Feature Comparison

Detailed side-by-side comparisons of Microsoft AI technologies. Use this page after you’ve clarified requirements in the Decision Framework, so the tables confirm trade-offs (rather than driving the decision by brand names alone).

Sanity check before you compare: If the work is deterministic, repeatable, or can be expressed as a clear function/workflow, don’t use an agent. Use a workflow, API integration, or traditional code. Agents are best when the task is ambiguous, multi-step, and conversational, where the steps can’t be fully specified up front.1


Table of contents

  1. Comprehensive Platform Comparison
  2. Developer Agent Comparison
  3. Workflow Orchestration Platform Comparison
  4. When to Use Each Workflow Technology
  5. Agent Governance Layering Guide
  6. IQ Layer Comparison
  7. Lifecycle & Operational Readiness Comparison
  8. Data Grounding Technology Comparison
  9. Local and Edge AI Comparison
  10. Agent Development Approach Comparison
  11. Custom Engine Agent Tool Comparison

Comprehensive Platform Comparison

Quick view of core platforms (M365 Copilot, Studio, Foundry, Agent Framework, Logic Apps) across UX, governance, orchestration, and hosting trade-offs.

How to use this section: Start with the columns that match your trust boundary and channel needs, then compare orchestration and governance features to validate whether you should stay in SaaS, step into low-code, or move to pro-code.

Feature M365 Copilot Copilot Studio Microsoft Foundry (Azure) Microsoft Agent Framework AG-UI Protocol (Preview) Microsoft Foundry Agent Service M365 Agents SDK Azure Logic Apps  
User Experience M365 apps (Frontier creation agents Preview2) + mobile parity for custom engine/message-extension agents3 Custom channels Custom apps Embedded in apps Protocol-based web/mobile UI Custom apps Copilot/Teams/Web Custom/Conversational  
Build Approach No-build (consume) Low-code to pro-code Code-first Pro-code (orchestration SDK) Pro-code protocol integration (ASP.NET Core, FastAPI) Code-first Pro-code Visual designer + code  
Data Boundary M365 tenant M365 or Azure Azure Any Inherits host runtime Azure M365 or Azure Azure  
Governance Tenant-integrated (automatic) + registry lifecycle (publish/activate/deploy/pin/block/remove/delete/owner transfer/export)4 Tenant or workload Workload-tailored (custom) Application-level Inherits host app controls; approvals via middleware Workload-tailored (custom) Tenant or workload Azure RBAC  
Admin Center M365 admin center Power Platform admin Azure RBAC Application-level Host platform (Azure/App) Azure RBAC M365 admin center Azure portal  
Licensing Model Per-user (/month) Metered messages Azure consumption Open-source (free) Open-source adapters (no license) Azure consumption Included in M365 Consumption (agentic workflows explicitly in preview) or Standard (status not stated) 5
Extensibility Via Studio/SDK + Copilot Search API (Preview, OneDrive hybrid search)6 Plugins, connectors Full custom Workflow orchestration Seven protocol features (streaming, backend tool rendering, human approvals, generative UI, shared/predictive state) Full custom Full custom 1,400+ connectors  
Deployment Microsoft-managed Microsoft-managed Self-managed Self-managed (SDK) Self-hosted endpoints (ASP.NET Core, FastAPI) Microsoft-managed Self-managed Self-managed (Azure)  
Time to Value Immediate Days to weeks Weeks to months Weeks (with dev skills) Weeks (requires pro dev + UI build) Weeks to months Weeks Days to weeks  
Skill Level End user Maker to developer Developer/engineer Developer (C#/Python) Developers (front-end + back-end) Developer/engineer Developer Developer  
Orchestration Built-in Built-in Custom Workflow-based (Executor/Edge) Inherits Agent Framework orchestration Managed orchestration BYO orchestrator Visual workflow  
Checkpointing N/A No Custom Yes (built-in) Inherits from orchestrator No Via orchestrator State management  
AI Agent Workflows N/A Via agent flows Via Microsoft Foundry Agent Service7 N/A N/A (UI protocol) ✅ Yes N/A ✅ Yes: “agentic workflows” with an “agent loop”8  
MCP Server N/A ✅ Yes (Preview) ✅ Yes (MCP tool)9 Consumer (GA) N/A ⚠️ Custom N/A ✅ Yes (Preview)10  
Optimized For Productivity at scale Speed to market + connectors Latency & control Workflow orchestration Bespoke agent UI with streaming & approvals Managed agents Pro-code flexibility Enterprise integration  
Latency Profile <1s (M365 apps) <1s (managed platform) <100ms (direct API) Workflow processing SSE streaming (depends on backend) <100ms (direct API) <1s (M365 integration) Workflow processing  
Infrastructure Model Microsoft-managed SaaS (managed) PaaS (self-managed) SDK (self-managed) SDK bridging host + client PaaS (self-managed) SDK (self-managed) PaaS (self-managed)  
Best For Broad productivity Custom agents Custom AI apps Workflow orchestration Custom branded experiences and generative UI atop Agent Framework Managed agents Pro-code extensions Enterprise integration + AI  

