AWS bedrock documentation change
Summary
Added links to related documentation throughout, removed a tutorial video note, and enhanced explanations about policy refinement and testing workflows.
Security assessment
The changes focus on improving documentation clarity by adding references to concepts, best practices, and troubleshooting guides. No security vulnerabilities, incidents, or security-specific features are mentioned. Changes are routine documentation improvements for usability.
Diff
diff --git a/bedrock/latest/userguide/kiro-cli-automated-reasoning-policy.md b/bedrock/latest/userguide/kiro-cli-automated-reasoning-policy.md index 4cfe66acc..4ab2d2e96 100644 --- a//bedrock/latest/userguide/kiro-cli-automated-reasoning-policy.md +++ b//bedrock/latest/userguide/kiro-cli-automated-reasoning-policy.md @@ -9 +9 @@ PrerequisitesGetting startedResolving policy issuesInteracting with a policyEdit -You can use Kiro CLI to ask questions about your Automated Reasoning policies, understand the behavior of the various rules, and request changes that address failing tests or ambiguities in the policy itself. +You can use Kiro CLI to ask questions about your Automated Reasoning policies, understand the behavior of the various rules, and request changes that address failing tests or ambiguities in the policy itself. Kiro CLI is particularly useful for the iterative refinement workflow described in [Troubleshoot and refine your Automated Reasoning policy](./address-failed-automated-reasoning-tests.html) because it can load your policy definition, analyze test results, and apply annotations through natural language conversation. @@ -20,0 +21,2 @@ To use Kiro CLI with your Automated Reasoning policies, you must first complete + * Familiarize yourself with Automated Reasoning checks concepts, particularly policies, rules, variables, and findings. For more information, see [Automated Reasoning checks concepts](./automated-reasoning-checks-concepts.html). + @@ -66 +68 @@ You can use Kiro CLI to resolve policy issues reported in the policy report. Fir -The quality report includes a list of the unused variables, conflicting rules, and disjointed rules and other potential issues with the policy. +The quality report includes a list of the unused variables, conflicting rules, and disjointed rules and other potential issues with the policy. For more information about interpreting the quality report, see [Use the quality report](./address-failed-automated-reasoning-tests.html#use-quality-report). @@ -68 +70 @@ The quality report includes a list of the unused variables, conflicting rules, a -Conflicting rules will cause your policy to respond with `IMPOSSIBLE` to all validation requests. You can ask Kiro CLI to explain the conflict and propose a solution: +Conflicting rules will cause your policy to respond with `IMPOSSIBLE` to all validation requests. For more information about conflicting rules and how to resolve them, see [Conflicts in the policy](./address-failed-automated-reasoning-tests.html#fix-impossible-policy-conflicts). You can ask Kiro CLI to explain the conflict and propose a solution: @@ -73 +75 @@ Conflicting rules will cause your policy to respond with `IMPOSSIBLE` to all val -Unused variables can cause validation result to return `TRANSLATION_AMBIGUOUS` results. You can ask Kiro CLI to help with this issue: +Unused variables can cause validation results to return `TRANSLATION_AMBIGUOUS` results. For more information about why unused variables cause issues, see [Unused variables](./automated-reasoning-policy-best-practices.html#bp-anti-unused-variables). You can ask Kiro CLI to help with this issue: @@ -78 +80 @@ Unused variables can cause validation result to return `TRANSLATION_AMBIGUOUS` r -Similarly, ambiguous variable that are semantically similar can cause validation result to return `TRANSLATION_AMBIGUOUS` results. You can ask Kiro CLI to help with this issue: +Similarly, ambiguous variables that are semantically similar can cause validation results to return `TRANSLATION_AMBIGUOUS` results. For more information about overlapping variables and how to fix them, see [Overlapping variables](./automated-reasoning-policy-best-practices.html#bp-anti-overlapping-variables) and [Overlapping variable definitions](./address-failed-automated-reasoning-tests.html#fix-overlapping-variables). You can ask Kiro CLI to help with this issue: @@ -94 +96 @@ You can use Kiro CLI to explore your policy. For example, you could ask Kiro CLI -You can also use Kiro CLI to add functionality to the policy. Automated Reasoning policies often work around some key output variables that capture the user intent. For example, the sample homework submission policy uses an `isSubmissionAcceptable` variable as the output of its rules. You can use Kiro CLI to alter the policy to capture other possible user questions. +You can also use Kiro CLI to add functionality to the policy. Automated Reasoning policies often work around some key output variables that capture the user intent. For example, the sample homework submission policy uses an `isSubmissionAcceptable` variable as the output of its rules. You can use Kiro CLI to alter the policy to capture other possible user questions. When adding new rules, follow the best practices described in [Automated Reasoning policy best practices](./automated-reasoning-policy-best-practices.html), particularly [Use implications (=>) to structure rules](./automated-reasoning-policy-best-practices.html#bp-use-implications). @@ -144,6 +145,0 @@ Once Kiro CLI confirms the annotations are ready, you can open your policy in th -###### Note - -**Tutorial video:** For a step-by-step walkthrough of reviewing and applying annotations, watch the following tutorial: - -[Tutorial Demo 3 - Refining the Automated Reasoning policy](https://youtu.be/YmohVGWr_PA) - @@ -157 +153 @@ After applying the annotations, ask Kiro CLI to reload the latest build of the p -A good way to test that your Automated Reasoning policy can validate natural language generated by your application is to use tests. After creating test Q&As with their expected results, you can use Kiro CLI to understand why a test did not return the expected result and adjust the policy. For more information about creating and running tests, see [Test an Automated Reasoning policy](./test-automated-reasoning-policy.html). +A good way to test that your Automated Reasoning policy can validate natural language generated by your application is to use tests. After creating test Q&As with their expected results, you can use Kiro CLI to understand why a test did not return the expected result and adjust the policy. For more information about creating and running tests, see [Test an Automated Reasoning policy](./test-automated-reasoning-policy.html). For a systematic approach to diagnosing test failures without Kiro CLI, see [Troubleshoot and refine your Automated Reasoning policy](./address-failed-automated-reasoning-tests.html). @@ -169 +165 @@ A good way to test that your Automated Reasoning policy can validate natural lan -When suggesting rule changes, Kiro CLI may try to overfit to the specific example and create rules that are not useful in other use cases. Check the test output and give Kiro CLI guidance to focus it on the right problem. +When suggesting rule changes, Kiro CLI may try to overfit to the specific example and create rules that are not useful in other use cases. Check the test output and give Kiro CLI guidance to focus it on the right problem. For guidance on writing effective rules, see [Automated Reasoning policy best practices](./automated-reasoning-policy-best-practices.html). @@ -187,0 +184,2 @@ Once you are happy with the Automated Reasoning policy, you can deploy it for us +After deploying your policy, see [Integrate Automated Reasoning checks in your application](./integrate-automated-reasoning-checks.html) for guidance on using Automated Reasoning checks at runtime to validate LLM responses and act on the feedback. + @@ -745 +743 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Address failed Automated Reasoning policy tests +Troubleshoot and refine your policy