From Workflows to Agents

From Workflows to Agents

A prescriptive, one-path course for people who already build with visual automation tools. You will understand models, prompts, and agents; call a model through Amazon Bedrock; build a small Strands agent with a tool, an MCP connection, and memory; define its infrastructure with AWS CDK; deploy it to Bedrock AgentCore Runtime; and verify, estimate cost, and clean up.

  1. 00Setup and safetyInstall the tools this course uses and set guardrails before touching AWS.
  2. 01An AI mental model for automation buildersLearn the core language model terms and decide which workflow steps should use a model and which should not.
  3. 02Your first Amazon Bedrock model callSend one request to a hosted model through Amazon Bedrock, read the reply and its token usage, and handle the two errors beginners hit most.
  4. 03From free text to a validated recordTurn a plain-English work request into a strict, validated data structure, and reject bad or hostile input with deterministic code outside the model.
  5. 04Your first Strands agent with a local toolWrap the intake behavior in a Strands agent, give it one read-only lookup tool, and watch the agent loop decide when to call it.
  6. 05Connect an allow-listed MCP toolGive the agent a tool hosted by a separate server over MCP, treat that server as an untrusted boundary, and let only two read-only tools through a deterministic allow-list.
  7. 06Remember one preference across sessionsGive the agent long-term memory for exactly one harmless preference, key it on a synthetic identity that is never the user's email, and see why the recall step needs a real cloud resource.
  8. 07Test behavior, safety, and failure pathsProve the agent is safe with a fast offline test suite: schema and tool-contract tests, a prompt-injection case, a tool-failure case, and a tiny fixed eval set that records latency and tokens without asserting exact prose.
  9. 08Describe the cloud in code with AWS CDKRead the two real CDK stacks that define the capstone's cloud, run cdk synth to turn that TypeScript into CloudFormation templates, and name every resource each stack creates — all offline, with no AWS account touched.
  10. 09Deploy the agent and invoke it in the cloudBuild the agent's linux/arm64 container image, push it to the repository the stack creates, deploy the agent stack with CDK, and invoke the running agent with the AWS CLI — with the exact commands and a prominent cost note.
  11. 10Observe, estimate cost, and tear it all downFind the deployed agent's logs, traces, and metrics in CloudWatch, understand the runtime, model, and memory cost model, debug without leaking prompts, then destroy every tutorial resource and verify nothing billable is left.