Fine-tuned model management

Understand recommended and checkpoint model labels

Interpret the model-table badges accurately. The guide then takes you through the correct route, the checks to complete before making changes, the workflow in order, and the evidence to review afterwards.

Audience: CRM administrators and authorised staffPermission: Settings: ViewModule v1.0.0

Jump to steps

Where to goAdmin Area → Setup → Settings → AI → OpenAI → Advanced Features → OpenAI Fine Tuning

Before you start

Use an account with Settings: View and confirm the intended record or setting before making a change.
Follow the exact route above. If the screen or action is absent, check module activation, ownership and permissions rather than using another person’s account.
Use controlled test data for configuration, integration, email, AI, payment, portal or automation changes before production-wide use.

What you’ll accomplish

Interpret the model-table badges accurately. The instructions reflect the supplied module’s registered menus, controller actions, views, settings and code-backed validation flow.

Follow these steps

Go to Admin Area → Setup → Settings → AI → OpenAI → Advanced Features → OpenAI Fine Tuning.
Select the relevant record, filter, report, model or configuration described below.
Use the displayed action or read the current values without altering unrelated data.
Compare the output with the code-backed rules and expected result in this guide.
Record or correct any mismatch before relying on the output in production.

Fields and options to review

ActionUnderstand recommended and checkpoint model labels

Exact navigationAdmin Area → Setup → Settings → AI → OpenAI → Advanced Features → OpenAI Fine Tuning

Module version1.0.0

VerificationVerify the saved record, status, output or setting in the same workspace and review any linked activity, file or notification.

Rules the system enforces

A pcrm-owned model without :ckpt-step- is marked recommended.
Checkpoint entries are not marked recommended by that condition.

How to confirm it worked

The supported understand recommended and checkpoint model labels flow completes without bypassing permission or validation checks.
The resulting record, setting, status, file, delivery event or external response is visible from the relevant workspace.
Unexpected validation, provider or linked-record errors are investigated before retrying.

Security, privacy and operational checks

Restrict the API key and AI settings to authorised administrators.
Do not submit confidential, special-category or unnecessary personal data to the external AI provider.
Check generated text before using it in customer, staff, legal, financial or compliance communication.
Monitor provider billing and retention independently because this module has no built-in cost dashboard.

Was this guide useful?Your response is stored only in this browser.