Quick Reference: Technology by Need

This page provides fast-lookup tables for common scenarios and common “starting points.” For detailed decision logic (and to avoid overfitting to a tool too early), see the Decision Framework.

Table of contents

  1. CAF Agent Adoption Quick Cues
  2. Technology by User Experience
  3. Agentic Retrieval Quick Facts
  4. Agent Development Approach Comparison
  5. Custom Engine Agent Tool Comparison
  6. Data Grounding Pattern by Source
  7. Memory & Analytics by Technology
  8. Orchestration Complexity Decision Matrix
  9. Budget & Timeline Quick Guide
  10. Governance Decision Quick Reference

CAF Agent Adoption Quick Cues

  • Phases in one line: Plan (business + tech + org + data), Govern & secure (responsible AI, controls, environment prep), Build (single vs multi, orchestrate, secure process), Operate (integrate, monitor, retire). CAF AI agent adoption.
  • When not to use an agent: Highly deterministic workflows or static Q&A/content generation → use code or plain RAG. Business plan.
  • SaaS vs build: Use SaaS agents when they meet requirements; if not, prototype on Foundry or Copilot Studio before committing to custom builds. Technology plan.
  • Single vs multi: Start single; go multi-agent only for hard security/compliance boundaries, distinct owning teams, or planned modular growth. Single vs multiple.
  • Prioritize use cases fast: Score business impact, feasibility, desirability; pick high-impact, low-friction pilots first.
  • Org roles: Platform owns guardrails, workload teams own use cases and data, AI CoE advises and standardizes. Organizational readiness.
  • Build safely: Use workflows for deterministic control, treat instructions as versioned config, gate tool calls, isolate memory per role/tenant, and run evaluations before production. Build process.
  • Operate with evidence: Keep an agent inventory/identity, centralize logging, track cost and quotas, red team regularly, retire unused agents. Manage agents.

CAF agent decision tree CAF decision tree: SaaS first, then build; validate single vs multi during planning. —

How to prioritize agent use cases Use impact × feasibility × desirability to rank pilots.

Typical agent responsibilities across the organization Platform governs; workloads deliver; AI CoE advises and enforces patterns.

Data architecture for Fabric, OneLake, Foundry, and Azure Anchor grounding in governed data (OneLake/Fabric/Foundry) with clear landing zones.

Sources (CAF):

Technology by User Experience

Where Users Interact Recommended Technologies Use When
Microsoft 365 Apps Free Microsoft 365 Copilot Chat (included) + Graph Connectors for baseline pilots; Microsoft 365 Copilot add-on + declarative agents for work-grounded copilots; Frontier Word/Excel/PowerPoint creation agents (Preview) require admin Frontier opt-in and Anthropic data-sharing consent; mobile parity for custom engine/message-extension agents (iOS/Android)1; Copy to Copilot Studio (rolling out) copies data sources/actions but GPTs/custom actions must be reattached2 Need managed copilots embedded in Word, Excel, Outlook, or Teams with tenant-level governance—start with the free chat surface and graduate to the hero add-on when Graph grounding or in-app assistants are required; use Frontier creation agents only for controlled pilots
Microsoft Teams Only Copilot Studio, M365 Agents SDK Teams-centric chat or calling scenarios where admins may enforce “only during the call” retention
Custom Web/Mobile App Azure AI Foundry, Foundry Agent Service (Standard setup) Building standalone applications while keeping files, search, and thread storage in customer-owned Azure resources
Governance / Registry Agent 365 (Preview); Foundry Control Plane; M365 Agent Registry lifecycle (publish/activate/deploy/pin/block/remove/delete/owner transfer/export)3 Centralize agent identity/registry, conditional access, and security posture across M365/Azure agents
Custom Web/Mobile UI with streaming Microsoft Agent Framework + AG-UI protocol (Preview) Need Server-Sent Events streaming, backend tool rendering, shared state, and human approvals in bespoke front-ends
Multiple Channels M365 Agents SDK Deliver one agent across Microsoft 365 Copilot, Teams, web, email, SMS, and other channels
Power Platform Copilot Studio, AI Builder Integrated with low-code Power Apps/Power Automate workloads
Enterprise Workflows Azure Logic Apps AI Agents (Preview), MCP Server Workflow automation that needs autonomous/conversational agent patterns with Easy Auth guardrails
Data Grounding / RAG Azure AI Search knowledge bases (agentic retrieval, preview); Graph Connectors (M365); Microsoft 365 Copilot Search API (Preview) for OneDrive hybrid semantic+lexical search4 ACL- and label-aware search with reasoning effort/partial responses (Search); tenant-scoped content for M365 copilots (Graph); hybrid OneDrive search for custom engine agents (Search API)
Developer Tools GitHub Copilot Extensions IDE and development workflow integration

