary@v1',
  variables: { company_name: 'Acme Corp', website_content: '...' }
});

Output searches recursively from your workflow’s directory to find the prompt file.

File Organization

Place prompt files in a prompts/ subfolder within your workflow directory:

src/workflows/
├── lead_enrichment/
│   ├── workflow.ts
│   ├── steps.ts
│   ├── evaluators.ts
│   ├── types.ts
│   └── prompts/
│       ├── [e-mail]
│       └── [e-mail]
├── classify_tickets/
│   ├── workflow.ts
│   ├── steps.ts
│   └── prompts/
│       └── [e-mail]
└── shared/
    └── prompts/
        └── [e-mail]   # Shared across workflows

The recursive search means you can also keep prompts alongside your workflow code if you prefer a flatter structure. For prompts used by multiple workflows, create a shared prompts/ folder at a higher level.

Frontmatter

The YAML frontmatter configures the LLM call.

Required Fields

Field	Description	Example
provider	LLM provider	anthropic, openai, azure, vertex, bedrock
model	Model identifier	claude-sonnet-4-20250514, gpt-4o

Optional Fields

Field	Description	Example
temperature	Randomness (0-2)	0 for judges, 0.3 for summaries, 0.7 for general
maxTokens	Max output tokens	2000
providerOptions	Provider-specific config	See below

All fields use camelCase. Using max_tokens instead of maxTokens will fail validation.

---
provider: anthropic
model: claude-sonnet-4-20250514
temperature: 0.3
maxTokens: 2000
---

Configuration Structure

Prompt configurations have two layers:

1. Top-level config — Standard AI SDK options:

provider: anthropic
model: claude-sonnet-4-20250514
temperature: 0.7        # Standard option
maxTokens: 4000         # Standard option

2. providerOptions — Provider-specific and special options:

providerOptions:
  thinking:             # Special: AI SDK extension (top-level)
    type: enabled
    budgetTokens: 5000
  anthropic:            # Provider-specific options (nested)
    effort: medium

When to use providerOptions:

• Provider-specific options that aren’t standard across all providers
• Special AI SDK extensions like thinking or order (AI Gateway)
• Multi-provider configurations (Vertex with multiple model types)

When NOT to use providerOptions:

• Standard options: temperature, maxTokens, topP, etc.
• These go at the top level alongside provider and model

Provider Options

Use providerOptions for provider-specific configuration.

Anthropic-specific options:

---
provider: anthropic
model: claude-sonnet-4-20250514
providerOptions:
  anthropic:            # Namespace for Anthropic-specific options
    effort: medium      # Not available on other providers
---

OpenAI-specific options:

---
provider: openai
model: gpt-4o
providerOptions:
  openai:               # Namespace for OpenAI-specific options
    maxToolCalls: 1
    reasoning: true
---

Vertex with Gemini (important namespace note):

---
provider: vertex
model: gemini-2.0-flash
providerOptions:
  google:               # Use 'google' for Gemini, not 'vertex'!
    useSearchGrounding: true
---

Extended thinking (special top-level key):

---
provider: anthropic
model: claude-sonnet-4-20250514
providerOptions:
  thinking:             # Special: stays at top level (not under 'anthropic')
    type: enabled
    budgetTokens: 5000
  anthropic:            # Provider-specific options
    effort: medium
---

Common Provider Options Reference:

Provider	Option	Namespace	Description
Anthropic	effort	anthropic:	Reasoning effort: low, medium, high
OpenAI	reasoningEffort	openai:	Reasoning effort for o1 models
OpenAI	maxToolCalls	openai:	Maximum tool calls per turn
Vertex (Gemini)	useSearchGrounding	google:	Enable Gemini search grounding
Vertex (Claude)	effort	anthropic:	Claude models on Vertex use anthropic namespace
AI SDK	thinking	Top-level	Extended thinking (not under provider)
AI Gateway	order	Top-level	Provider routing order

Vertex Provider Namespace Guide:

When using provider: vertex, the providerOptions namespace depends on the model:

• Gemini models → Use google: namespace
• Claude models → Use anthropic: namespace
• Vertex-specific options → Use vertex: namespace

Message Blocks

Message blocks use XML-style tags to define the conversation structure.

