- Lab
-
Libraries: If you want this lab, consider one of these libraries.
- Cloud
Diagnosing and Correcting Unstable Bedrock Behavior
In this challenge lab, you will investigate an Amazon Bedrock-powered prototype that is operating outside its expected value boundaries. You will review previously collected operational results, identify the source of excessive token usage, and examine the prototype's predefined inference configurations to determine which operational control is responsible for the observed behavior. You will then apply a focused configuration correction and execute the same predefined workload using the corrected configuration. Finally, you will review the resulting validation data and verify that the prototype now operates within its defined token usage boundary. Successful validation produces a deterministic artifact in Amazon S3, providing measurable evidence that the correction restored expected operational behavior without relying on the quality of AI-generated responses.
Lab Info
Table of Contents
-
Challenge
Correct the prototype configuration
In CloudShell apply a focused configuration correction that restores the prototype to its expected operational boundary.
- Download the lab files linked-to in the Additional Resources section.
- Create an S3 bucket whose name begins with
bedrock-validation-to store the validation. - Note the issue indicated in the
operational_results.jsonfile, and fix this inprototype_config.json: Change itsactive_profilevalue to the correct profile.
-
Challenge
Validate the corrected prototype
Execute the corrected prototype by running the downloaded
.pyfile, and verify that its operational behavior satisfies the defined validation requirements, with the newtoken_usage_statusvalue now showingPASS.Successful execution uploads
validation.jsonto your S3 bucket, and that artifact contains the deterministic evidence. -
Challenge
Produce a validation artifact
Manually verify that successful validation creates the expected
validation.jsonartifact in your S3 bucket.
Real skill practice before real-world application
Hands-on Labs are real environments created by industry experts to help you learn. These environments help you gain knowledge and experience, practice without compromising your system, test without risk, destroy without fear, and let you learn from your mistakes. Hands-on Labs: practice your skills before delivering in the real world.
Learn by doing
Engage hands-on with the tools and technologies you’re learning. You pick the skill, we provide the credentials and environment.
Follow your guide
All labs have detailed instructions and objectives, guiding you through the learning process and ensuring you understand every step.
Turn time into mastery
On average, you retain 75% more of your learning if you take time to practice. Hands-on labs set you up for success to make those skills stick.