Skip to main content
The Custom Agent gives you direct access to frontier Large Language Models (LLMs) like GPT-5.2, Claude Opus 4.5, and Deepseek V3. Pick your model, write your prompts, and get a single text response—perfect for simple, one-shot AI tasks.

​
Key Capabilities

Choose Your Model

Pick from GPT-5.2, Claude Opus 4.5, Deepseek V3, and other frontier LLMs.

Fine-Grained Control

Use a System Prompt for context and role, plus a Prompt for your specific instruction.

Temperature Control

Lower temperature for consistent, focused outputs. Higher for more creative responses.

Simple Output

Returns a single Agent Response field with the model’s text output.

​
Configuration

​
Central Panel Options

SettingDescription
ModelChoose your LLM (GPT-5.2, Claude Opus 4.5, Deepseek V3, etc.)
PromptYour main instruction—what you want the AI to do
System PromptContext and role for the model (e.g., “You are a data extraction assistant”)
TemperatureControls randomness: 0 = focused and consistent, 1 = creative and varied

​
Input Variables

Custom Agent accepts all typed variables:
TypeBest Practice
TextPrimary input type; most reliable
NumberConvert to string in prompt if needed
Object/ListSerialize as JSON string for reliable handling
For file inputs, use a Text Extraction task first to convert the file to text before passing to Custom Agent.

​
Output Variables

Custom Agent returns a single output called Agent Response, which contains the text generated by the LLM.
Unlike Opus Agent, Custom Agent always returns one text output. If you need multiple structured outputs:
  • use Opus Agent, or
  • parse the Custom Agent’s response in a downstream Opus Agent.

​
Using Custom Agent

1

Add the task

Drag a Custom Agent task into the builder.
2

Select a model

Choose your preferred LLM from the Model dropdown based on your requirements (capability, cost, latency).
3

Write the system prompt

Define the agent’s persona and behavior. Include explicit format instructions for structured outputs.
You are a data extraction assistant. Always return valid JSON
matching the provided schema. Do not include prose or explanations
outside the JSON structure.
4

Configure the user prompt

Write the task-specific instructions. Reference input variables using the templating syntax.
5

Set temperature

Use lower temperature (0) for consistent, deterministic outputs. Use higher temperature (closer to 1) for creative tasks.
6

Set output type and validate

Configure the output variable type. Preview with representative data to verify the output format.

​
Prompt Engineering For Reliability

The power of Custom Agent comes from precise prompt design. Follow these patterns for consistent results:

​
Enforce Structured Output

System Prompt:
You are a structured data extractor. Your responses must be valid JSON
matching this exact schema:
{
  "field1": "string",
  "field2": number,
  "field3": ["array", "of", "strings"]
}

Do not include any text outside the JSON. Do not include markdown code fences.
Return only the raw JSON object.

​
Maintain Consistency

System Prompt:
Always format dates as YYYY-MM-DD.
Always format currency as numbers without symbols (e.g., 1000.50).
Always use lowercase for category names.

​
Best Practices

Use Opus Text Extraction to extract text from files before passing to Custom Agent.
Include schema definitions directly in prompts:
  • “Return only valid JSON matching this schema: {...}”
  • “Do not include prose or markdown”
  • “Use null for missing fields, not empty strings”
For structured extraction and deterministic tasks:
  • Set temperature to 0 or near-0
  • Higher temperatures introduce variation
  • Reserve higher temperatures for creative tasks only

Opus Agent

Simplified AI tasks with auto-generated blueprints.

Agentic Review

AI-powered validation and repair for outputs.

Opus Code

Deterministic Python logic for type validation.

Builder Guide

Learn workflow design fundamentals.