Sources:

Confidence Level: High (all technologies GA except Logic Apps AI Agents Preview)

Agentic Retrieval Quick Facts

  • Knowledge agents are now knowledge bases (Preview, 2025-11-01-preview); routes /knowledgebases/*, outputMode + retrievalReasoningEffort (minimal/low/medium) replace fast path.
  • Knowledge sources (Preview): indexed SharePoint, remote SharePoint (Copilot Retrieval API, ACL-trimmed), indexed OneLake, web/Bing, search index, Azure Blob; ingestionParameters wraps embeddings/chat models/Content Understanding; portal creates 2025-08-01-preview objects—migrate for 2025-11-01-preview.
  • Semantic ranker is available on free tier (quota limits); enable on the service before using KBs.
  • Hybrid/vector preview (2024-09-01-preview): MRL truncationDimension, filterOverride for vector-only filters, debug subscores for RRF, token-based Text Split parameters.
  • Content Understanding skill (Preview) replaces Text Split for richer chunking; billed to Foundry resource when used via contentExtractionMode.

Agent Development Approach Comparison

Approach Declarative Agents Custom Engine Agents
Definition Microsoft-managed orchestration where you supply instructions, knowledge, actions Bring your own orchestration, models, and tooling for bespoke agents
Best For Rapid delivery of guided experiences in M365 apps Advanced workflows, multi-agent patterns, or non-M365 channels
Development Model Low-code (Copilot Studio) or pro-code via Agents Toolkit scaffolding Pro-code using Agents SDK, Teams AI Library, or custom frameworks
Orchestration Microsoft 365 Copilot orchestrator handles planning and grounding You decide orchestration (Semantic Kernel, LangChain, Teams AI action planner, etc.)
M365 Integration Native to Microsoft 365 Copilot UI and Teams Requires explicit integration via M365 Agents SDK or Teams AI Library
Typical Timeline Days to a few weeks Weeks to months
Skill Level Makers or full-stack developers Professional developers

Sources:

Confidence Level: High (official Microsoft guidance)

Custom Engine Agent Tool Comparison

Tool Copilot Studio Teams AI Library M365 Agents SDK
Primary Use Case Managed SaaS for custom agents with built-in governance Collaborative agents inside Teams Pro-code agents running across M365 and third-party channels
Orchestration Copilot Studio-managed orchestrator Built-in Teams AI action planner Bring your own orchestration (Semantic Kernel, LangChain, custom)
Supported Channels Microsoft 365 Copilot, Teams, partner apps, mobile apps, custom websites Microsoft 365 Copilot, Teams Microsoft 365 Copilot, Teams, web, email, SMS, Office add-ins, custom sites
Development Experience Low-code UI with Power Platform controls Visual Studio/VS Code libraries for C#, TS/JS, Python Agents Toolkit scaffolding for .NET/JS with multi-channel deployment
Ideal Team Makers or fusion dev teams Teams-focused pro dev squads Professional developers delivering enterprise-scale agents
Status GA GA GA

Sources:

Confidence Level: High (all GA, official Microsoft documentation)

