🔒 Guided

Pre-launch preview. Authorised access only.

Incorrect code

Guided by A Guide to Cloud
Explore AB-900 AI-901 aws-aif-c01
Guided AB-620 Domain 2
Domain 2 — Module 3 of 12 25%
13 of 28 overall

AB-620 Study Guide

Domain 1: Plan and Configure Agent Solutions

  • Getting Started: Copilot Studio for Developers Free
  • Planning Enterprise Integration and Reusable Components Free
  • Identity Strategy for Agents Free
  • Channels, Deployment and Audience Design Free
  • Responsible AI and Security Governance Free
  • Agent Flows: Build, Monitor and Handle Errors Free
  • Human-in-the-Loop Agent Flows Free
  • Topics, Tools and Variables Free
  • Advanced Responses: Custom Prompts and Generative Answers Free
  • API Calls, HTTP Requests and Adaptive Cards Free

Domain 2: Integrate and Extend Agents in Copilot Studio

  • Enterprise Knowledge Sources: The Big Picture
  • Copilot Connectors and Power Platform Connectors
  • Azure AI Search as a Knowledge Source
  • Adding Tools: Custom Connectors and REST APIs
  • MCP Tools: Model Context Protocol in Action
  • Computer Use: Agent-Driven UI Automation
  • Multi-Agent Solutions: Design and Agent Reuse
  • Integrating Foundry Agents
  • Fabric Data Agents: Analytics Meets AI
  • A2A Protocol: Cross-Platform Agent Collaboration
  • Grounded Answers: Azure AI Search with Foundry
  • Foundry Model Catalog and Application Insights

Domain 3: Test and Manage Agents

  • Test Sets & Evaluation Methods
  • Reviewing Results & Tuning Performance
  • Solutions & Environment Variables
  • Power Platform Pipelines for Agent ALM
  • Agent Lifecycle: From Dev to Production
  • Exam Prep: Diagnostic Review

AB-620 Study Guide

Domain 1: Plan and Configure Agent Solutions

  • Getting Started: Copilot Studio for Developers Free
  • Planning Enterprise Integration and Reusable Components Free
  • Identity Strategy for Agents Free
  • Channels, Deployment and Audience Design Free
  • Responsible AI and Security Governance Free
  • Agent Flows: Build, Monitor and Handle Errors Free
  • Human-in-the-Loop Agent Flows Free
  • Topics, Tools and Variables Free
  • Advanced Responses: Custom Prompts and Generative Answers Free
  • API Calls, HTTP Requests and Adaptive Cards Free

Domain 2: Integrate and Extend Agents in Copilot Studio

  • Enterprise Knowledge Sources: The Big Picture
  • Copilot Connectors and Power Platform Connectors
  • Azure AI Search as a Knowledge Source
  • Adding Tools: Custom Connectors and REST APIs
  • MCP Tools: Model Context Protocol in Action
  • Computer Use: Agent-Driven UI Automation
  • Multi-Agent Solutions: Design and Agent Reuse
  • Integrating Foundry Agents
  • Fabric Data Agents: Analytics Meets AI
  • A2A Protocol: Cross-Platform Agent Collaboration
  • Grounded Answers: Azure AI Search with Foundry
  • Foundry Model Catalog and Application Insights

Domain 3: Test and Manage Agents

  • Test Sets & Evaluation Methods
  • Reviewing Results & Tuning Performance
  • Solutions & Environment Variables
  • Power Platform Pipelines for Agent ALM
  • Agent Lifecycle: From Dev to Production
  • Exam Prep: Diagnostic Review
Domain 2: Integrate and Extend Agents in Copilot Studio Premium ⏱ ~14 min read

Azure AI Search as a Knowledge Source

Semantic, vector, and hybrid search across document collections.

When your document collection outgrows simple search

☕ Simple explanation

Azure AI Search is like hiring a research librarian for your agent.

Copilot connectors and SharePoint knowledge work fine for thousands of documents. But when you have tens of thousands — or hundreds of thousands — of documents, and you need the agent to understand meaning, not just match keywords? That is when you bring in Azure AI Search.

It is a dedicated search engine that lives in Azure. You feed it your documents, it builds an index, and your Copilot Studio agent queries that index to find relevant answers. You get four search modes: keyword (exact match), vector (meaning-based), semantic (AI-ranked), and hybrid (best of all worlds).

Azure AI Search is a fully managed search-as-a-service platform in Azure. In the Copilot Studio context, it serves as the third knowledge pillar — offering enterprise-grade search capabilities that go beyond what Copilot connectors or Power Platform connectors provide.

