Official Technical Resources: Microsoft (page 19)
Official Technical Resources · Microsoft: 312 entries in total; this page lists entries 271–285.
CLU multi-turn conversations
Learn how CLU handles entity slot-filling across multi-turn conversations.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Supervised Learning · Embedding
Link last checked: 2026-09-24
Multilingual projects
Learn about how to make use of multilingual projects in conversational language understanding.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Supervised Learning · Embedding
Link last checked: 2026-09-24
Evaluation metrics for custom named entity recognition models
Learn about evaluation metrics in Custom Named Entity Recognition (NER)
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Model Evaluation and Benchmarks · Large Language Model (LLM)
Link last checked: 2026-09-24
Custom text classification model concepts
Learn core concepts for custom text classification models: evaluation metrics and accepted data formats.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Model Evaluation and Benchmarks · Large Language Model (LLM)
Link last checked: 2026-09-24
Resolve entities to standard formats
Learn about entity resolutions in the Named Entity Recognition feature.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Supervised Learning · Embedding
Link last checked: 2026-09-24
Named entity categories and types
Learn about the entities the NER feature can recognize from unstructured text.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Supervised Learning · Embedding
Link last checked: 2026-09-24
Orchestration workflow model concepts
Learn core concepts for orchestration workflow models: evaluation metrics and accepted data formats.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Model Evaluation and Benchmarks · Large Language Model (LLM)
Link last checked: 2026-09-24
Back up and recover your orchestration workflow models
Learn how to save and recover your orchestration workflow models.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Workflow Orchestration · Multi-agent Orchestration
Link last checked: 2026-09-24
The "None" intent in orchestration workflow
Learn about the default None intent in orchestration workflow.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Workflow Orchestration · Multi-agent Orchestration
Link last checked: 2026-09-24
Orchestration workflow limits
Learn about the data, region, and throughput limits for Orchestration workflow
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: Workflow Orchestration · Multi-agent Orchestration
Link last checked: 2026-09-24
Recognized conversational PII entities
Learn about the types of entities the conversational PII feature can detect and identify within conversation inputs.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: AI Agent · Agent Frameworks
Link last checked: 2026-09-24
Recognized PII and PHI entities
Learn about the types of entities the PII feature can detect and identify within unstructured text.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: AI Agent · Agent Frameworks
Link last checked: 2026-09-24
Custom question answering best practices
Use these best practices to improve your project and provide better results to your application/chat bot's end users.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: AI Agent · Agent Frameworks
Link last checked: 2026-09-24
Confidence score
When a user query is matched against a knowledge base, Custom question answering returns relevant answers, along with a confidence score.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: AI Agent · Agent Frameworks
Link last checked: 2026-09-24
Project limits and boundaries
Custom question answering has meta-limits for parts of the knowledge base and service. It's important to keep your knowledge base within those limits in order to test and publish.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only Microsoft's own implementation and claims. Recheck preview features and product lifecycle before use.
Related concepts: AI Agent · Agent Frameworks
Link last checked: 2026-09-24