<system>

The system message sets the persona and constraints. It defines who the LLM is and how it should behave. This stays constant across requests.

<system>
You are a sales research assistant. You summarize company information for sales teams.

Rules:
- Be factual and concise
- Never make up information
- Focus on business-relevant details
</system>

<user>

The user message is the actual request — what you want right now. This typically contains your variables.

<user>
Write a company summary for {{ company_name }}.

Industry: {{ industry }}
Company size: {{ size }} employees
Website content: {{ website_content }}
</user>

<assistant>

The assistant block is for conversation history or response prefilling. Use it when you want to prime the model’s response format:

<assistant>
Based on my analysis, here is the company summary:
</assistant>

<tool>

The tool block is for tool/function call results in multi-turn conversations:

<user>
What's the latest news about {{ company_name }}?
</user>

<assistant>
I'll search for recent news about {{ company_name }}.
</assistant>

<tool name="web_search" id="search_123">
{{ search_results }}
</tool>

The name attribute identifies which tool was called, and id matches the original tool use request.

System vs User

A common mistake is putting everything in the user message. The split matters:

System message (constant):

• Who the LLM is (“You are a sales research assistant”)
• Behavioral constraints (“Never make up information”)
• Output format requirements (“Respond in JSON”)

User message (varies per request):

• The specific request
• The data to process
• Dynamic instructions based on input

This separation makes prompts easier to maintain. When you need to change the task, you edit the user message. When you need to change behavior, you edit the system message.

Using Prompts

Call prompts from your steps using the generate functions from @outputai/llm.

With generateText

For single-shot LLM calls, use generateText:

steps.ts

import { step } from '@outputai/core';
import { generateText } from '@outputai/llm';
import { GenerateSummaryInput, GenerateSummaryOutput } from './types.js';

export const generateSummary = step({
  name: 'generateSummary',
  description: 'Generate a company summary from research data',
  inputSchema: GenerateSummaryInput,
  outputSchema: GenerateSummaryOutput,
  fn: async (input) => {
    const { result } = await generateText({
      prompt: 'generate_summary@v1',
      variables: {
        company_name: input.name,
        website_content: input.websiteContent
      }
    });

    return result;
  }
});

// types.ts
// import { z } from '@outputai/core';
//
// export const GenerateSummaryInput = z.object({
//   name: z.string(),
//   websiteContent: z.string()
// });
//
// export const GenerateSummaryOutput = z.string();

generateText also supports skills for on-demand instruction loading:

const { result } = await generateText({
  prompt: 'generate_summary@v1',
  variables: { company_name: input.name, website_content: input.websiteContent },
  skills: [audienceSkill],
  maxSteps: 5
});

With Agent

For multi-step tool loops and stateful conversations, use the Agent class:

steps.ts

import { step } from '@outputai/core';
import { Agent } from '@outputai/llm';
import { ReviewContentInput, ReviewContentOutput } from './types.js';

export const reviewContent = step({
  name: 'reviewContent',
  description: 'Review technical content with structured feedback',
  inputSchema: ReviewContentInput,
  outputSchema: ReviewContentOutput,
  fn: async (input) => {
    const agent = new Agent({
      prompt: 'writing_assistant@v1',
      variables: {
        content_type: 'documentation',
        focus: 'clarity',
        content: input.content
      },
      maxSteps: 5
    });
    const { text } = await agent.generate();
    return text;
  }
});

Use generateText for single-shot LLM calls. Use Agent when you need multi-step tool execution, conversation history, or a reusable agent instance. See the Agents section for the full API.

The variables object maps to the {{ variable }} placeholders in your prompt. For dynamic content like conditionals and loops, see Templating.