Developer Agent Comparison

The comparison below covers four developer-agent roles: asynchronous repository work, parallel development-session coordination, Azure reliability operations, and supported application-stack modernization. GitHub Copilot cloud agent is the remote worker, GitHub Copilot app is the dispatch desk, Azure SRE Agent is the reliability engineer, and GitHub Copilot Modernization is the renovation crew. Their capabilities overlap; their primary jobs differ.

Feature GitHub Copilot cloud agent GitHub Copilot app Azure SRE Agent GitHub Copilot Modernization
Primary Role Asynchronous repository research, planning, code changes, and pull requests in a GitHub Actions-powered environment Desktop control surface for parallel agent-driven development and GitHub pull-request lifecycle management Azure operational investigation, diagnosis, and approved remediation Modernization solution delivered through complementary IDE extensions and the Modernize CLI, not a standalone agent product
Execution Surface GitHub-hosted session working on one branch and up to one pull request per assigned task Local repository, dedicated worktree, or GitHub-hosted cloud sandbox (Public Preview) Configured Azure resources, telemetry, connectors, and operational controls IDE extensions for developer execution; Modernize CLI for portfolio assessment, planning, and orchestration
Planning and Autonomy Can research a repository, create a plan, change code, and optionally open a pull request GitHub Copilot app session modes: Interactive, Plan, and Autopilot; model and reasoning-effort selection per session11 Investigation and action scope follow configured permissions and approvals Assessment and modernization plans guide transformations; developers choose and review the work to execute
Parallelism and Isolation Separate cloud-agent sessions; each task remains branch-scoped Multiple isolated sessions in parallel, each with its own branch/worktree; cloud sandbox isolation is Public Preview Multiple investigations can run within configured service and quota boundaries Modernize CLI can coordinate assessment and planning across multiple applications; IDE work remains project/repository scoped
GitHub Workflow Tasks can begin from issues or Copilot prompts; work is visible through commits, logs, and pull requests Browse issues/PRs, start sessions with issue context, review diffs and CI, comment or request fixes, and use Agent Merge when GitHub rules allow Use governed issues or incident records as the handoff to coding workflows; no direct SRE-to-coding-agent protocol is assumed Produces reviewed code and deployment changes that should flow through normal branches, builds, tests, scans, and pull requests
Steering and Review Developers manage sessions and decide whether to create or merge the pull request Steer and archive sessions, switch modes/models, review diffs/comments, inspect CI, and use canvases where the workflow benefits from a shared custom surface Human approval gates remain required for consequential actions Human review remains mandatory; successful transformation does not guarantee application correctness, security, or production readiness
Modernization Scope General-purpose repository work; no modernization-specific guarantee General-purpose session and PR management Operations, not application framework modernization Java, .NET, and C++ language/framework/tool upgrades; supported .NET/Java Azure migration; dependency/runtime upgrades, OpenRewrite transformations, build/test validation, CVE remediation, containerization, IaC, and deployment assets
Feature-Level Status GA on all paid Copilot plans, including Student (not available on Copilot Free); related capabilities carry their own availability labels App is GA on all Copilot plans (macOS, Linux, Windows); cloud sandboxes Public Preview No preview banner; production billing documented in AAU (4 AAU per agent-hour plus variable). Microsoft does not publish an explicit GA statement IDE language/framework/tool upgrades GA for .NET, Java, and C++; IDE Azure migration GA for .NET and Java; Modernization agent CLI Public Preview

