Agents & GenAI Application Architecture

Bedrock Agents, tool use, and how the pieces — models, knowledge bases, guardrails — assemble into applications.

8 min read

LLMs generate text — but real tasks need *actions*: look up an order, book a meeting, call an API. Agents wrap an LLM in a loop that can plan multi-step tasks, call tools/APIs, observe results, and continue until the goal is done.

Amazon Bedrock Agents

  • You define the agent's instructions, available action groups (APIs/Lambda functions), and optional knowledge bases.
  • The agent breaks a request into steps, calls the right actions with the right parameters, and synthesizes the final answer.
  • Example: "Cancel my order and email me confirmation" → look up order → call cancel API → trigger email → confirm to user.
  • Guardrails and IAM permissions constrain what the agent can see and do.
Think of it like this

A plain LLM is a brilliant advisor behind glass — it can only talk. An agent hands that advisor a phone, a company directory, and permission to make calls on your behalf (with limits you set).

A reference GenAI architecture

  1. Frontend calls your backend (API Gateway + Lambda, or an app on ECS).
  2. Guardrails screen the user input (and later, the output).
  3. Knowledge Base retrieval fetches relevant company context (RAG).
  4. Bedrock model (or Agent, if actions are needed) generates the response.
  5. Observability: prompts, outputs, and API calls logged via CloudWatch and CloudTrail.
Exam tip

Keyword map: "multi-step task / call APIs / take actions" → Bedrock Agents. "answer from documents" → Knowledge Bases (RAG). "block harmful topics or PII in prompts/responses" → Bedrock Guardrails.

Knowledge check
Question 1 of 3

A travel app needs its AI assistant to check flight availability via an API, book the flight, and email an itinerary — all from one user request. Which Bedrock capability enables this?