Create prompts and models in AI Hub
Unlock the complete study guide.
Bundled into the existing Building Intelligent Applications premium course — no separate purchase.
14-day refund guarantee on one-time purchases and your first subscription charge.
Included in this chapter:
- Prompts and AI models in AI Hub
- Build a prompt from a template or from blank
- Prompt inputs: text, files, and Power Fx
- Ground a prompt with knowledge
- Choose the model a prompt runs on
- Tune prompt settings
- Text or JSON output
- Prebuilt and custom AI models
- Share prompts and AI models
- Call prompts and AI models from a canvas app
- Choose a text or image model by its output
- Run a prompt in a cloud flow
- Use AI Builder models in a cloud flow
- Prompt and AI model configuration by requirement
Prompt vs prebuilt AI model vs custom AI model
| Decision point | Prompt | Prebuilt AI model | Custom AI model |
|---|---|---|---|
| What you supply | A natural-language instruction, inputs, and optional knowledge | Nothing to train; the model is ready to use | Your own training data, such as sample documents, labeled text, or images |
| Fits when | The task is described in words: summarize, draft, rewrite, or answer from records | The task is common across businesses: receipts, language, sentiment, text recognition | The fields, categories, entities, or objects are unique to your business |
| Before first use | Test with sample input values, then save | None; add it and call it | Train, then publish the trained version |
| Canvas app call | Add data, then 'Prompt name'.Predict(...) | Add data > AI models, then Predict, or a prebuilt component | Add data > AI models, then Predict, or the form processor or object detector component |
| Cloud flow call | Run a prompt | The model's AI Builder action, such as Detect the language being used in the text | The model's AI Builder action, such as Process documents |
| What comes back | Text (default) or the saved JSON format | The model's fixed output fields, such as Language and Confidence | Your trained fields, classes, or objects, with confidence scores |
Decision tree
Cheat sheet
Unlock with Premium — includes all practice exams and the complete study guide.
Also tested in
References
- https://learn.microsoft.com/en-us/microsoft-copilot-studio/prompts-overview
- https://learn.microsoft.com/en-us/ai-builder/model-types
- https://learn.microsoft.com/en-us/credentials/certifications/resources/study-guides/ab-410
- https://learn.microsoft.com/en-us/ai-builder/use-a-custom-prompt-in-flow
- https://learn.microsoft.com/en-us/ai-builder/use-a-custom-prompt-in-app
- https://learn.microsoft.com/en-us/power-apps/maker/data-platform/prompt-column
- https://learn.microsoft.com/en-us/ai-builder/administer-licensing
- https://learn.microsoft.com/en-us/microsoft-copilot-studio/prompt-library
- https://learn.microsoft.com/en-us/microsoft-copilot-studio/create-custom-prompt
- https://learn.microsoft.com/en-us/microsoft-copilot-studio/add-inputs-prompt
- https://learn.microsoft.com/en-us/microsoft-copilot-studio/code-interpreter-for-prompts
- https://learn.microsoft.com/en-us/microsoft-copilot-studio/azure-openai-human-review
- https://learn.microsoft.com/en-us/microsoft-copilot-studio/use-your-own-prompt-data
- https://learn.microsoft.com/en-us/microsoft-copilot-studio/prompt-model-settings
- https://learn.microsoft.com/en-us/microsoft-copilot-studio/bring-your-own-model-prompts
- https://learn.microsoft.com/en-us/microsoft-copilot-studio/process-responses-json-output
- https://learn.microsoft.com/en-us/ai-builder/train-model
- https://learn.microsoft.com/en-us/ai-builder/manage-model
- https://learn.microsoft.com/en-us/ai-builder/publish-model
- https://learn.microsoft.com/en-us/ai-builder/form-processing-model-in-flow
- https://learn.microsoft.com/en-us/microsoft-copilot-studio/share-your-prompt
- https://learn.microsoft.com/en-us/ai-builder/share-model
- https://learn.microsoft.com/en-us/ai-builder/powerfx-in-powerapps
- https://learn.microsoft.com/en-us/ai-builder/use-in-powerapps-overview
- https://learn.microsoft.com/en-us/ai-builder/flow-text-recognition
- https://learn.microsoft.com/en-us/ai-builder/use-in-flow-overview
- https://learn.microsoft.com/en-us/troubleshoot/power-platform/ai-builder/power-automate/the-output-of-an-ai-builder-action-is-empty-in-power-automate-or-the-next-action-returns-an-error
- https://learn.microsoft.com/en-us/power-automate/guidance/coding-guidelines/asychronous-flow-pattern
- https://learn.microsoft.com/en-us/ai-builder/prebuilt-category-classification-pwr-automate
- https://learn.microsoft.com/en-us/ai-builder/flow-language-detection