Where the Copilot SDK fits: none of the four columns above is the embedding story. The GitHub Copilot SDK is GA across Python, TypeScript, Go, .NET, Java, and Rust, and it wraps the Copilot CLI engine over JSON-RPC so you can put agent behavior inside your own product. Microsoft Foundry lists it as a framework you can bring to a Hosted agent, but Foundry Hosted agents support Python and C# only, so a Go, Rust, or Java Copilot SDK agent needs its own hosting (Azure Container Apps, AKS, or your runtime) and integrates via the Responses API. Pick the SDK language with the hosting endgame in mind.12

Sources: GitHub Copilot cloud agent; GitHub Copilot app; agent sessions; issues and pull requests; Azure SRE Agent; GitHub Copilot Modernization (updated June 12, 2026).


Workflow Orchestration Platform Comparison

Agentic workflows automate business processes and orchestrate AI agents through deterministic sequences with AI integration. Microsoft provides three primary technologies for different development approaches and team skills.

Use this matrix to choose between Agent Framework Workflows, Logic Apps Agentic Workflows, and Copilot Studio agent flows based on skills, hosting, connectors, and checkpointing needs.

Technology Options

Feature Agent Framework Workflows Logic Apps Agentic Workflows Copilot Studio Agent Flows
Approach Pro-code (C#, Python) Visual designer + code Low-code (natural language/visual)
Architecture Graph-based (Executors + Edges) Workflow designer + connectors Workflow designer + connectors
Checkpointing ✅ Yes (built-in) ✅ Yes (state management) ❌ No
Type Safety ✅ Yes (compile-time) ⚠️ Partial (schema validation) ⚠️ Partial (schema validation)
AI Integration Native (\IChatClient) Azure OpenAI, Microsoft Foundry (Azure), Microsoft Foundry Agent Service Azure OpenAI, Microsoft Foundry (Azure), Microsoft Foundry Agent Service
Connectors Custom code (any API) 1,400+ connectors + custom code 1,000+ (Power Platform)
Hosting Self-managed (Azure) Azure Portal Microsoft SaaS (managed)
Licensing Open-source (free SDK) Azure consumption/Standard Copilot Studio Credits
DevOps ✅ Yes (code-based CI/CD) ✅ Yes (GitHub Actions, Azure DevOps) ✅ Yes (Pipelines, GitHub Actions, Azure DevOps)
MCP Server ⚠️ Custom ✅ Yes (Preview) ✅ Yes (Preview)
Status GA Consumption agentic workflows explicitly in preview; Standard carries no preview banner on the agent loop, but Microsoft never states Standard is GA and some Standard capabilities are marked preview8 GA
Best For Multi-agent orchestration + checkpointing Enterprise integration + AI agents Fast automation within Studio agents

Sources:

Last Updated: 2026-03-25 Confidence Level: High (official Microsoft documentation for all three technologies)


When to Use Each Workflow Technology

Agent Framework Workflows

Use When:

  • Type-safe workflow orchestration with compile-time validation is required
  • Checkpointing needed for long-running or human-in-the-loop processes
  • Multi-agent patterns required (Sequential, Concurrent, Handoff, Magentic)
  • Pro-code development team (C#, Python) available
  • Integrating with M365 Agents SDK

Don’t Use When:

  • Low-code approach preferred
  • Need 1,000+ pre-built connectors
  • Fast time-to-market is critical priority
  • No development team available

Sources:


Logic Apps Agentic Workflows

Use When:

  • Enterprise integration with 1,400+ connectors (cloud + on-premises) required
  • Visual designer + code hybrid approach fits team skills
  • Azure-native hosting with DevOps deployments needed
  • MCP server capabilities required (expose workflows as AI tools)
  • Autonomous or conversational agent workflows with Azure OpenAI

Don’t Use When:

  • Purely low-code approach needed (use Copilot Studio instead)
  • Budget constraints prohibit Azure consumption costs
  • M365-only governance required
  • Compile-time type safety is critical (use Agent Framework instead)

Sources:


Copilot Studio Agent Flows

Use When:

  • Native automation within Copilot Studio agents needed (no separate license)
  • Fastest time-to-value with low-code/natural language approach required
  • Managed SaaS preferred (no infrastructure management)
  • Business process automation for Studio agents
  • Makers without coding skills available

Don’t Use When:

  • Checkpointing or state persistence required for long workflows
  • Complex multi-agent orchestration needed
  • Full DevOps control and Azure-native hosting required
  • MCP server capabilities needed

Sources:


Agent Governance Layering Guide

Agent governance requires several complementary layers: runtime policy enforcement, fleet and lifecycle administration, platform guardrails, and behavioral evaluation. The guide below maps each layer to its responsibility and product anchors. It is a framework-authored composition model; Microsoft does not publish it as an official product comparison.

