-
Module 1: AI in the context of SQL Server
10 Lessons-
StartModule introduction
-
StartAI features in SQL Server 2025
-
StartWhat is new in SQL Server 2025
-
StartWhat SQL Server is responsible for
-
StartWhat SQL Server is not responsible for
-
StartMisconceptions to avoid
-
StartPositioning SQL Server correctly
-
StartLab 1
-
StartLab 1 video walkthroughs
-
StartQuiz 1
-
-
Module 2: Vector data and embeddings fundamentals
15 Lessons-
StartModule introduction
-
StartWhat is an AI model?
-
StartWhat embeddings are and why they exist
-
StartHow vector similarity differs from relational comparison
-
StartHow SQL Server uses vector similarity
-
StartTypical AI scenarios that involve vectors
-
StartWhy vectors work well for these scenarios
-
StartWhen vectors are inappropriate
-
StartHow this applies to SQL Server
-
StartHow to think about vectors going forward
-
StartWhere embeddings models are hosted
-
StartCommon embeddings models
-
StartLab 2
-
StartLab 2 video walkthroughs
-
StartQuiz 2
-
-
Module 3: Vector data types in SQL Server
17 Lessons-
StartModule introduction
-
StartVector data type basics
-
StartDeclaring VECTOR columns and variables
-
StartHow VECTOR values are represented
-
StartEmbeddings as derived data
-
StartPractical table pattern for embeddings
-
StartVectors complement relational data
-
StartParallel tables and schema evolution
-
StartDimensionality is enforced
-
StartDimensionality changes are migration events
-
StartStorage characteristics of VECTOR
-
Startfloat16 vectors
-
StartVECTOR limitations in SQL Server
-
StartLab 3
-
StartLab 3 solution
-
StartLab 3 video walkthroughs
-
StartQuiz 3
-
-
Module 4: Querying vector data
16 Lessons-
StartModule introduction
-
StartWhat similarity search means in T-SQL
-
StartExact similarity vs approximate search
-
StartWriting similarity queries in T-SQL
-
StartUsing VECTOR_DISTANCE
-
StartCombining vector similarity with relational predicates
-
StartUsing VECTOR_SEARCH
-
StartCommon query mistakes and inefficiencies
-
StartHow to reason about vector queries in T-SQL
-
StartUsing VECTOR_NORM
-
StartUsing VECTOR_NORMALIZE
-
StartUsing VECTORPROPERTY
-
StartLab 4
-
StartLab 4 solution
-
StartLab 4 video walkthroughs
-
StartQuiz 4
-
-
Module 5: Vector indexing and performance
13 Lessons-
StartModule introduction
-
StartWhy vector indexing exists
-
StartVector index characteristics
-
StartOperational constraints of vector indexes
-
StartCreating a vector index
-
StartAccuracy versus performance trade-offs
-
StartCPU and memory impact of vector queries
-
StartMonitoring and diagnosing vector query performance
-
StartWhen vector indexes should not be used
-
StartLab 5
-
StartLab 5 solution
-
StartLab 5 video walkthroughs
-
StartQuiz 5
-
-
Module 6: Generating embeddings outside SQL Server
9 Lessons-
StartModule introduction
-
StartWhy SQL Server does not generate embeddings
-
StartCommon embedding generation patterns
-
StartStoring embeddings safely in SQL Server
-
StartRefreshing and regenerating embeddings
-
StartHandling changes in embedding models
-
StartVersioning strategies for embeddings
-
StartRe-embedding strategies at scale
-
StartQuiz 6
-
-
Module 7: REST and HTTP basics
14 Lessons-
StartModule introduction
-
StartWhat REST means in practice
-
StartCore HTTP concepts
-
StartJSON as a data format
-
StartAuthentication at a conceptual level
-
StartError handling and diagnostics
-
StartHow REST concepts apply to SQL Server integrations
-
StartWhat SQL Server professionals need to know
-
StartUsing Caddy as a proxy
-
StartTesting the Caddy proxy
-
StartLab 7
-
StartLab 7 solution
-
StartLab 7 video walkthroughs
-
StartQuiz 7
-
-
Module 8: Calling AI services from SQL Server
19 Lessons-
StartModule introduction
-
StartSynchronous vs asynchronous calls