Data Grounding Pattern by Source

Data Source Type Recommended Approach Technologies
SharePoint/OneDrive Graph Connectors Microsoft Graph Connectors SDK, Copilot Studio connectors
External Structured Data Graph Connectors (inside M365) or Azure AI Search (Foundry Agent Service standard setup) Microsoft Graph Connectors, Azure AI Search
Unstructured Documents Vector search with chunking Azure AI Search, Azure OpenAI Embeddings
Real-Time Transactional Data API-based grounding API plugins, Functions, Logic Apps agent workflows
Multimodal Content Azure AI Content Understanding (Preview) Process documents, images, audio, video with reasoning
Database Vectors AI-capable databases with managed embeddings Azure Cosmos DB for NoSQL (standard setup: 3 × 1000 RU containers), PostgreSQL (GA), SQL Server 2025 (Preview)
Microsoft Fabric Platform Direct data access Lakehouse (Delta tables), Warehouse (T-SQL), OneLake (ADLS Gen2 APIs), SQL analytics endpoint
Microsoft Fabric via Agent Conversational data layer Fabric Data Agents (Preview) with Copilot Studio or Foundry Agent Service

Sources:

Confidence Level: High for GA technologies, Medium for Preview (Fabric Data Agents, Content Understanding)

Memory & Analytics by Technology

Common Customer Confusion: Grounding (RAG) ≠ Memory ≠ Analytics

Technology 📋 Grounding (RAG) 💾 Memory / Thread Storage 📊 Analytics / Transcripts Admin Access Retention Control
M365 Copilot ✅ M365 content per request ❌ No tenant-wide memory export; user history lives in mailbox/Graph ⚠️ Copilot activity history, Teams call summaries if policy allows ⚠️ Purview/eDiscovery only ✅ Purview retention policies; Teams calling policy can force “only during the call”
Copilot Studio ✅ M365 data, Dataverse, connectors ⚠️ Dataverse variables per conversation ✅ Session reports, transcript downloads, ROI analytics ✅ Transcript Viewer role required ✅ Toggle Dataverse save, default 30-day retention, bulk delete
Foundry Agent Service ✅ Azure AI Search, Cosmos DB, Fabric, tools ✅ BYO thread storage in Cosmos DB (standard setup) ⚠️ Custom telemetry (App Insights, OpenTelemetry) ✅ Customer RBAC on Azure resources ✅ Customer deletes threads/files in own storage
M365 Agents SDK ✅ Custom (developer implements) ⚠️ Custom (developer implements thread storage) ⚠️ Custom (Application Insights, custom logging) ⚠️ Custom (developer implements) ⚠️ Custom (developer implements)

Key Compliance Questions:

  • Where is conversation history stored? → M365 Copilot (user mailbox/Purview), Copilot Studio (Dataverse), Foundry Agent Service (customer Cosmos DB), SDK (customer datastore)
  • How long is it retained? → M365 Copilot (Purview retention or user deletion), Copilot Studio (policy configurable, 30-day default), Foundry Agent Service (customer-defined lifecycle), SDK (custom)
  • Who can query chat logs? → M365 Copilot (admins via eDiscovery, users see activity history), Copilot Studio (admins with Transcript Viewer role), Foundry Agent Service (Azure RBAC), SDK (custom controls)
  • Can we scrub PII? → Foundry Agent Service (customer deletes in Cosmos/Storage), Studio (bulk delete transcripts), M365 Copilot (user clears activity history, Purview retention)
  • Can we run without saved transcripts? → Teams calling “Only during the call” mode keeps speech-to-text transient; Copilot Studio toggle stops Dataverse saving.

