AWS bedrock documentation change

Service: bedrock · 2026-06-10 · Documentation low

File: bedrock/latest/userguide/agents-how.md

Summary

Restructured content about agent operations: simplified image captions and moved detailed descriptions to body text for better readability.

Security assessment

Purely presentational changes with no security implications. Modifications only affect how existing technical information is organized without altering security controls or introducing security-related content.

Diff

diff --git a/bedrock/latest/userguide/agents-how.md b/bedrock/latest/userguide/agents-how.md
index 7ae35f3ae..8d69fceb9 100644
--- a//bedrock/latest/userguide/agents-how.md
+++ b//bedrock/latest/userguide/agents-how.md
@@ -56 +56,3 @@ At build-time, all these components are gathered to construct base prompts for t
-![How build-time APIs construct your agent. An action group consists of an OpenAPI schema and a Lambda function to define what API operations an agent can call and how the agent should handle the requests and responses. The agent synthesizes information from the base prompt templates, instructions provided to it, and any attached action groups and knowledge bases to generate prompts with the model that it uses. The prompts are added to the agent's prompt store.](/images/bedrock/latest/userguide/images/agents/agents-buildtime.png)
+![How build-time APIs construct your agent with action groups and knowledge bases.](/images/bedrock/latest/userguide/images/agents/agents-buildtime.png)
+
+An action group consists of an OpenAPI schema and a Lambda function to define what API operations an agent can call and how the agent should handle the requests and responses. The agent synthesizes information from the base prompt templates, instructions provided to it, and any attached action groups and knowledge bases to generate prompts with the model that it uses. The prompts are added to the agent's prompt store.
@@ -91 +93,3 @@ As the user session with the agent continues through more `InvokeAgent` requests
-![How your agent works in runtime. After receiving user input, the agent fetches augmented prompts from the prompt store and conversation history from the sessions store. If the preprocessing step is enabled, the agent invokes the FM with the preprocessing prompt to validate the user input. In the orchestration step, the agent invokes the FM with the orchestration prompt and parses the response. It then determines action groups and queries knowledge bases as necessary and generates an observation that might trigger a new orchestration prompt. The orchestration stage loops until the observation returns a final response to the user.](/images/bedrock/latest/userguide/images/agents/agents-runtime.png)
+![How your agent processes user input at runtime through orchestration and action execution.](/images/bedrock/latest/userguide/images/agents/agents-runtime.png)
+
+After receiving user input, the agent fetches augmented prompts from the prompt store and conversation history from the sessions store. If the preprocessing step is enabled, the agent invokes the FM with the preprocessing prompt to validate the user input. In the orchestration step, the agent invokes the FM with the orchestration prompt and parses the response. It then determines action groups and queries knowledge bases as necessary and generates an observation that might trigger a new orchestration prompt. The orchestration stage loops until the observation returns a final response to the user.