-
StartPatterns for invoking external AI services
-
StartSecurity considerations for outbound calls
-
StartCost and throttling implications
-
StartOperational risks and failure modes
-
StartDesigning SQL Server–safe AI integrations
-
StartUsing sp_invoke_external_rest_endpoint
-
StartCalling sp_invoke_external_rest_endpoint
-
StartMinimal structure of a REST call in T-SQL
-
StartRetrieving text embeddings via SQL Server REST
-
StartUsing CREATE EXTERNAL MODEL
-
StartUsing AI_GENERATE_EMBEDDINGS
-
StartHandling REST authentication
-
StartSupported external model types
-
StartLab 8
-
StartLab 8 solution
-
StartLab 8 video walkthroughs
-
StartQuiz 8
-
-
Module 9: Retrieval-augmented query patterns
12 Lessons-
StartModule introduction
-
StartWhat RAG means in practical terms
-
StartDesigning SQL tables for retrieval
-
StartExecuting similarity search as part of a workflow
-
StartPassing retrieved data to AI services
-
StartLimitations of RAG for SQL Server
-
StartFailure modes in SQL Server–based RAG
-
StartHow to use SQL Server effectively in RAG
-
StartLab 9
-
StartLab 9 solution
-
StartLab 9 video walkthroughs
-
StartQuiz 9
-
-
Module 10: Security, governance, and operational concerns
9 Lessons-
StartModule introduction
-
StartProtecting sensitive data used in AI workflows
-
StartControlling access to vector data
-
StartAuditing AI-related queries
-
StartManaging secrets and credentials
-
StartOperational risks introduced by AI features
-
StartGovernance boundaries in AI-enabled systems
-
StartHow to approach AI governance with SQL Server
-
StartQuiz 10
-
-
Module 11: When NOT to use AI features in SQL Server
8 Lessons-
StartModule introduction
-
StartWhy it matters to say no
-
StartScenarios where SQL Server is the wrong tool
-
StartWhen a separate vector database makes more sense
-
StartWhen Fabric or other platforms are more appropriate
-
StartCost, complexity, and maintenance trade-offs
-
StartDecision checklist for architects and DBAs
-
StartQuiz 11
-
Using AI Features in SQL Server 2025
Store, retrieve, and integrate data for AI systems using SQL Server
Course Summary
Do you want to start working with AI-related features in SQL Server 2025?
As these features are relatively new, the focus of this course is on design and architecture decisions that remain valid, even as individual features, syntax, and external AI services evolve. It does not aim to turn SQL Server into an AI platform, nor does it attempt to teach model training, data science, or vendor-specific AI tooling.
This course is about using SQL Server to store, retrieve, and integrate data for AI systems, in a way that is reliable, understandable, and operationally sound. We assume you already understand SQL Server fundamentals and are comfortable working with T-SQL and database design.
— Are you responsible for deciding where AI-related logic should live, and where it should not?
— Do you need to support vector search, retrieval, or AI integration without turning the database into an experimental system?
— Have you been asked whether SQL Server should be used for embeddings, RAG patterns, or AI orchestration, and wanted a clear answer that you can explain?
If that matches the kind of responsibility you have, you’re in the right place. You'll get clear explanations, hands-on exercises, and short quizzes to make sure you not only understand the concepts but can confidently apply them in real SQL Server environments. And while the practical exercises are optional, we strongly encourage completing them. They are designed to be straightforward and focused on realistic scenarios, rather than tooling complexity. Setup is easy. The main requirement is access to a SQL Server 2025 environment (trial or production) or a system you can install SQL Server on.
