# AI service design

URL: https://donedeploy.com/devops-services/ai-service-design/

[!AI · November 2, 2026CI/CD for Models and PromptsEvaluation gates, model registries, canary releases and rollback: applying CI/CD discipline to prompts and models in LLM applications.](https://donedeploy.com/cicd-for-llms/)[!AI · October 23, 2026Fine-Tuning or Prompting? A Decision Guide for Small TeamsWhen prompting, RAG or fine-tuning is the right way to adapt a language model, and what each one costs a small engineering team.](https://donedeploy.com/fine-tuning-or-prompting/)

Related services

## Often done together

[**AI observability**Know what is wrong, and why, before your customers tell you*Learn more »*](https://donedeploy.com/devops-services/monitoring/)[**Automation with AI**Hand repetitive engineering and business work to automation you control*Learn more »*](https://donedeploy.com/devops-services/ai-automation/)[**Containers and orchestration**Containers and Kubernetes sized for your team, not for a giant*Learn more »*](https://donedeploy.com/devops-services/containers-and-orchestration/)

Questions

## Frequently asked

Should we self-host a model or use an API?

APIs are quicker to start with and need no GPUs; self-hosting gives more control over data and can be cheaper at steady, high volume. We work out which fits your case.

Can our data stay in Ireland or the EU?

Yes, by choosing EU regions for hosted services or self-hosting open models in your own cloud account. We document where data flows.

How do we know the AI gives good answers?

We build an evaluation set from your real cases and run it on every change of model, prompt or data.

Tell us what you run and what you want to change. We reply personally, and the first consultation is free.

[Let's talk »](https://donedeploy.com/lets-talk/)