Layer Role Product Anchor Status / Scope Configuration Caveat
Runtime checkpoint Intercept agent actions and enforce application policy Agent Governance Toolkit (Microsoft-origin, MIT OSS) Public Preview v4.1.0; zero GA features; ACS policy layer beta Self-hosted middleware; pin versions; APIs and schemas can change; no managed-service SLA or Microsoft product support contract
Fleet and lifecycle Inventory, identity, access, and administrative posture Agent 365 (GA 2026-05-01), Agent Registry, Microsoft Entra Agent ID (generally available), or Foundry control surfaces Agent 365 GA; Agent 365 SDK and CLI Preview; Shadow AI Preview. Registry Sync coverage beyond Microsoft surfaces is not documented. Do not assume AWS or Google Cloud discovery Registration does not automatically intercept every in-process tool call
Platform guardrails Apply identity, network, data, and service policies Hosting and cloud platform controls Status varies by control Coverage follows the configured service boundary, not arbitrary application code
Behavioral evaluation Test whether an agent follows policy and fails safely ASSERT and platform evaluation tools Project/service status varies Tests provide evidence; they do not enforce runtime decisions

Authorship and method: This framework authored the layering model from official product scopes and the AGT repository/release record. It compares architectural responsibility, enforcement point, operational owner, and lifecycle, not feature counts. See the Microsoft announcement, AGT repository, and v4.1.0 changelog.


IQ Layer Comparison

Four intelligence layers – collectively branded Microsoft IQ – give agents access to different slices of your world. Think of them as The Four Libraries: one holds your enterprise documents, one remembers every meeting and email, one crunches your business metrics, and one reads every public source on the internet. No single librarian covers all four, but together they give an agent near-total recall.

Feature Foundry IQ Work IQ Web IQ Fabric IQ
Domain Enterprise knowledge (files, blobs, indexes, web) M365 organizational context + extensible business systems (the intelligence layer that powers Copilot) Public web and fresh external signals Business analytics (semantic models, ontologies, OneLake)
Status Partial GA (agentic retrieval GA via the 2026-04-01 REST API; portal experiences, answer synthesis, and multi-turn remain Preview) APIs GA (2026-06-16): Chat, Context, Tools, Workspaces. ⚠️ Work IQ MCP is Preview; do not conflate the two Limited Access (enrollment required) Preview (documented Fabric workload at /fabric/iq/*)
Data Boundary Azure M365 tenant Limited Access web grounding service Fabric capacity
Access Method MCP endpoint (agentic retrieval via knowledge bases) Built-in MCP servers (Copilot, Calendar, Mail, SharePoint, OneDrive, Teams, User, Word, Dataverse/Dynamics 365) + custom MCP servers via MCP Management Server (1,500+ connectors, Graph APIs, REST) Agent-native web grounding APIs Fabric Data Agents, SQL endpoint
Permission Model ACL sync + Purview labels + Entra identity at query time Entra delegated auth only; app-only is not supported; admin allow/block. API access is independent of Microsoft 365 Copilot licensing Limited Access terms and web-source policies Fabric RBAC + OneLake ACLs
Knowledge Sources Azure Blob, SharePoint (indexed + remote), OneLake, existing indexes, web (Bing) M365 Graph signals (files, emails, meetings, chats, calendar, people); Workspaces use SharePoint Embedded storage Web pages, news, public information sources Lakehouse, warehouse, KQL, semantic models, ontologies and graph models
Consumers Foundry Agent Service, custom agents via MCP Copilot Studio, Microsoft Foundry, VS Code, CLI Limited Access agent scenarios Copilot Studio, M365 Copilot, Power BI
Best For Custom agents with governed enterprise data + citation-backed responses Agents that need organizational context: not just file contents, but who decided what, when, and what happened after Agents needing current public information (news, research, regulations) Chat-with-data and analytics scenarios
Licensing Azure consumption Billed in Copilot Credits; API access is independent of Microsoft 365 Copilot licensing Limited Access enrollment Fabric capacity (F2+)

Sources:


Lifecycle & Operational Readiness Comparison

Before selecting a platform, check the expiration date. This matrix flags active migration deadlines and governance readiness.