Key architectural points: the search index lives in your Azure subscription (you control the region, tier, and network configuration). Documents are ingested via indexers (pull from Azure Blob Storage, Cosmos DB, SQL) or the push API. The index schema defines fields, types, and behaviours (searchable, filterable, facetable, sortable, retrievable). At query time, the agent sends a search request via REST API and receives ranked results.

Azure AI Search supports four search modalities — keyword, vector, semantic ranking, and hybrid — each suited to different query patterns. The exam tests your ability to choose the right mode and connect the index to Copilot Studio correctly.

The four search modes

Understanding these four modes is essential. The exam will present scenarios and expect you to pick the right one.

Azure AI Search: four modes of finding information
FeatureHow it worksStrengthsWeaknessesBest for
Keyword searchClassic BM25 text matching — searches for exact terms and variations in the indexFast, predictable, works well for technical terms, product codes, and exact phrasesMisses synonyms and conceptual matches — 'automobile' will not match 'car'Structured queries, known terminology, product SKU lookups
Vector searchConverts query and documents to numerical embeddings — finds conceptually similar contentUnderstands meaning — 'vehicle maintenance' matches 'car repair schedule'Requires an embedding model (Azure OpenAI), higher compute cost, embeddings must be generated at index timeNatural-language questions, cross-language search, finding conceptually related documents
Semantic rankingAI re-ranker on top of keyword results — promotes the most relevant passagesDramatically improves result quality for natural-language queries without needing embeddingsOnly re-ranks existing keyword results — cannot find documents that keyword search missedImproving keyword search quality when vector search is not feasible or not needed
Hybrid searchRuns keyword AND vector search in parallel, then fuses results with Reciprocal Rank Fusion (RRF)Gets the best of both — exact matches from keyword, conceptual matches from vectorMost complex setup, highest compute cost, requires embedding modelProduction workloads where query patterns are unpredictable — recommended default for most agents
💡 Exam tip: hybrid + semantic is the gold standard

For the exam, the recommended production pattern is hybrid search with semantic ranking. This gives you keyword precision, vector conceptual understanding, and AI-powered re-ranking in one query. If a question asks for the “best” or “recommended” approach for a Copilot Studio agent, hybrid + semantic is almost always the answer — unless constraints (cost, no embedding model) rule it out.

Index architecture — what you need to know

An Azure AI Search index is like a database table optimised for search. Understanding its structure helps you connect it correctly.

ComponentWhat it isWhy it matters
IndexA collection of documents with a defined schemaOne index per knowledge domain (e.g., one for medical papers, one for HR policies)
FieldsNamed attributes on each document (title, content, category, embedding)Fields marked as “searchable” are included in full-text search. Fields marked “filterable” support pre-query narrowing
IndexerAn automated pipeline that pulls data from a source into the indexBlob Storage, Cosmos DB, Azure SQL, and other sources. Runs on a schedule or on-demand
SkillsetOptional AI enrichment pipeline attached to an indexerOCR for scanned PDFs, language detection, entity extraction, chunking for vector search
Scoring profileCustom relevance tuning rulesBoost recent documents, prioritise certain fields, weight by category
💡 Chunking matters for RAG

When using vector search, documents must be split into chunks (typically 500-2,000 tokens). Each chunk gets its own embedding vector. The integrated vectorisation feature in Azure AI Search can handle chunking and embedding automatically using a skillset with the Azure OpenAI embedding skill. The exam may reference “integrated vectorisation” — it means the search service handles chunking + embedding during indexing so you do not need a separate pipeline.

Connecting Azure AI Search to Copilot Studio

The connection workflow has specific steps the exam expects you to know:

  1. Create the Azure AI Search resource in your Azure subscription (choose the tier based on volume — Free, Basic, Standard S1/S2/S3).
  2. Create an index — define the schema, configure fields, optionally add a skillset for enrichment.
  3. Populate the index — run an indexer or push data via the REST API.
  4. In Copilot Studio, go to the agent’s knowledge sources and select “Azure AI Search.”
  5. Provide the connection details: search service endpoint URL, index name, and authentication.
  6. Configure field mappings — tell Copilot Studio which index fields contain the title, content, and URL for citations.
  7. Test — ask questions in the test pane and verify the agent returns grounded answers from the index.

