> ## Documentation Index
> Fetch the complete documentation index at: https://docs.validio.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Generating Validator Recommendations

> Learn how to use Validio's LLM-powered recommendations to quickly set up monitoring on your sources with pre-configured validators.

Validio Recommendations use AI and ML to automatically analyze your data sources and suggest pre-configured validators, streamlining the setup of comprehensive data monitoring.

![The Validators tab of a source with the AI recommendations action available](https://mintcdn.com/validio/30m58lWK6Ph-vklQ/images/docs/ai-features/800-recommendations-ai.png?fit=max\&auto=format\&n=30m58lWK6Ph-vklQ\&q=85\&s=d54ab3dba39056e5a72caa498c023584)

Configure Validators with AI recommendations

Setting up comprehensive data monitoring can be time-consuming when configuring validators individually. **Recommendations** streamline this process by automatically analyzing your data source and suggesting appropriate validators tailored to your schema and data patterns.

Validio offers two recommendation modes:

* **AI recommendations:** Uses LLM-powered analysis for context-aware suggestions (requires LLM credentials).
* **ML recommendations:** Uses statistical machine learning and heuristics

Both modes allow you to profile your data and review existing resources to suggest pre-configured windows, filters, and segmentations alongside validators. You can then select which recommendations to apply, creating multiple validators and resources at once.

## Prerequisites for AI recommendations

To generate recommendations using LLMs, ensure that you have the following:

* Enabled the **Allow LLM credentials** setting in your Validio Workspace. See [Managing Workspace Settings](https://docs.validio.io/v11.0/docs/access-and-settings/settings/workspace-settings.md).
* Appropriate permissions to create credentials (`credentials:WRITE` permissions for the Namespace). See [Managing Roles](https://docs.validio.io/v11.0/docs/access-and-settings/settings/managing-roles.md).
* At least one LLM credential configured in your environment. See [LLM Credentials](https://docs.validio.io/v11.0/docs/integrations/llm-credentials.md).

## Generating recommendations

On the **Validators** tab for a configured Source,

1. Click **AI recommendations** (or **New recommendations** if you do not have an LLM credential).

   ![The recommendations dialog with data profiling, guidance notes, and LLM credential options](https://mintcdn.com/validio/30m58lWK6Ph-vklQ/images/docs/ai-features/800-recommendations-config.png?fit=max\&auto=format\&n=30m58lWK6Ph-vklQ\&q=85\&s=5f11da52591f3214d136d36b50ea5f79)

   AI recommendation options

2. (Optional) In the dialog window, toggle **Use data profiling**. Profiling increases the accuracy of the recommendations.
   * **Sampling Percentage**: (Only available for tables and materialized views.) Use the slider or enter a number to adjust the percentage of data to include in profiling. A higher sampling percentage results in more accurate results, but reads more data and takes longer to complete.

   * **Data Scope**: (Recommended) Cap the execution time on large datasets by limiting the fields and number of rows used for profiling:

     | Setting | Description |
     | :- | :- |
     | Fields | Select specific fields to analyze. By default, all fields are profiled. |
     | Row limit | Set the maximum number of rows to include in the profiling run. |

   * **Lookback Filter**: (Recommended) Limit the data volume scanned by targeting only a specific window of recent data:

     | Setting | Description |
     | :- | :- |
     | Lookback field | Select a timestamp or date field to define the profiling window. This limits the scan to recent data rather than scanning the full dataset. |
     | Lookback duration | The specific amount of time to look back when filtering data. Use this with the **Lookback field** to target only recent records and optimize performance. |

3. (Optional) Add **Guidance notes** to provide domain knowledge or business context, such as key metrics to monitor, data quality priorities, or specific fields to focus on. Guidance notes are used only for AI recommendations, when you select an LLM credential in the next step. Statistical ML ignores them.

4. Choose an LLM credential or **Use statistical ML**. When you have an LLM credential, it is selected by default, but you can still choose **Use statistical ML**, for example to get recommendations without sending source metadata to an LLM provider. If you do not have an LLM credential, **Use statistical ML** is the only option.

5. Click **Run**.

   * Click **Processing** to view a progress checklist as the system and model gathers information and generates recommendations. The process runs in the background, so you can navigate away while it completes.
   * To cancel a processing recommendation, click **Cancel**.

   ![The recommendations progress checklist showing each step as the agent works](https://mintcdn.com/validio/30m58lWK6Ph-vklQ/images/docs/ai-features/800-recommendations-progress.png?fit=max\&auto=format\&n=30m58lWK6Ph-vklQ\&q=85\&s=80f313992fd5442048555673761ff3e3)

   The recommendations agent runs in the background, but you can view its progress

6. Click **View recommendations** to see the list of pre-configured **Validators** as well as relevant **Windows**, **Filters**, and **Segmentations**. The **Requires** column indicates dependencies between the resources.

   ![The generated recommendations list with validators, windows, filters, and segmentations and their dependencies](https://mintcdn.com/validio/30m58lWK6Ph-vklQ/images/docs/ai-features/900-validator-recommendations.png?fit=max\&auto=format\&n=30m58lWK6Ph-vklQ\&q=85\&s=e50f4554ff98ee0a047d8d37f6f2ea16)

   Generated recommendations list

7. Check each of the resources that you want to apply to your source. If you uncheck one resource (such as a segmentation), it will automatically uncheck all validators that require that resource.

8. Click **Apply selected** to create the recommended validators. If you are creating many validators at once, this may take a few minutes to process.

   Once they are created, the validators will automatically backfill with historical data. It may take a few minutes for the data to populate while this initial sync completes.