AI-200 study guide
AI-200 · Work through your exam, one topic at a time.
AI-200: Developing AI Cloud Solutions on Azure is a role-based credential aimed at developers who build, deploy and operate AI workloads on Azure, rather than at researchers who only train models. It assumes working knowledge of a programming language (usually Python or C#), REST APIs and the Azure portal, and it tests whether you can move an AI capability from a prototype to a governed production service. The AI-200 study guide has 6 sections and about 1,907 words.
01Plan and manage an Azure AI solution
Every AI-200 scenario is assembled from the same parts: an Azure AI Services resource (multi-service or single-service), Azure OpenAI model deployments, an Azure AI Search service, a storage account, and - in Foundry-based designs - a hub with one or more projects plus connections to those services. Ask early which boundary owns each setting: identity and networking usually sit at the resource or hub level, while deployments, indexes, and evaluation runs live in the project or service itself.
339 words, about 2 min02Implement generative AI solutions
A chat completion request is a list of role-tagged messages: system (behaviour and constraints), user, and assistant (few-shot examples or prior turns). The system message is the cheapest place to fix tone, format, and refusal behaviour.
293 words, about 1 min03Implement agentic solutions
An agent = a model + instructions + tools + state, in a loop that decides which tool to call until the goal is met. In Azure AI Agent Service you define the agent, create a thread to hold conversation state, and start runs; the service executes tool calls server-side and appends results to the thread.
317 words, about 2 min04Implement computer vision solutions
Azure AI Vision image analysis returns captions, dense captions, tags, objects with bounding boxes, people, and Read-based OCR. Custom Vision (or Foundry custom models) trains on your own images: image classification gives one or more labels per image; object detection returns labels plus bounding boxes and can count instances.
324 words, about 2 min05Implement natural language processing solutions
Azure AI Language offers prebuilt capabilities with no training: sentiment, opinion mining, key phrase extraction, entity recognition (including PII detection with masking), language detection, summarization, and text analytics for health. Custom capabilities require labelled data: conversational language understanding (CLU) for intents and entities in utterances, custom named entity recognition, and custom text classification (single-label or multi-label).
308 words, about 2 min06Implement information extraction and knowledge mining solutions
Azure AI Search mining follows a fixed chain: data source (Blob, ADLS, SQL, Cosmos DB) → indexer (scheduling, change detection, field mappings) → skillset (AI enrichment) → index (searchable, filterable, sortable fields). Skills build an enrichment tree rooted at /document; built-in skills include OCR, text merge, text split (chunking), language detection, entity recognition, key phrase extraction, entity linking, Document Intelligence layout, embedding, and an Azure OpenAI chat completion skill.
326 words, about 2 min