Dimension M365 Copilot Copilot Studio Microsoft Foundry Agent Framework GitHub Copilot
Platform Status GA GA GA GA (.NET, Python) GA (various features Preview)
Active Deprecations None None Foundry Workflows: Retiring from Preview without a GA path on December 1, 2026; Assistants API (Aug 26, 2026, date unconfirmed, verify before planning); azure-ai-agents deprecated Breaking changes tracked in upgrade guides GitHub App-based Copilot Extensions deprecated 2025-11-10 (migrate to MCP servers); model LTS policies active
Publish to M365 Copilot Native Native Early Access Preview; validate each tool and identity path Via M365 Agents SDK N/A
Multi-Agent Orchestration Via Researcher agent (GA) + connected agents Agent-to-agent (A2A) GA (April 2026); “Connect other agents” shows Preview; Microsoft states no blanket GA for connected, child (inline), Foundry, Fabric data, or M365 Agents SDK agents inside Studio Incoming A2A endpoint (Preview); use Agent Framework for code-first orchestration Custom workflow graphs; built-in Sequential, Concurrent, Handoff, Group Chat, and Magentic-One patterns N/A
MCP Compatibility N/A Consumer (GA) Consumer + Producer (MCP tool GA) Consumer (GA) Consumer (MCP servers in VS Code); enterprise MCP policy is disabled by default and applies to Business/Enterprise only
Permission-Aware Grounding Graph security trimming (automatic) Via connectors + Work IQ (APIs GA; Work IQ MCP Preview) Foundry IQ ACL/label sync; SharePoint ACL flow-through in AI Search Inherits from host runtime Repository-scoped
Built-in Evaluation N/A Test sets + analytics Foundry portal evals + continuous evaluation OpenTelemetry hooks N/A
Governance Export Agent Registry (export inventory) Power Platform admin + Purview audit Foundry Control Plane + Azure Policy + Defender Application-level Org admin telemetry
Observability M365 admin center Purview audit + Application Insights Application Insights agent details view OpenTelemetry (ENABLE_OTEL) Usage metrics + plan mode
Identity Model (attribution) User-scoped (always) Entra agent identity created automatically per new agent; pre-rollout agents remain on app registrations pending migration Shared project identity; dedicated identity at publish Application-defined GitHub identity
Data Access Model (authorization) Invoking user’s permissions Set per tool: delegated to the invoking user by default, maker’s credentials as an override, and maker-only on event triggers App-only against the agent’s own RBAC by default; OBO available Application-defined Repository-scoped

Data Grounding Technology Comparison

Side-by-side grounding options (Copilot connectors, AI Search, Fabric, Cosmos, PostgreSQL, SQL Database Engine family) by search mode, boundary, and best-fit workloads.

