How-To Guides
These guides are recipe-style — each one shows a complete .prompty file and
the code to run it. Copy, paste, fill in your API keys, and go.
Providers
Section titled “Providers”Use with OpenAIChat completions with the OpenAI API and API key auth.
Use with Microsoft FoundryFoundry project endpoints with API key and Microsoft Entra ID auth.
Use with AnthropicChat completions using Anthropic Claude.
Discover Available ModelsList models and deployments before choosing model.id.
Custom ProvidersBuild your own executor and processor for any LLM.
Features
Section titled “Features”Agent with Tool CallingDefine tools, register handlers, and let the agent loop call them.
Streaming ResponsesStream tokens in real time with PromptyStream and tracing.
Structured OutputGet typed JSON back matching an output schema you define.
EmbeddingsGenerate text embeddings with apiType: embedding.
Image GenerationGenerate images with DALL-E via apiType: image.
Development
Section titled “Development”Testing Your PromptsUnit test .prompty files without calling the LLM.
Run Live Provider TestsExercise Prompty against real endpoints before publishing packages.
TroubleshootingSolutions to common errors and issues.
Reference
Section titled “Reference”CookbookReady-to-use .prompty examples — copy, customize, and run.