AWS prescriptive-guidance documentation change

Service: prescriptive-guidance · 2026-07-10 · Documentation low

File: prescriptive-guidance/latest/agentic-ai-foundations/generative-ai-agents.md

Summary

Updated image path and converted bold headings to proper markdown subheadings (###)

Security assessment

Changes are purely cosmetic (image path update) and structural (heading formatting). No security-related content was added, modified, or referenced. The modifications don't impact security documentation or address vulnerabilities.

Diff

diff --git a/prescriptive-guidance/latest/agentic-ai-foundations/generative-ai-agents.md b/prescriptive-guidance/latest/agentic-ai-foundations/generative-ai-agents.md
index 1a60eb367..fc64439ec 100644
--- a//prescriptive-guidance/latest/agentic-ai-foundations/generative-ai-agents.md
+++ b//prescriptive-guidance/latest/agentic-ai-foundations/generative-ai-agents.md
@@ -13 +13 @@ The following diagram illustrates how large language models (LLMs) now serve as
-![Agent architecture with Perceive, Reason, and Act stages, using LLM for goals and planning.](/images/prescriptive-guidance/latest/agentic-ai-foundations/images/gen-ai-modules.png)
+![](/images/prescriptive-guidance/latest/agentic-ai-foundations/images/guide-img/bf0cde42-baef-4bee-8fff-ca482667d2b6/images/7e2e2c89-16b8-4520-8ecb-f14ea7c73f40.png)
@@ -36 +36 @@ Unlike traditional agents, which stored long-term memory in structured knowledge
-**Agent store: external long-term memory**
+### Agent store: external long-term memory
@@ -40 +40 @@ Agent state, user history, decisions, and outcomes are stored in a long-term age
-**RAG**
+### RAG
@@ -44 +44 @@ RAG enhances LLM performance by combining retrieved knowledge with generative ca
-**In-context learning and prompt chaining**
+### In-context learning and prompt chaining
@@ -48 +48 @@ Agents maintain short-term memory by using in-session token context and structur
-**Continued pretraining and fine-tuning**
+### Continued pretraining and fine-tuning