Build a careful AI helper — Bedrock and Guardrail configuration

Your goal

Create an AI guardrail configuration and customize its blocked-input message.

Why this matters

An AI application needs explicit safety settings and clear limits. You will create a guardrail configuration and change its blocked-input message. This exercise does not call a model or prove the guardrail catches harmful content.

Words you will use

A guardrail describes checks and response settings for AI use. A draft is an editable version. A blocked-input message is the text configured for a rejected request. This lab does not test a model.

How to proceed

Start a fresh emulator, read each numbered step, and enter the practice settings shown. Run the action, inspect its API receipt, then continue. Finish lab checks the emulator state again before saving your progress.

1. Create a guardrail draft

Create a Bedrock guardrail draft with a content-filter setting and practice response messages. The emulator stores the configuration; this exercise does not call a trained model.

2. Write the input guidance

Enter a short message explaining that an input cannot be handled. Save it on the guardrail draft. A helpful message should guide the visitor without revealing private system details.

Practice message: Type a short message that you can recognize in the API result. Suggested practice value: Hello from my lab.

3. Read the draft back

Retrieve the DRAFT version and compare its blocked-input message with your text. This verifies a configuration change, not the accuracy or safety of a model’s answers.

Practice, then check your understanding

Perform the actions yourself and inspect the returned state. Errors keep your settings so you can retry. Starting another lab clears the previous live environment. Earned XP is kept, and signed-in achievements sync to your account. Replay does not award duplicate XP.

Read the official AWS documentation for service behavior and production details.