Feature Copilot connectors Azure AI Search Microsoft Fabric Cosmos DB PostgreSQL SQL Database Engine (Azure SQL DB, SQL MI, SQL Server 2025, SQL database in Fabric)
Vector Search No (semantic index only) ✅ Yes (IVF, HNSW) ✅ Yes (Lakehouse via external tools) ✅ Yes (flat/kNN, quantized flat, DiskANN) ✅ Yes (pgvector, IVF) ✅ Yes (vector type + VECTOR_DISTANCE(); VECTOR_SEARCH() Preview)
Hybrid Search No ✅ Yes (vector + keyword) ✅ Yes (SQL endpoint + external) ✅ Yes ✅ Yes ✅ Yes
Data Boundary M365 tenant Azure Azure (OneLake) Azure Azure Azure SQL DB & SQL MI: Azure. SQL Server 2025: On-prem or Azure VM. SQL database in Fabric: Fabric.
Index Target Microsoft Graph (connector ingestion) Azure AI Search index / knowledge bases (agentic retrieval GA via the 2026-04-01 REST API; portal preview-only) Lakehouse Delta tables, Warehouse tables Cosmos DB collection PostgreSQL table SQL table (VECTOR column)
Access Method Graph API (Copilot connector APIs) REST API, SDKs (2025-11-01-preview for knowledge bases) ADLS Gen2 APIs, SQL endpoint, Fabric Data Agents SDKs, REST API SQL, pgvector T-SQL, VECTOR type, VECTOR_DISTANCE, VECTOR_SEARCH
Best For M365-centric knowledge (Copilot, Search, Context IQ) Azure-native RAG with ACL/label enforcement and agentic retrieval Analytics data + unified data platform Transactional + vector data PostgreSQL workloads with AI SQL workloads with AI. Choose deployment by existing estate (cloud PaaS, lift-and-shift, on-prem, Fabric)
Licensing Included with M365 Azure consumption: dedicated tiers, plus a serverless consumption tier (Public Preview, pay-per-use, scale-to-zero); agentic retrieval available on free tier quotas Fabric capacity (F2+) Azure consumption Azure consumption Azure SQL DB/MI: Azure consumption. SQL Server 2025: SQL license. SQL in Fabric: Fabric capacity.
Status GA GA (dedicated tiers); Serverless tier Preview; agentic retrieval GA via the 2026-04-01 REST API, portal preview-only GA (Platform); Fabric data agent GA; Fabric IQ Preview Vector search available (flat, quantized flat, DiskANN); Microsoft does not state a GA date pgvector GA vector type and VECTOR_DISTANCE() available; VECTOR_SEARCH() is Preview on Azure SQL Database, SQL database in Fabric, and SQL Server 2025

Fabric app-backend note: Rayfin is not a grounding store. It is a Preview SDK and CLI for defining and deploying managed application backends on Microsoft Fabric, so app data lands in OneLake and inherits Fabric governance. Use it when the question is “Where should this AI-enabled app backend live?” rather than “Which retrieval engine should ground this answer?”

Sources:

Confidence Level: High for GA capabilities (Fabric data agent, pgvector, Azure Managed Redis); Medium for Preview capabilities (VECTOR_SEARCH, Fabric IQ, AI Search Serverless) and for Cosmos DB vector search, where Microsoft states no GA date


Azure AI Search Agentic & Hybrid Preview Highlights

Feature Status Notes API Version Documentation
Agentic retrieval (REST) GA Agentic retrieval is generally available through the 2026-04-01 REST API. Portal experiences remain preview-only. 2026-04-01 Agentic retrieval concepts
Knowledge bases (renamed from knowledge agents) Preview Routes /knowledgebases/*, outputMode replaces outputConfiguration, retrievalReasoningEffort (minimal/low/medium) replaces fast path; partial responses supported. 2025-11-01-preview Agentic retrieval migration
Knowledge sources Preview Indexed/remote SharePoint, indexed OneLake, web/Bing, search index, Azure Blob; ingestionParameters wrap embeddings/chat models, schedules, contentExtractionMode (Content Understanding). Portal uses 2025-08-01-preview objects. Migrate to 2025-11-01-preview. 2025-11-01-preview Knowledge sources
Content Understanding skill Preview Rich Markdown/table extraction and chunking without Text Split; billed to Foundry resource. 2025-05-01-preview Content Understanding skill
Semantic ranker on free tier GA Semantic reranking available on free tier with volume limits. n/a Semantic ranker
Hybrid/vector debug & control Preview truncationDimension for MRL embeddings, filterOverride for vector-only filters in hybrid queries, debug subscores for RRF, token-based Text Split parameters. 2024-09-01-preview Hybrid search preview

Last Updated: January 28, 2026


Local and Edge AI Comparison

Not every model belongs in the cloud. This compact matrix helps you decide where inference should run – the datacenter, the device, or somewhere in between.

