The Agentic Stack
The building blocks of an agentic AI platform, each mapped three ways: the capability, the popular open-source tools, and the AWS-native service that does the same job. One shared map under everything we build, whether you are building software with agents or shipping an agent to your own customers.
The same building blocks, weighted differently
People mix these up, so we name them. The stack is the same for both. What changes is which parts carry the most weight.
Building with agents
Using agents to build software faster. The org and process side leads here: who owns the platform, and who helps the teams adopt it.
Running agentic systems
The product itself is an agent your customers use. Identity, sandboxing, guardrails, and evals lead here, because the agent is now in front of users.
Capability, open source, AWS-native
AWS-native is our default. Where open source earns its place for portability or control, we say so. The capability is what matters; the tools are just how you get it.
One front door to every model, with routing, fallback, and cost control.
Where agents actually run, with their tools and context around them.
Short and long-term memory, so agents keep context across steps and sessions.
Grounding agents in your own knowledge and documents.
How agents call tools and talk to each other.
Running agent actions and generated code safely, isolated per session.
Weighs heavier when you ship agents to customersGiving agents their own identity and least-privilege access.
Weighs heavier when you ship agents to customersSeeing what agents did, and proving they did it well.
OpenTelemetry-based, so the same traces export to your own tooling too.
Keeping agent output safe, on policy, and free of sensitive data.
Weighs heavier when you ship agents to customersEval and contract gates that stop a bad agent change before it ships.
AgentCore Evaluations scores agent trajectories and outputs; Bedrock Evaluations covers the model and RAG. The managed parts exist; wiring them into a release gate is where most teams still want a hand.
Amazon Bedrock AgentCore has been generally available since October 2025 (Runtime, Memory, Gateway, Identity, Browser, Code Interpreter, and Observability), with Policy and Evaluations reaching GA in March 2026. It is modular and maps almost one to one onto the open-source rows above, which is the whole point of this page: the same capabilities, with a clear AWS-native answer for each.
Where do you sit on this stack?
The map is the easy part. Knowing where you stand, what to build first, and what good looks like for your team is the work we do together.
Agentic SDLC Maturity Workshop
Where your teams stand on building and running agents, the AWS-native target, and the path up the ladder.
Learn more → For exec teamsAI Readiness Workshop
Where the business stands on AI, the use cases worth building, and what to build first.
Learn more →Not sure yet? Take the free 2-minute AI Readiness Check first. Take the check →