Start an OpenAI fine-tuning job
Create and upload training JSONL and submit a job with the selected base model.
Exact navigationAdmin Area → Setup → Settings → AI → OpenAI → Advanced Features → OpenAI Fine Tuning
Before you begin
- Use an account with Settings: Edit 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 this guide covers
Create and upload training JSONL and submit a job with the selected base model. The instructions reflect the supplied module’s registered menus, controller actions, views, settings and code-backed validation flow.
Exact step-by-step process
- Open Admin Area → Setup → Settings → AI → OpenAI → Advanced Features → OpenAI Fine Tuning.
- Choose the New, Add, Create or Start action exposed on that screen.
- Complete the required fields described below and review any linked record, currency, tax, approval or recipient selection.
- Save or submit the form once; correct any validation message rather than bypassing it.
- Open the resulting record and verify its number, status, totals, files, activity and downstream links.
Fields, choices and supported possibilities
ActionStart an OpenAI fine-tuning job
Exact navigationAdmin Area → Setup → Settings → AI → OpenAI → Advanced Features → OpenAI Fine Tuning
Module version1.0.0
VerificationConfirm the saved record, status, output or setting in the same workspace and review any linked activity, file or notification.
Code-backed validations and workflow rules
- Starting a new job first attempts to delete previous pcrm-owned fine-tuned models.
- The endpoint returns a failure message instead of a job ID if data collection or provider submission fails.
Expected result and verification
- The supported start an openai fine-tuning job 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.
- Review 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.