Feature Foundry Local Windows AI APIs Windows ML (ONNX)
What It Does Runs Foundry-catalog SLMs locally with cloud-parity API Pre-built on-device intelligence (text, image, speech) Custom ONNX model execution on DirectML hardware
Status Verify current scope on Learn GA (Windows 11) GA
Platforms Windows 11, macOS, Azure Local Windows 11 (Copilot+ PCs preferred) Windows 10/11
Hardware CPU/GPU (device-class) NPU, GPU, CPU (auto-selected) DirectML (GPU/NPU)
Model Source Foundry catalog subset (Phi, Mistral, others) System-provided models Bring your own ONNX model
Offline Capable Yes (after model download) Yes (built-in) Yes
Best For Hybrid cloud/edge agents, air-gapped environments, dev inner loop Client-side features (captions, OCR, summarization) in Windows apps Specialized vision, NLP, or sensor models in Windows apps
Cloud Fallback Yes (same API targets Foundry cloud) No (device-only) No (device-only)

The trade-off: Foundry Local gives you cloud portability at the cost of a narrower model catalog. Windows AI APIs give you zero-setup device intelligence but no custom model support. Windows ML gives you full model control but requires ONNX conversion and DirectML expertise. Choose based on whether you need portability, simplicity, or specialization.


Agent Development Approach Comparison

Declarative vs custom engine: when to stay with managed orchestration versus bringing your own orchestrator and hosting.

Approach Declarative Agents Custom Engine Agents
Definition Pre-built orchestration; configure instructions, knowledge, actions Bring your own orchestrator (Agent Framework recommended, LangChain (Third-party))
Best For Simple → Moderate complexity; fast time-to-market Complex workflows; multi-agent systems; custom reasoning
Development Model Low-code (Copilot Studio) or Pro-code (M365 Agents Toolkit) Pro-code only; full control over logic
Orchestration Microsoft-managed orchestration (GPT-based) You control orchestration framework and model selection
M365 Integration Native M365 Copilot integration Can integrate via M365 Agents SDK
Typical Timeline Days to weeks Weeks to months
Skill Level Makers (low-code) or Developers (pro-code) Developers required

Sources:

Confidence Level: High (official Microsoft guidance)


Custom Engine Agent Tool Comparison

Tooling snapshot for custom engine agents across Copilot Studio, Teams SDK, and M365 Agents SDK (channels, orchestration fit, developer experience). Microsoft guidance positions Teams SDK and M365 Agents SDK as coexisting options with different optimization targets, not a strict replacement path.

Tool Copilot Studio Teams SDK M365 Agents SDK
Primary Use Case Low-code custom engine agents Teams-first collaborative agents (channels/meetings), including Bot Framework migration Multi-channel pro-code agents with bring-your-own orchestration
Orchestration Options Copilot Studio orchestration (topics and generative orchestration on the standard harness, or the enhanced orchestration runtime on the GitHub Copilot harness), plus Agent Flows and connected agents for cross-agent patterns Teams SDK (Action Planner) Bring your own orchestration (Agent Framework recommended, LangChain (Third-party), custom planners)
Deployment Channels Microsoft 365 Copilot, Teams, SharePoint, custom websites, and mobile endpoints Microsoft 365 Copilot + Teams, optimized for collaborative Teams surfaces 10+ channels (Teams, Slack, web chat, etc.)
Developer Experience Visual designer + code Code-first Code-first with Toolkit in VS Code
Target Audience Makers and developers Teams app/agent developers Professional developers and ISVs
Licensing Model Per-user subscription or consumption (prepaid/Pay-as-you-go) Included with M365 Included with Azure Bot Service
Status GA GA GA

Publishing scope: Only agents built with the Teams SDK, M365 Agents SDK, or Foundry can be published to the Microsoft Commercial Store via Agents Toolkit; Copilot Studio agents are org-only by default. Source: Custom engine agents for Microsoft 365 overview.

Coexistence guidance:

  • Use Teams SDK when the primary experience is collaborative and Teams-centric (channels, meetings, team conversations).
  • Use M365 Agents SDK when you need broader cross-channel distribution and full control over orchestration/model stack.

Capability maturity in Copilot Studio and adjacent SDKs can shift month-to-month. Validate GA/Preview status per feature in the Copilot Studio “What’s new” feed before production commitments.

