Skip to main content

For AWS users

You know AWS. This page translates its vocabulary into Crusoe Agent Platform terms, tells you what will feel familiar, is honest about what AWS has that we don't, and points you at the exact docs pages to migrate each workload.

Terminology map

In AWSHereNotes
AWS account + AWS OrganizationsOrganization + projectsA project is your isolated workspace: its own namespace, quota, members, and audit log.
IAM userUser accountEmail and password. Accounts are created by an admin or an invitation link — ask your administrator; there is no sign-up page. See create an account.
IAM policy JSONProject role: admin or memberThere is no policy language. A member uses a project's resources; an admin can also do the irreversible things. Simpler than IAM, and less expressive — both on purpose.
Access key (AKIA...)API key (cai_<keyid>_<secret>)Shown exactly once at creation, revocable instantly, optional expiry. A personal key acts as you and loses access the moment you do. See API keys.
IAM role for a workloadService accountA machine identity that belongs to one project, GCP-style: name@<project-short>.cai.local. Its keys can never mint more credentials.
CloudTrailPer-project audit logOn by default, readable by every project member, no trail to configure. Honest gap: no export or retention settings yet.
Service QuotasProject quotasA live view of instances, services, CPU, and memory against your project's caps.
Lambda functionFunctionOne file exposing handle(event). Runtimes: Python, Node.js, Go, Ruby.
Lambda handler lambda_handler(event, context)def handle(event) in handler.pyThe event is the parsed JSON request body. Return a dict; include statusCode to set the HTTP status.
API Gateway / Function URLNothing — the URL is includedEvery function and agent gets https://<name>-<project-short>.apps.codyhill.dev. No separate resource to create or pay for.
Lambda cold startScale-to-zero cold startSame physics, documented as an explicit setting rather than folklore. See autoscaling and scale to zero.
App Runner / Fargate serviceServerless serviceOne deploy command; no cluster, task definition, or service triplet. Note: App Runner itself is closed to new AWS customers.
Bedrock Agents / AgentCore RuntimeAgent EngineUpload ADK, LangGraph, or CrewAI code; get a scale-to-zero chat endpoint. There is one agent product here, not a "Classic" and a successor running in parallel.
Bedrock action group (OpenAPI schema + Lambda)A Python function in your agent's tools listNo schema to author, no Lambda to wire. See tools.
AgentCore Memory (short-term)SessionsConversation history, stored by the platform and replayed to the model each turn.
AgentCore Memory (long-term) / Knowledge BaseMemory + VectorDB"Memorize" a session to commit it to a searchable memory bank; agents query it with the built-in search_memory tool.
AgentCore Code InterpreterCode SandboxOne HTTP call, one single-use pod, destroyed after the run. No session lifecycle to manage.
AgentCore GatewayMCP ServersPublish Python tools as a hosted Model Context Protocol endpoint with immutable versions and rollback.
Bedrock GuardrailsNo equivalent yetWe do not have a content-safety layer. We would rather tell you that than stretch a mapping.
SNS topic / SQS queue / EventBridge busPub/Sub topics and subscriptionsOne messaging service covers fan-out and queue-style consumption. AWS ships an official decision guide to pick between its three; here there is nothing to pick.
Step Functions state machine (Amazon States Language)Durable workflowWritten in ordinary code. Branches and loops are language constructs, not JSON states — no ASL casing bugs.
Secrets Manager secretSecretWrite-only key-value pairs injected as environment variables. No rotation Lambda, and honestly: no automatic rotation at all.
ElastiCache / MemoryDBMemoryStoreRedis/Valkey protocol, existing clients work unchanged. One product, not a cache-vs-durable-database pair.
OpenSearch Service vector engine (k-NN)VectorDBA dedicated vector database with collections and points, not a vector field inside a search engine.
CloudWatch LogsAgent logsLive tail plus persisted history that survives scale-to-zero. Default retention is 14 days.
AWS CLIplatformctlOne binary. See install the CLI.

What will feel familiar

  • Scale-to-zero and cold starts. Idle workloads stop; the next request wakes them. Same mental model as Lambda, applied to agents and containers too.
  • The handler contract. handle(event) receiving a dict and returning a dict is a direct cousin of lambda_handler.
  • Bearer credentials for machines. A CI pipeline holds a service-account key the way it would hold an access key — created once, revoked instantly. See the CI/CD tutorial.
  • An audit trail. Every state change lands in the project audit log, the way CloudTrail records management events — except ours needs no setup.

What is different

Simpler here

  • No API Gateway step. Deploying a function is the whole job; the HTTPS URL comes with it.
  • No IAM policy authoring. Nothing on this platform requires writing a policy document before your first call. Two roles cover the access model.
  • One agent product. No Bedrock-Agents-vs-AgentCore research project before you start. One deploy path: deploy an agent.
  • Predictable cost story. AgentCore meters roughly a dozen components separately. This platform has no usage-based metering today — capacity is bounded by visible project quotas. That is an alpha simplification, and we state it as such.

AWS has more

  • Global footprint. Dozens of regions and availability zones, formal SLAs, and compliance programs. We have none of those today.
  • Model catalog. Bedrock's first-party model catalog is large. Agents here use the platform's OpenAI-compatible inference endpoint, configured by your administrator.
  • Event sources. EventBridge integrates SaaS partners and has a content-based rule language. Our functions accept HTTP and CloudEvents; the trigger catalog is much smaller.
  • Long-running compute. Lambda MicroVMs offer hours-long stateful sessions. Our agent invokes default to a 60-second timeout.
  • Secret rotation. Secrets Manager rotates credentials automatically. Here you rotate by writing a new value, which rolls a new revision.
  • Observability. CloudWatch keeps historical metrics; our metrics are live counts only, and logs default to 14-day retention.
  • Identity. MFA, SSO federation, fine-grained policies. Here: email plus password and 12-hour sessions.

Try the Lambda muscle memory

If you can write a Lambda handler, you can deploy a function right now. With the CLI installed and signed in:

mkdir hello-http
cat > hello-http/handler.py <<'EOF'
def handle(event):
return {"echo": event.get("message", "")}
EOF
platformctl functions deploy ./hello-http --name hello-http
platformctl invoke hello-http "ping"

You should see:

{"echo":"ping"}

No execution role, no API Gateway, no test-event JSON to build. Full walkthrough: functions quickstart.

Migration pointers

Moving this from AWSStart here
A Lambda functionFunctions quickstart, then runtimes
A Bedrock agent (or AgentCore app)Agent quickstart, then deploy and tools
A Knowledge Base / RAG pipelineVectorDB quickstart and the RAG chatbot tutorial
SNS/SQS/EventBridge plumbingPub/Sub quickstart, then publish and consume
A Step Functions state machineRun a workflow and the durable agent pipeline tutorial
Secrets Manager secretsManage secrets, then use in workloads
ElastiCache / MemoryDB dataMemoryStore quickstart
IAM users, roles, and CI keysProjects and access and the CI/CD service account tutorial