# How LLMOps Differs — MLOps

Source: https://www.skillbyai.com/en/mlops/g-llmops

> Same principles, different artefacts.

## Prompts, providers, evaluation and cost

Systems built on large language models follow the same MLOps principles with different emphasis. The versioned artefacts are often **prompts, retrieval settings and model choices** rather than trained weights; the provider may update models underneath you. **Evaluation** relies on test sets of questions, rubric-based or model-based grading, and human review. **Monitoring** adds token cost, latency, refusal and hallucination signals, safety filters and user feedback. Release practices (gates, canaries, rollback) apply unchanged.

## Classic MLOps versus LLMOps

Where the emphasis moves.

```text
                 classic ML                         LLM applications
main artefact    trained model weights              prompts, retrieval config, model id
training         you train regularly                mostly provider-trained; fine-tune sometimes
evaluation       labelled metrics                   eval sets + rubric/LLM graders + humans
monitoring       drift, accuracy                    cost, latency, quality samples, safety, feedback
change risk      new data / retraining              prompt edits, provider model updates
```

## Pin model versions

Use dated model identifiers where providers offer them, and re-run evaluations before switching.

**Quiz:** What is often the main versioned artefact in LLM applications?

- [ ] The training dataset of the provider
- [ ] Only GPU drivers
- [x] Prompts, retrieval settings and the chosen model id
- [ ] The office floor plan

*Answer:* Prompts, retrieval settings and the chosen model id. Version what you control.