AI agents
Amazon Bedrock AgentCore vs Foundry Agent Service
The Azure equivalent of Amazon Bedrock AgentCore is Foundry Agent Service.
Both host declarative or code-based agents from any framework and model.
Side-by-side comparison
| Aspect | Amazon Web Services | Microsoft Azure |
|---|---|---|
| Service | Amazon Bedrock AgentCore | Foundry Agent Service |
| Lifecycle | Generally available | Voice-based agents and some monitoring/eval/telephony capabilities are in preview. |
| What it is | Modular agent platform. Harness (managed agent loop), Runtime, Memory, Gateway (MCP), Identity, Code Interpreter, Browser, Observability, Evaluations, Optimization, Policy, Registry, Payments. Works with any framework and any model. | Managed agent platform. Prompt agents (declarative), voice-based prompt agents (Voice Live), and hosted agents (your container or zip, any framework), plus the Responses API for "ephemeral" agents. Shared toolbox via a managed MCP endpoint. |
| Pricing model | Consumption-based per AgentCore component (for example Runtime compute while active, Gateway calls, Memory events/records, Browser and Code Interpreter sessions), plus model tokens. No upfront commitment. | Prompt agents are billed per call for inference plus tool usage. Hosted agents add container compute, and voice agents add Voice Live usage. |
| Docs | Amazon Bedrock AgentCore docs | Foundry Agent Service docs |
| Pricing page | Amazon Bedrock AgentCore pricing | Foundry Agent Service pricing |
| Exams | Generative AI Developer – Professional AIF-C01 | AI-103 AI-500 |
Key differences
- Shape. AgentCore is a set of modular services you can use independently: Harness (config-defined managed agent loop in an isolated microVM), Runtime (serverless hosting for code agents), Memory, Gateway, Identity, Code Interpreter, Browser, Observability, Evaluations, Optimization, Policy, Registry, and Payments.
- Foundry Agent Service has three agent types. Prompt agents are declarative. Voice-based prompt agents run on Voice Live (preview). Hosted agents run your container or zip. You can also call the Responses API for "ephemeral" agents you define in code.
- Frameworks. AgentCore Runtime lists Strands, LangGraph, CrewAI, LlamaIndex, Google ADK, and OpenAI Agents SDK. Foundry hosted agents list Microsoft Agent Framework, LangGraph, OpenAI Agents SDK, Anthropic Agent SDK, and GitHub Copilot SDK.
- Models. AgentCore works with models in or outside Bedrock (OpenAI, Gemini, and others). Foundry agents use Foundry catalog models.
- Distribution. Foundry agents can be published to Microsoft Teams, Microsoft Copilot, and the Entra Agent Registry. AgentCore has its own Registry for agents, MCP servers, and skills.
- Only AgentCore offers Payments (x402 and Machine Payments Protocol microtransactions).
Pricing summary
Pricing models only. No prices are quoted because they change by region and over time.
- AWS
- Consumption-based per AgentCore component (for example Runtime compute while active, Gateway calls, Memory events/records, Browser and Code Interpreter sessions), plus model tokens. No upfront commitment. Amazon Bedrock AgentCore pricing →
- Azure
- Prompt agents are billed per call for inference plus tool usage. Hosted agents add container compute, and voice agents add Voice Live usage. Foundry Agent Service pricing →
Certification exam mapping
| Exam | Provider | Level | Status |
|---|---|---|---|
| AWS Certified Generative AI Developer – Professional | AWS | Professional | current Exam code not confirmed from the official page at build time; shown by name only. |
| AWS Certified AI Practitioner AIF-C01 | AWS | Foundational | current Italian and German versions retire after Oct 15, 2026 (per AWS cert page). |
| Microsoft Certified – Azure AI Apps and Agents Developer Associate AI-103 | Azure | Associate | current Generative AI and agentic solutions with Microsoft Foundry using Python. Successor in scope to the retired AI-102. |
| Microsoft Certified – Multi-Agent AI Solutions Expert AI-500 | Azure | Expert | current |
Relevance is based on each exam's published scope, not a line-by-line objective match. Check the official study guide.
FAQ
What is the Azure equivalent of Amazon Bedrock AgentCore?
The Azure equivalent of Amazon Bedrock AgentCore is Foundry Agent Service. Both host declarative or code-based agents from any framework and model.
How does pricing compare between Amazon Bedrock AgentCore and Foundry Agent Service?
AWS: Consumption-based per AgentCore component (for example Runtime compute while active, Gateway calls, Memory events/records, Browser and Code Interpreter sessions), plus model tokens. No upfront commitment. Azure: Prompt agents are billed per call for inference plus tool usage. Hosted agents add container compute, and voice agents add Voice Live usage. Check the official pricing pages for current rates.
Which certification exams cover this topic?
AWS Certified Generative AI Developer – Professional; AWS Certified AI Practitioner (AIF-C01); Microsoft Certified – Azure AI Apps and Agents Developer Associate (AI-103); Microsoft Certified – Multi-Agent AI Solutions Expert (AI-500).
Should I use Bedrock Agents or AgentCore?
New customers should use AgentCore. Bedrock Agents was renamed Agents Classic and stopped accepting new customers on July 30, 2026.
What is the Azure equivalent of AgentCore Runtime?
Foundry Agent Service hosted agents. You bring code in any supported framework, and Foundry runs it with a managed endpoint, scaling, and a dedicated Entra identity.