Sources:

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


Related Pages


Next: Quick Reference - Fast lookup tables to accompany the matrices


  1. Agent Framework guidance on when not to use an agent (prefer deterministic functions/workflows). Source: Microsoft Agent Framework overview

  2. Frontier Word/Excel/PowerPoint creation agents (Preview) require admin Frontier opt-in (Frontier is the early access program for experimental/preview Copilot features), Anthropic provider connection, and acceptance of Anthropic commercial terms; data is processed outside Microsoft-managed environments. Sources: Word/Excel/PowerPoint Agents, Microsoft 365 Copilot admin user access

  3. Microsoft 365 Copilot release notes (Nov 25, 2025): mobile support for custom engine agents and message-extension agents on iOS/Android. Source: Microsoft 365 Copilot release notes - Nov 25, 2025 (Retrieved: 2025-01-27). 

  4. Agent Registry lifecycle actions (publish, activate, deploy, pin, block, remove, delete, reassign owner, export inventory). Source: Agent Registry in the Microsoft 365 admin center (Retrieved: 2026-01-23). 

  5. Two prepurchase plans, not one. Microsoft sells two distinct Azure reservation products, both 1-year term with auto-renew on by default and all purchases final. The Copilot Credit Pre-Purchase Plan buys CCCUs against eligible Copilot Credit usage. The Microsoft Agent Prepurchase Plan buys ACUs against “select services across Microsoft Foundry, Microsoft Copilot Studio*, Microsoft Fabric, and GitHub costs” (* = Copilot Studio, Dynamics 365 first-party agents, and Copilot). 1 ACU pays down US$1 of qualifying retail cost, purchased at a tiered discount. Discount precedence is verbatim: “Reservations always apply before prepurchase plans” → Microsoft Foundry PTU Reservations → Microsoft Fabric Capacity Reservations → Copilot Credit Prepurchase Plan → Microsoft Agent Prepurchase Plan. Coverage of Copilot Cowork or Work IQ is not stated by Microsoft. Do not assume it. Sources: Copilot Credit Pre-Purchase Plan, Microsoft Agent Prepurchase Plan (Verified: 2026-07-29). 

  6. Overview of the Microsoft 365 Copilot Search API (Preview) for hybrid semantic + lexical search across OneDrive via Graph /beta. Source: Microsoft 365 Copilot Search API overview (Retrieved: 2025-10-20). 

  7. What is Microsoft Foundry Agent Service?, Microsoft Learn. GA update includes Azure Logic Apps triggers for agents. Source: Foundry Agent Service overview (Retrieved: 2026-03-25). 

  8. Microsoft’s official term is “agentic workflows”, built around an “agent loop.” Status splits by hosting model: Consumption agentic workflows are explicitly in preview: verbatim, “Consumption agentic workflows capability is in preview and is subject to the Supplemental Terms of Use for Microsoft Azure Previews.” Standard carries no preview banner on the agent loop itself, but Microsoft never states that Standard is GA, and specific Standard capabilities (for example, “with an LLM API”) are marked preview. Check the exact capability you intend to ship. Source: Logic Apps agentic workflow concepts (Verified: 2026-07-29).  2

  9. What is Microsoft Foundry Agent Service?, Microsoft Learn. MCP tool available as built-in agent tool. Source: Foundry Agent Service overview (Retrieved: 2026-03-25). 

  10. Set up Standard logic apps as remote MCP servers (Preview), Microsoft Learn. Source: Set up Standard logic apps as remote MCP servers (Retrieved: 2025-11-18). 

  11. These are session modes inside the GitHub Copilot desktop app, a GitHub product surface. They are unrelated to the Microsoft 365 marketing term “Autopilots” (which has no Microsoft Learn definition) and unrelated to Windows Autopilot, the Windows device provisioning service. Source: GitHub Copilot app

  12. GitHub Copilot SDK is GA with Python, TypeScript, Go, .NET, Java, and Rust bindings, supports BYOK to OpenAI, Microsoft Foundry, and Anthropic, and works with Entra/managed identity via bearerTokenProvider composition with the Azure Identity SDK. The Microsoft Foundry Agent Service overview lists the GitHub Copilot SDK among hosted-agent frameworks, while the hosted agents concept page states verbatim: “Hosted agents support Python and C#.” Sources: Copilot SDK getting started, Foundry Agent Service overview, Foundry hosted agents (Verified: 2026-07-29). 


Back to top

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

This site uses Just the Docs, a documentation theme for Jekyll.