Custom AI Models

Create and train custom AI Models to return better results when generating Load and Truck Postings.

Train new models based on customer email requests and user-submitted requests from the Text to Load and Text to Truck Posting Lightning Web Components (LWCs).

Note: The Winter ’26 TMS release includes support for the gpt-5 and gpt-5-mini AI models. These models are faster and more accurate than previous versions and includes the use of reasoning. However, these models and custom models using GPT5 are not available for training yet. Instead, use the AI Description field in the AI Console Configuration for prompt engineering to return better responses.

From the AI Console - Activity console, select the Model Training button to view the Model Training console.

Create a Custom AI Model

Custom AI Models are generated from existing models and trained on returned Load and Truck Posting records from Artimus. Currently, a custom AI Model cannot be trained multiple times. A new model must be created and trained off of an existing model, including custom models.

1. Select the Add button in the AI Models header. This opens the Add AI Model modal.
   

2. Enter a Model Name and search for and select a Parent Model.

   Note: The non-mini GPT AI models typically returns better results, but takes more time to finish. The GPT-mini models returns results more quickly, but may not be as accurate.

3. Check the Enabled box. This field adds the new model to the AI Model field in the AI Console Configuration.

4. Check the Is Custom Model box. All user-created AI models are custom models.

5. Click Save.

The new custom AI model is added to the list in the AI Models section.

Note: All available GPT5 AI models (gpt-5 or gpt-5-mini) and any custom models where the Parent Model is a GPT5 model have the Reasoning Enabled field set to true.

Create Training Sets

Create AI Model Training Sets to train the AI Model. Training Sets consist of AI Model Training records.

Note: Training records are created from the output generated by Artimus. Review the output and correct any fields before creating training records.

Create a Training Set record by selecting the Add button in the AI Model Training Sets header. This opens the Add AI Model Training Set modal.

In the modal, enter a Name and an optional Description for the AI Model Training Set. Select Save.

The new training set is added to the list in the AI Model Training Sets list. Return to the AI Console by selecting the Activity button.

Create Training Records

Review and correct Load or Truck Posting records as necessary to train a custom AI Model.

1. Select a Load or Truck Posting record from the AI Console activity section.

2. View the input sent to the AI to generate the record.

3. In the Output from AI section, view the returned field values. Update any values that returned incorrectly.

4. Set the Confidence Score to 100.

5. Click the Save button to keep any field changes.

6. View the JSON payload with the JSON button returned from the AI.

Select the Create Training Record button to open the modal. Choose the AI Model Training Set to add the Training Record to that set. Select Create.

Create additional Training Records from a Load or Truck Posting record type and add them to the Training Set.

Note: Training Sets should consist of approximately 10-200 Training Records.

Edit and Upload Training Sets

Select the Model Training button to switch back to the Model Training console. When an AI Model Training Set is selected, all the Training Records are displayed in the AI Model Training Records section.

View AI Model Training Set information with the Edit button.

The Edit Training Set modal allows you to change the Training Set name or add a Description.

The available buttons complete the following actions:

• Preview: Preview the system prompts, user prompts from the Input to AI field, and the returned JSON from the user prompt for each Training Record in the Training Set modal.

  Note: If any records require changes, return to the individual record and update the fields as necessary. Only corrected Load or Truck Posting records should be used in Training Sets.

• Upload: Send the AI Model Training Set. This action updates the Upload Status and API File ID.

• Save: Save the AI Model Training Set with the edited Name and Description.

• Clone: Create a copy of the AI Model Training Set.

• Cancel: Discard any changes and return to the Model Training console.

Preview Button

Upload Button

Conduct Training Sessions

To use a Training Set, it must first be sent to OpenAI. Click the Upload button. The Upload Status appears in the AI Console as Uploaded when the Training Set is successfully received.

Note: A single Training Set may be used to train multiple AI Models.

Once the Training Set is uploaded, create a new Training Session by selecting the Add button in the AI Model Training Sessions header.

This opens the Add AI Model Training Session modal.

Select the AI Model Training Set and a Validation Training Set. The Training Set makes changes to the AI Model and the Validation Training Set verifies that those changes are correct.

Note: A Validation Training Set is not required but is recommended.

Click Save to create the AI Model Training Session record and return to the Model Training console.

Select the AI Model to train. The AI Model Training Session appears in the console. Select the Edit button to view the record.

This opens the Edit Training Session modal. Select the Start Training button.

Warning: All available GPT5 models (gpt-5 and gpt-5-mini) and any custom AI models that use the GPT5 models as the Parent Model is not available for fine-tuning.

The Status field for the Training Session updates to Validating.

Use the Refresh button on the Training Session record to view the latest status update.

Note: Training an AI Model may take several minutes.

When the Training Session completes successfully, the newly-trained AI Model may be used to create Load and Truck Posting records:

1. Return to the Activity screen of the AI Console by selecting the Activity button.

2. Click the Configuration button in the banner.

3. Select the new model from the AI Model picklist.

4. Click Save.