AI LabsbyThe Ops ToolboxOps Toolbox
All examples
Live demo

Orchestrated Agents on AWS Bedrock

Multi-step Q&A on AWS — full agent mode when configured, honest fallback pipeline when not.

Multi-step workflowsEnterprise
Jump to demo

You're handling a multi-part customer question — follow retrieve, classify, and answer steps (or full agent mode when configured).

Assistant workflow

Retrieve context, classify intent, and draft an answer.

Support operationsMulti-step enquiry
Live
Scenario: Bedrock IAM patterns
Platform · Runbook agentIAM
Account
shared-services
Agent
bedrock-platform-assist
Question
IAM for Bedrock agents
KB
KB-OPS-RUNBOOKS
User
Cloud platform eng

Customer question

Case studyArchitecture, governance, and how to adapt this pattern in a pilot

Business use case

Problem

AWS-first teams want an orchestration pattern that can start small (few steps) and grow into a fully-managed agent platform without rewriting every app.

Who benefits

  • Platform teams, standardize how agents are invoked and audited
  • Security, IAM boundaries enforced per environment/workload
  • Product teams, faster iteration with incremental orchestration steps

Success metrics

  • Prove value with a deterministic multi-step pipeline before provisioning full agents
  • Maintain an AWS-only posture for data residency and IAM controls
  • Provide per-step timing for performance and spend reviews

Solution

This demo supports two modes:

  • Full Bedrock Agent when you have an agent configured in your account
  • Step-by-step pipeline (default) that retrieves context, classifies intent, and drafts an answer — with a visible timeline

Technical implementation

Stack

  • @aws-sdk/client-bedrock-agent-runtime (Agent mode)
  • @aws-sdk/client-bedrock-runtime (Converse mode)

Architecture

Three-step orchestration in the hosted demo: retrieve, classify, then generate via AI Gateway.

How it runs
Drawing the flow…

Implementation highlights

  • Hosted demo runs retrieve → classify → generate with per-step timing
  • Returns a step timeline so the orchestration is visible for governance and tuning

Outcomes and learnings

  • Early pilots can use lighter orchestrations to validate workflows before provisioning full agent tools/KBs
  • Explicit step timelines make performance budgeting practical (p95 by step)
  • IAM should be least-privilege and environment-specific for public demos
Delivery playbookDiscovery → pilot → scale
  1. 1
    Discovery2–4 wks

    Decide between Bedrock Agents vs a lighter orchestrated pipeline; align on IAM boundaries and data residency constraints.

  2. 2
    Pilot6–8 wks

    Start with orchestrated steps (retrieve/context, classify, answer) to validate usefulness before provisioning full agent tooling.

  3. 3
    Scaleongoing

    Move to Bedrock Agents with guardrails and KB-backed retrieval; add per-team roles and production-grade observability.

Where else this appliesMulti-step Bedrock flows matter when you need agent-like behaviour but want to phase in Bedrock Agents, guardrails, and KBs on your timeline.

Supply chain exception handling

Retrieve shipment context, classify exception type, propose resolution playbooks.

Cloud cost anomaly triage

Pull CUR context, classify spike drivers, suggest remediation runbooks.

Security operations copilot

Retrieve runbooks and ticket history, classify incident type, draft containment steps for analyst approval.

Product support macros

Orchestrate retrieval and response before suggesting Zendesk macro text.

Start with an orchestrated pipeline in Lambda or Step Functions calling Converse; promote to Bedrock Agents when tool use and memory requirements justify the ops overhead.