---
title: "Advanced AI settings"
canonical_url: "https://www.nutrient.io/guides/workflow-automation/ai-capabilities-in-workflow/advanced-settings/"
md_url: "https://www.nutrient.io/guides/workflow-automation/ai-capabilities-in-workflow/advanced-settings.md"
last_updated: "2026-05-30T02:20:01.449Z"
description: "Fine-tune AI behavior in Nutrient Workflow Automation by configuring temperature, token limits, stop sequences, and other advanced parameters."
---

# Advanced AI settings

When configuring an AI feature, expand the **Advanced Settings** section to adjust AI behavior. These settings are available in the [AI Data Extraction task](https://www.nutrient.io/guides/workflow-automation/admin-guide/processes/tasks/integration-task/integration-task-ai-data-extraction.md) and other AI-powered features.

## Parameters

These parameters control how the AI model generates and returns responses.

### Temperature (0–2)

Temperature controls response randomness. Lower values produce more focused and deterministic output, while higher values introduce more variation.

Use temperature to tune consistency only after the prompt itself is clear and well-grounded. A lower temperature can make outputs more consistent, but it doesn’t make a weak prompt more accurate. For prompt-writing guidance, refer to the [prompt engineering for AI features](https://www.nutrient.io/guides/workflow-automation/ai-capabilities-in-workflow/prompt-engineering.md) guide.

- **0–0.3** — Use for structured data extraction where consistency matters — for example, when extracting invoice numbers or dates.

- **0.5–0.7** — General-purpose setting for most extraction tasks. Good for extracting summaries or descriptions.

- **1.0+** — Produces more creative and varied output.

### Top P (0–1)

Top P controls token selection diversity by limiting the pool of tokens the model considers, and works alongside temperature.

Adjust either **Top P** or **Temperature** first — not both at the same time — so you can tell which change improved consistency.

- **0.1** — Only the most probable tokens are considered. Use for highly predictable output like extracting IDs or amounts.

- **0.5–0.9** — Allows moderate diversity. Suitable for general extraction tasks.

- **1.0** — All tokens are considered. Use when the AI needs maximum flexibility, such as generating summaries.

### Max tokens

Max tokens sets the maximum length of the AI response. Higher token limits increase the cost per request, as most AI providers charge based on the number of tokens consumed.

### Stop sequences

Stop sequences are text patterns that stop AI response generation, preventing the model from producing unwanted content after the required data.

Use stop sequences to limit extra trailing output, but don’t rely on them to compensate for unclear prompts. In Workflow Automation, prompt quality should stay focused on the information you want the AI to extract or generate. For broader prompt design guidance, refer to [prompt engineering for AI features](https://www.nutrient.io/guides/workflow-automation/ai-capabilities-in-workflow/prompt-engineering.md).

- Setting `---` as a stop sequence prevents the AI from continuing past a logical boundary in its response.

- If your prompt asks the AI to return JSON, use `}` followed by a newline to prevent the model from appending extra text after the closing brace.

- If your extraction prompt returns a numbered list, a double newline (`\n\n`) can prevent the AI from adding unsolicited commentary after the extracted fields.

### Return to request detail

When enabled, the AI Data Extraction task processes in the background while users continue working. The extracted data becomes available once processing completes.

- **Enabled** — Recommended for large documents or complex prompts that take longer to process.

- **Disabled** — The user waits for the AI to finish before proceeding. Use for quick extractions where immediate results are expected.
---

## Related pages

- [AI in Nutrient Workflow Automation](/guides/workflow-automation/ai-capabilities-in-workflow.md)
- [Common AI configurations](/guides/workflow-automation/ai-capabilities-in-workflow/common-ai-configurations.md)
- [Write prompts that produce reliable AI results](/guides/workflow-automation/ai-capabilities-in-workflow/prompt-engineering.md)