Sources:

Confidence Level: High (all technologies GA)

Orchestration Complexity Decision Matrix

Complexity Level Characteristics Recommended Technologies
Simple (Q&A) Single-turn conversations, basic RAG Declarative Agents (Copilot Studio or M365 Agents Toolkit)
Moderate (Task Execution) Multi-turn, 1-5 actions, simple branching Declarative Agents with API plugins, Foundry Agent Service
Complex (Workflows) Sequential workflows, conditional logic Declarative Agents + Power Automate, Agent Framework workflows
Advanced (Multi-Agent) Agent-to-agent delegation, parallel execution Copilot Studio multi-agent, Foundry Agent Service, Agent Framework
Expert (Custom Reasoning) Custom orchestration logic, model selection Custom engine agents with Microsoft 365 Agents SDK, Teams AI Library, or Foundry Agent Service

Sources:

Confidence Level: High (official patterns documented)

Budget & Timeline Quick Guide

Scenario Fastest Path Most Cost-Effective (Long-Term)
Extend M365 Copilot (Knowledge Only) Graph Connectors (days) Graph Connectors (no additional cost)
Extend M365 Copilot (Knowledge + Actions) Declarative Agent (Copilot Studio, 1-2 weeks) Declarative Agent (M365 Agents Toolkit, 2-4 weeks)
Custom Multi-Channel Agent M365 Agents SDK with templates (2-4 weeks) Azure AI Foundry (consumption-based, 4-8 weeks)
Multi-Agent Orchestration Copilot Studio (low-code, 2-4 weeks) Foundry Agent Service (managed, 4-8 weeks)
Enterprise Workflow Automation Azure Logic Apps AI Agents Preview (1-2 weeks) Azure AI Foundry + Agent Framework (4-8 weeks)

Key Budget Considerations:

  • M365-Centric: Per-user licensing (Copilot Studio, M365 Copilot)
  • Azure-Native: Consumption-based (Azure OpenAI tokens, AI Search queries, compute)
  • Hybrid: Mix of per-user and consumption models

Sources:

Confidence Level: Medium (pricing models subject to change)

Governance Decision Quick Reference

Requirement M365 Trust Boundary Azure Workload Boundary
Data Residency M365 tenant region Azure region selection
Identity Management Entra ID (automatic) Entra ID + Azure RBAC
Approval Workflows M365 admin center (Integrated Apps) Azure custom workflows
Audit Logging Purview + M365 audit logs Azure Monitor + Log Analytics
Data Classification Purview DLP policies Azure Policy + custom tagging
Deployment Control IT admin approval (tenant-wide settings) Azure DevOps, CI/CD pipelines
Real-Time Meeting/Call Transcripts Teams calling policy can enforce “Only during the call” to avoid post-call storage Build ephemeral transcript handling or disable logging in custom stack

Copilot Studio compliance snapshot: Covered under HIPAA BAA, HITRUST CSF, FedRAMP High, SOC, ISO 9001/20000-1/22301/27001/27017/27018/27701, PCI DSS, CSA STAR, UK G-Cloud, OSPAR, K-ISMS, Singapore MTCS Level 3, and Spain ENS High (audit artifacts via the Microsoft Service Trust Portal). (Updated: 2024-12-20)

Best For:

  • M365 Trust Boundary: Organizations with strong Microsoft 365 governance already in place
  • Azure Workload Boundary: Organizations requiring granular control, custom policies, or Azure-native compliance

Sources:

Confidence Level: High (official Microsoft compliance documentation)

Quick Navigation

Next: Resources - Official Microsoft references to keep research evidence-backed

  1. Mobile parity for custom engine agents and message-extension agents on iOS/Android. Source: Microsoft 365 Copilot release notes (November 24, 2025). ↩

  2. Copy to Copilot Studio (rolling out) copies agent data sources and actions; GPTs and custom actions must be reattached. Source: Copy a Copilot agent to Microsoft Copilot Studio (Retrieved: 2025-12-09). ↩

  3. Agent Registry lifecycle actions in M365 admin center: publish, activate, deploy, pin, block, remove, delete, reassign owner, export inventory. Source: Agent Registry documentation (Retrieved: 2025-12-08). ↩

  4. Microsoft 365 Copilot Search API (Preview) for hybrid semantic + lexical search across OneDrive via Graph /beta. Source: Search API overview (Retrieved: 2025-12-09). ↩

Back to top

Copyright © 2025. This documentation is based on official Microsoft sources and best practices.