Graded C+ on resilience. In Vannus's assessment it has not disclosed which model it runs — acceptable, with limits worth knowing.
AWS managed platform for running production AI agents. Published components include Runtime for deploying and running agents, Gateway for tool-call authorisation across MCP servers, knowledge bases, APIs and Lambda functions, Memory, Browser and Code Interpreter tools, Observability for tracing agent decisions, and Evaluations for testing variations against real traffic. Supports LangChain, OpenAI
Not disclosed. Amazon Bedrock AgentCore does not publish which model it runs, so this criterion is excluded and the grade rests on what we could verify. We say so rather than guess.
This is a separate question from the grade above. The grade measures resilience — whether the tool endures and whether you could leave it. This measures who can compel your data. A tool can score modestly on one and strongly on the other, and many do.
The vendor's published or catalog-recorded posture — the concrete facts this grade is built from. A full audit verifies each against the vendor's current documentation.
Vannus grades Amazon Bedrock AgentCore against nine dimensions of trust — data sovereignty, training privacy, compliance posture, operational resilience, exit portability, and more. The heaviest criterion asks whether the tool builds its own AI or resells someone else's model; where the vendor discloses it, the grade cites the vendor's own documentation. No paid placements — scoring is walled off from affiliate revenue. See the methodology →