Authentication options

MethodHow it worksWhen to use
API keyPass the search service admin or query key in the request headerSimplest setup — good for development and testing
Managed identityCopilot Studio environment uses a system-assigned managed identity with RBAC role on the search serviceProduction recommended — no keys to rotate, follows zero-trust principles
Microsoft Entra ID tokenOAuth 2.0 bearer token from Entra IDAdvanced scenarios with fine-grained access control
💡 How this differs from Module 21 (Foundry RAG)

In Module 21, you will connect Azure AI Search through Azure AI Foundry to build a full RAG (Retrieval-Augmented Generation) pipeline with a Foundry model. In this module, the agent connects to Azure AI Search directly as a knowledge source — no Foundry model in between. The search results feed into Copilot Studio’s built-in generative answers capability. Same search service, different integration pattern. The exam distinguishes these two paths.

Scenario: Lena indexes 50,000 medical papers

Lena is the AI engineer at a healthcare analytics firm. Their clinical research team needs an agent that can answer questions across 50,000 published medical papers stored as PDFs in Azure Blob Storage.

Lena’s architecture: she creates an Azure AI Search resource (Standard S1 tier for the volume), builds an index with fields for title, authors, abstract, full_text, publication_date, and a vector field for embeddings. She configures an indexer with a skillset that includes OCR (some older papers are scanned images), text chunking (1,000-token chunks), and the Azure OpenAI embedding skill for vector search.

After the indexer runs, she connects the search index to the Copilot Studio agent using managed identity authentication. She maps the title, full_text, and a URL field for citations. In the test pane, she asks: “What are the latest findings on immunotherapy response rates in stage 3 melanoma?” The agent returns a grounded answer citing three specific papers with publication dates — powered by hybrid search (keyword for “melanoma” + vector for conceptual “immunotherapy response” matching) with semantic ranking.

50,000 papers, searchable in seconds.

Question

What are the four search modes in Azure AI Search?

Click or press Enter to reveal answer

Answer

1. Keyword (BM25 text matching), 2. Vector (embedding-based semantic similarity), 3. Semantic ranking (AI re-ranker on keyword results), 4. Hybrid (keyword + vector with Reciprocal Rank Fusion). The recommended default for agents is hybrid + semantic ranking.

Click to flip back

Question

What is integrated vectorisation in Azure AI Search?

Click or press Enter to reveal answer

Answer

A feature where the search service handles document chunking and embedding generation automatically during indexing via a skillset. You do not need a separate pipeline — the indexer, chunking skill, and Azure OpenAI embedding skill do it all.

Click to flip back

Question

What authentication method is recommended for production Azure AI Search connections?

Click or press Enter to reveal answer

Answer

Managed identity with RBAC. The Copilot Studio environment uses a system-assigned managed identity granted a role (e.g., Search Index Data Reader) on the search service. No API keys to manage or rotate.

Click to flip back

Question

How does Azure AI Search as a direct knowledge source differ from the Foundry RAG pattern?

Click or press Enter to reveal answer

Answer

Direct: agent queries Azure AI Search → results feed into Copilot Studio's built-in generative answers. Foundry RAG: agent calls a Foundry model that queries Azure AI Search internally → model generates the response. Same search service, different integration pattern.

Click to flip back

Question

What index field behaviours must a developer understand when building a schema?

Click or press Enter to reveal answer

Answer

Searchable (included in full-text search), Filterable (used in pre-query filters like OData), Sortable (used for result ordering), Facetable (used for faceted navigation), Retrievable (returned in results). A field not marked searchable will never match a text query.

Click to flip back

Knowledge Check

Lena's healthcare agent needs to find papers about 'treatment efficacy for resistant tumours' even when papers use terms like 'therapeutic effectiveness' and 'refractory neoplasms.' Which search mode handles this best?

Knowledge Check

A developer connects Azure AI Search to their Copilot Studio agent but the agent never returns results from one specific field. What is the most likely cause?

Knowledge Check

Which authentication method is recommended for a production Copilot Studio agent connecting to Azure AI Search?

🎬 Video coming soon

Azure AI Search as a Knowledge Source

← Previous

Copilot Connectors and Power Platform Connectors

Next →

Adding Tools: Custom Connectors and REST APIs

Guided

I learn, I simplify, I share.

A Guide to Cloud YouTube Feedback

© 2026 Sutheesh. All rights reserved.

Guided is an independent study resource and is not affiliated with, endorsed by, or officially connected to Microsoft. Microsoft, Azure, and related trademarks are property of Microsoft Corporation. Always verify information against Microsoft Learn.